Showing 1–50 of 6,528 results for author: Suen, Y

DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy

Authors: Ming Dai, Wenxuan Cheng, Jiang-jiang Liu, Sen Yang, Wenxiao Cai, Yanpeng Sun, Wankou Yang

Abstract: Referring Image Segmentation (RIS) is a challenging task that aims to segment objects in an image based on natural language expressions. While prior studies have predominantly concentrated on improving vision-language interactions and achieving fine-grained localization, a systematic analysis of the fundamental bottlenecks in existing RIS frameworks remains underexplored. To bridge this gap, we pr… ▽ More Referring Image Segmentation (RIS) is a challenging task that aims to segment objects in an image based on natural language expressions. While prior studies have predominantly concentrated on improving vision-language interactions and achieving fine-grained localization, a systematic analysis of the fundamental bottlenecks in existing RIS frameworks remains underexplored. To bridge this gap, we propose DeRIS, a novel framework that decomposes RIS into two key components: perception and cognition. This modular decomposition facilitates a systematic analysis of the primary bottlenecks impeding RIS performance. Our findings reveal that the predominant limitation lies not in perceptual deficiencies, but in the insufficient multi-modal cognitive capacity of current models. To mitigate this, we propose a Loopback Synergy mechanism, which enhances the synergy between the perception and cognition modules, thereby enabling precise segmentation while simultaneously improving robust image-text comprehension. Additionally, we analyze and introduce a simple non-referent sample conversion data augmentation to address the long-tail distribution issue related to target existence judgement in general scenarios. Notably, DeRIS demonstrates inherent adaptability to both non- and multi-referents scenarios without requiring specialized architectural modifications, enhancing its general applicability. The codes and models are available at https://github.com/Dmmm1997/DeRIS. △ Less

Submitted 2 July, 2025; originally announced July 2025.

Comments: ICCV 2025

GPT, But Backwards: Exactly Inverting Language Model Outputs

Authors: Adrians Skapars, Edoardo Manino, Youcheng Sun, Lucas C. Cordeiro

Abstract: While existing auditing techniques attempt to identify potential unwanted behaviours in large language models (LLMs), we address the complementary forensic problem of reconstructing the exact input that led to an existing LLM output - enabling post-incident analysis and potentially the detection of fake output reports. We formalize exact input reconstruction as a discrete optimisation problem with… ▽ More While existing auditing techniques attempt to identify potential unwanted behaviours in large language models (LLMs), we address the complementary forensic problem of reconstructing the exact input that led to an existing LLM output - enabling post-incident analysis and potentially the detection of fake output reports. We formalize exact input reconstruction as a discrete optimisation problem with a unique global minimum and introduce SODA, an efficient gradient-based algorithm that operates on a continuous relaxation of the input search space with periodic restarts and parameter decay. Through comprehensive experiments on LLMs ranging in size from 33M to 3B parameters, we demonstrate that SODA significantly outperforms existing approaches. We succeed in fully recovering 79.5% of shorter out-of-distribution inputs from next-token logits, without a single false positive, but struggle to extract private information from the outputs of longer (15+ token) input sequences. This suggests that standard deployment practices may currently provide adequate protection against malicious use of our method. Our code is available at https://doi.org/10.5281/zenodo.15539879. △ Less

Submitted 2 July, 2025; originally announced July 2025.

Comments: 9 pages, ICML 2025 Workshop on Reliable and Responsible Foundation Models

Age Sensitive Hippocampal Functional Connectivity: New Insights from 3D CNNs and Saliency Mapping

Authors: Yifei Sun, Marshall A. Dalton, Robert D. Sanders, Yixuan Yuan, Xiang Li, Sharon L. Naismith, Fernando Calamante, Jinglei Lv

Abstract: Grey matter loss in the hippocampus is a hallmark of neurobiological aging, yet understanding the corresponding changes in its functional connectivity remains limited. Seed-based functional connectivity (FC) analysis enables voxel-wise mapping of the hippocampus's synchronous activity with cortical regions, offering a window into functional reorganization during aging. In this study, we develop an… ▽ More Grey matter loss in the hippocampus is a hallmark of neurobiological aging, yet understanding the corresponding changes in its functional connectivity remains limited. Seed-based functional connectivity (FC) analysis enables voxel-wise mapping of the hippocampus's synchronous activity with cortical regions, offering a window into functional reorganization during aging. In this study, we develop an interpretable deep learning framework to predict brain age from hippocampal FC using a three-dimensional convolutional neural network (3D CNN) combined with LayerCAM saliency mapping. This approach maps key hippocampal-cortical connections, particularly with the precuneus, cuneus, posterior cingulate cortex, parahippocampal cortex, left superior parietal lobule, and right superior temporal sulcus, that are highly sensitive to age. Critically, disaggregating anterior and posterior hippocampal FC reveals distinct mapping aligned with their known functional specializations. These findings provide new insights into the functional mechanisms of hippocampal aging and demonstrate the power of explainable deep learning to uncover biologically meaningful patterns in neuroimaging data. △ Less

Submitted 2 July, 2025; originally announced July 2025.

Prompt Mechanisms in Medical Imaging: A Comprehensive Survey

Authors: Hao Yang, Xinlong Liang, Zhang Li, Yue Sun, Zheyu Hu, Xinghe Xie, Behdad Dashtbozorg, Jincheng Huang, Shiwei Zhu, Luyi Han, Jiong Zhang, Shanshan Wang, Ritse Mann, Qifeng Yu, Tao Tan

Abstract: Deep learning offers transformative potential in medical imaging, yet its clinical adoption is frequently hampered by challenges such as data scarcity, distribution shifts, and the need for robust task generalization. Prompt-based methodologies have emerged as a pivotal strategy to guide deep learning models, providing flexible, domain-specific adaptations that significantly enhance model performa… ▽ More Deep learning offers transformative potential in medical imaging, yet its clinical adoption is frequently hampered by challenges such as data scarcity, distribution shifts, and the need for robust task generalization. Prompt-based methodologies have emerged as a pivotal strategy to guide deep learning models, providing flexible, domain-specific adaptations that significantly enhance model performance and adaptability without extensive retraining. This systematic review critically examines the burgeoning landscape of prompt engineering in medical imaging. We dissect diverse prompt modalities, including textual instructions, visual prompts, and learnable embeddings, and analyze their integration for core tasks such as image generation, segmentation, and classification. Our synthesis reveals how these mechanisms improve task-specific outcomes by enhancing accuracy, robustness, and data efficiency and reducing reliance on manual feature engineering while fostering greater model interpretability by making the model's guidance explicit. Despite substantial advancements, we identify persistent challenges, particularly in prompt design optimization, data heterogeneity, and ensuring scalability for clinical deployment. Finally, this review outlines promising future trajectories, including advanced multimodal prompting and robust clinical integration, underscoring the critical role of prompt-driven AI in accelerating the revolution of diagnostics and personalized treatment planning in medicine. △ Less

Submitted 27 June, 2025; originally announced July 2025.

On the angular momentum of many-nucleon states

Authors: Junchao Guo, Yang Sun

Abstract: We propose a new method to construct total angular momentum of many-nucleon states. We find that when restoring the broken rotational symmetry of the product state by angular momentum projection, the restrictions on the total states required by the fermionic antisymmetry are completely absorbed into the single j space. For different j shells, any total angular momentum that obeys the selection rul… ▽ More We propose a new method to construct total angular momentum of many-nucleon states. We find that when restoring the broken rotational symmetry of the product state by angular momentum projection, the restrictions on the total states required by the fermionic antisymmetry are completely absorbed into the single j space. For different j shells, any total angular momentum that obeys the selection rule is allowed, just as for non-identical particles. Our method based on this reorganization changes fundamentally the thinking of the J- and m-schemes and is expected to significantly improve the efficiency of traditional shell models. △ Less

Submitted 1 July, 2025; originally announced July 2025.

Comments: 6 pages, 0 figures

VEDA: Efficient LLM Generation Through Voting-based KV Cache Eviction and Dataflow-flexible Accelerator

Authors: Zhican Wang, Hongxiang Fan, Haroon Waris, Gang Wang, Zhenyu Li, Jianfei Jiang, Yanan Sun, Guanghui He

Abstract: Large Language Models (LLMs) excel in natural language processing tasks but pose significant computational and memory challenges for edge deployment due to their intensive resource demands. This work addresses the efficiency of LLM inference by algorithm-hardware-dataflow tri-optimizations. We propose a novel voting-based KV cache eviction algorithm, balancing hardware efficiency and algorithm acc… ▽ More Large Language Models (LLMs) excel in natural language processing tasks but pose significant computational and memory challenges for edge deployment due to their intensive resource demands. This work addresses the efficiency of LLM inference by algorithm-hardware-dataflow tri-optimizations. We propose a novel voting-based KV cache eviction algorithm, balancing hardware efficiency and algorithm accuracy by adaptively identifying unimportant kv vectors. From a dataflow perspective, we introduce a flexible-product dataflow and a runtime reconfigurable PE array for matrix-vector multiplication. The proposed approach effectively handles the diverse dimensional requirements and solves the challenges of incrementally varying sequence lengths. Additionally, an element-serial scheduling scheme is proposed for nonlinear operations, such as softmax and layer normalization (layernorm). Results demonstrate a substantial reduction in latency, accompanied by a significant decrease in hardware complexity, from O(N) to O(1). The proposed solution is realized in a custom-designed accelerator, VEDA, which outperforms existing hardware platforms. This research represents a significant advancement in LLM inference on resource-constrained edge devices, facilitating real-time processing, enhancing data privacy, and enabling model customization. △ Less

Submitted 1 July, 2025; originally announced July 2025.

Comments: DAC 2025

Monolayer Two-dimensional Materials Database (ML2DDB) and Applications

Authors: Zhongwei Liu, Zhimin Zhang, Xuwei Liu, Mingjia Yao, Xin He, Yuanhui Sun, Xin Chen, Lijun Zhang

Abstract: The discovery of two-dimensional (2D) materials with tailored properties is critical to meet the increasing demands of high-performance applications across flexible electronics, optoelectronics, catalysis, and energy storage. However, current 2D material databases are constrained by limited scale and compositional diversity. In this study, we introduce a scalable active learning workflow that inte… ▽ More The discovery of two-dimensional (2D) materials with tailored properties is critical to meet the increasing demands of high-performance applications across flexible electronics, optoelectronics, catalysis, and energy storage. However, current 2D material databases are constrained by limited scale and compositional diversity. In this study, we introduce a scalable active learning workflow that integrates deep neural networks with density functional theory (DFT) calculations to efficiently explore a vast set of candidate structures. These structures are generated through physics-informed elemental substitution strategies, enabling broad and systematic discovery of stable 2D materials. Through six iterative screening cycles, we established the creation of the Monolayer 2D Materials Database (ML2DDB), which contains 242,546 DFT-validated stable structures-an order-of-magnitude increase over the largest known 2D materials databases. In particular, the number of ternary and quaternary compounds showed the most significant increase. Combining this database with a generative diffusion model, we demonstrated effective structure generation under specified chemistry and symmetry constraints. This work accomplished an organically interconnected loop of 2D material data expansion and application, which provides a new paradigm for the discovery of new materials. △ Less

Submitted 1 July, 2025; originally announced July 2025.

Just Noticeable Difference for Large Multimodal Models

Authors: Zijian Chen, Yuan Tian, Yuze Sun, Wei Sun, Zicheng Zhang, Weisi Lin, Guangtao Zhai, Wenjun Zhang

Abstract: Just noticeable difference (JND), the minimum change that the human visual system (HVS) can perceive, has been studied for decades. Although recent work has extended this line of research into machine vision, there has been a scarcity of studies systematically exploring its perceptual boundaries across multiple tasks and stimulus types, particularly in the current era of rapidly advancing large mu… ▽ More Just noticeable difference (JND), the minimum change that the human visual system (HVS) can perceive, has been studied for decades. Although recent work has extended this line of research into machine vision, there has been a scarcity of studies systematically exploring its perceptual boundaries across multiple tasks and stimulus types, particularly in the current era of rapidly advancing large multimodal models (LMMs), where studying the multifaceted capabilities of models has become a mainstream focus. Moreover, the perceptual defects of LMMs are not investigated thoroughly, resulting in potential security issues and suboptimal response efficiency. In this paper, we take an initial attempt and demonstrate that there exist significant visual blind spots in current LMMs. To systemically quantify this characteristic, we propose a new concept, {\bf LMM-JND}, together with its determination pipeline. Targeting uncovering the behavior commonalities in HVS-aligned visual perception tasks, we delve into several LMM families and construct a large-scale dataset, named VPA-JND, which contains 21.5k reference images with over 489k stimuli across 12 distortion types, to facilitate LMM-JND studies. VPA-JND exposes areas where state-of-the-art LMMs, including GPT-4o and the InternVL2.5 series, struggle with basic comparison queries and fall significantly short of human-level visual performance. We further explore the effects of vision and language backbones and find a notable correlation between their design philosophy that may instruct the future refinement of LMMs for their visual acuity. Together, our research underscores the significance of LMM-JND as a unique perspective for studying LMMs, and predictable LMM-JND is crucial for security concerns. This work will be available at https://github.com/zijianchen98/LMM-JND. △ Less

Submitted 2 July, 2025; v1 submitted 1 July, 2025; originally announced July 2025.

Comments: 19 pages, 19 figures

Theoretical Modeling of LLM Self-Improvement Training Dynamics Through Solver-Verifier Gap

Authors: Yifan Sun, Yushan Liang, Zhen Zhang, Jiaye Teng

Abstract: Self-improvement is among the most prominent techniques within the realm of large language models (LLM), aiming to enhance the LLM performance without relying on external data. Despite its significance, generally how LLM performances evolve during the self-improvement process remains underexplored. In this paper, we theoretically model the training dynamics of self-improvement via the concept of s… ▽ More Self-improvement is among the most prominent techniques within the realm of large language models (LLM), aiming to enhance the LLM performance without relying on external data. Despite its significance, generally how LLM performances evolve during the self-improvement process remains underexplored. In this paper, we theoretically model the training dynamics of self-improvement via the concept of solver-verifier gap. This is inspired by the conjecture that the performance enhancement of self-improvement stems from the gap between LLM's solver capability and verifier capability. Based on the theoretical framework, we further introduce how to predict the ultimate power of self-improvement using only information from the first few training epochs. We empirically validate the effectiveness of the theoretical model on various LLMs and datasets. Beyond self-improvement, we extend our analysis to investigate how external data influences these dynamics within the framework. Notably, we find that under limited external data regimes, such external data can be utilized at any stage without significantly affecting final performances, which accords with the empirical observations. △ Less

Submitted 29 June, 2025; originally announced July 2025.

Comments: 24 pages

DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World

Authors: Xiangtai Li, Tao Zhang, Yanwei Li, Haobo Yuan, Shihao Chen, Yikang Zhou, Jiahao Meng, Yueyi Sun, Shilin Xu, Lu Qi, Tianheng Cheng, Yi Lin, Zilong Huang, Wenhao Huang, Jiashi Feng, Guang Shi

Abstract: Multimodal Large Language Models (MLLMs) demonstrate a complex understanding of scenes, benefiting from large-scale and high-quality datasets. Most existing caption datasets lack the ground locations and relations for visual entities. Several grounded caption datasets face the problems of missing detailed descriptions, relations, and massive object descriptions on high-resolution images. To fill t… ▽ More Multimodal Large Language Models (MLLMs) demonstrate a complex understanding of scenes, benefiting from large-scale and high-quality datasets. Most existing caption datasets lack the ground locations and relations for visual entities. Several grounded caption datasets face the problems of missing detailed descriptions, relations, and massive object descriptions on high-resolution images. To fill this gap for the community, we present DenseWorld-1M, the first massive, detailed, dense grounded caption dataset in the real world. We design a three-stage labeling pipeline, containing open-world perception, detailed object caption generation, and dense caption merging. The first stage obtains entity-level masks and labels. The second stage generates the object-level, detailed captions with the guidance of masks and labels from the first stage. The final stage merges object captions and masks into spatial and relational dense captions. To accelerate the labeling process and improve caption quality, we present two VLM models: the Detailed Region Caption model and the Spatial Caption Merging model. Extensive experiments on various settings, including vision-language understanding, visual grounding, and region caption generation, demonstrate the effectiveness of our DenseWorld-1M dataset and labeling models. △ Less

Submitted 30 June, 2025; originally announced June 2025.

Comments: Datasets and Models: https://github.com/lxtGH/DenseWorld-1M

Unveiling the Nature and Fate of the Almost-Dark Cloud AGC 226178 through HI Mapping

Authors: Yu-Zhu Sun, Hong-Xin Zhang, Elias Brinks, Rory Smith, Fujia Li, Minsu Kim, Se-Heon Oh, Zesen Lin, Jaebeom Kim, Weibin Sun, Tie Li, Patrick Côté, Alessandro Boselli, Lijun Chen, Pierre-Alain Duc, Sanjaya Paudel, Matthew A. Taylor, Kaixiang Wang, Enci Wang, Lanyue Zhang, Yinghe Zhao

Abstract: The origin of extragalactic, almost dark HI clouds with extreme gas-to-stellar mass ratios remains poorly understood. We investigate the nature and fate of the "almost dark" cloud AGC 226178, projected within the Virgo cluster, with an HI-to-stellar mass ratio of ~1000. We present deep single-dish HI mapping from the Five-hundred-meter Aperture Spherical Telescope (FAST), complemented by high-reso… ▽ More The origin of extragalactic, almost dark HI clouds with extreme gas-to-stellar mass ratios remains poorly understood. We investigate the nature and fate of the "almost dark" cloud AGC 226178, projected within the Virgo cluster, with an HI-to-stellar mass ratio of ~1000. We present deep single-dish HI mapping from the Five-hundred-meter Aperture Spherical Telescope (FAST), complemented by high-resolution interferometric data from the Very Large Array (VLA), as part of the Atomic gas in Virgo Interacting Dwarf galaxies (AVID) project. These observations provide the highest-quality HI analysis to date of such a cloud, combining resolution and sensitivity. FAST data reveal a short, low-velocity tail toward the dwarf galaxy VCC 2034, previously proposed as a possible origin for AGC 226178. However, VCC 2034 shows a line-of-sight asymmetric HI feature and cometary morphology indicating a stripping event unrelated to AGC 226178. VLA data reveal a velocity gradient across AGC 226178 and a clumpy internal structure. The velocity dispersion exceeds the thermal linewidth, implying turbulence or unresolved motions. The cloud cannot be gravitationally bound by atomic gas alone. The resolved HI clumps follow standard HI mass-star formation rate and mass-size relations, with those forming stars reaching surface densities above the threshold for self-shielding. We conclude that AGC 226178 is a free-floating HI cloud of unknown origin. The system appears to be in the process of disintegration. It is likely located well outside the Virgo cluster, as the preservation of its extended HI morphology within the cluster environment would otherwise require a substantial reservoir of unseen molecular gas with a mass exceeding that of the observed HI content. While confinement pressure from the hot intracluster medium may aid its stability, it is unlikely to be the dominant factor preventing its disruption. △ Less

Submitted 29 June, 2025; originally announced June 2025.

Comments: 18 pages, 14 figures. Accepted for Publication in A&A

Are Large Language Models Capable of Deep Relational Reasoning? Insights from DeepSeek-R1 and Benchmark Comparisons

Authors: Chi Chiu So, Yueyue Sun, Jun-Min Wang, Siu Pang Yung, Anthony Wai Keung Loh, Chun Pong Chau

Abstract: How far are Large Language Models (LLMs) in performing deep relational reasoning? In this paper, we evaluate and compare the reasoning capabilities of three cutting-edge LLMs, namely, DeepSeek-R1, DeepSeek-V3 and GPT-4o, through a suite of carefully designed benchmark tasks in family tree and general graph reasoning. Our experiments reveal that DeepSeek-R1 consistently achieves the highest F1-scor… ▽ More How far are Large Language Models (LLMs) in performing deep relational reasoning? In this paper, we evaluate and compare the reasoning capabilities of three cutting-edge LLMs, namely, DeepSeek-R1, DeepSeek-V3 and GPT-4o, through a suite of carefully designed benchmark tasks in family tree and general graph reasoning. Our experiments reveal that DeepSeek-R1 consistently achieves the highest F1-scores across multiple tasks and problem sizes, demonstrating strong aptitude in logical deduction and relational inference. However, all evaluated models, including DeepSeek-R1, struggle significantly as problem complexity increases, largely due to token length limitations and incomplete output structures. A detailed analysis of DeepSeek-R1's long Chain-of-Thought responses uncovers its unique planning and verification strategies, but also highlights instances of incoherent or incomplete reasoning, calling attention to the need for deeper scrutiny into LLMs' internal inference dynamics. We further discuss key directions for future work, including the role of multimodal reasoning and the systematic examination of reasoning failures. Our findings provide both empirical insights and theoretical implications for advancing LLMs' reasoning abilities, particularly in tasks that demand structured, multi-step logical inference. Our code repository will be publicly available at https://github.com/kelvinhkcs/Deep-Relational-Reasoning. △ Less

Submitted 29 June, 2025; originally announced June 2025.

Comments: 10 pages, 0 figures, accepted by 2025 IEEE international conference on artificial intelligence testing (AITest)

FuzzCoh: Robust Canonical Coherence-Based Fuzzy Clustering of Multivariate Time Series

Authors: Ziling Ma, Mara Sherlin Talento, Ying Sun, Hernando Ombao

Abstract: Brain cognitive and sensory functions are often associated with electrophysiological activity at specific frequency bands. Clustering multivariate time series (MTS) data like EEGs is important for understanding brain functions but challenging due to complex non-stationary cross-dependencies, gradual transitions between cognitive states, noisy measurements, and ambiguous cluster boundaries. To addr… ▽ More Brain cognitive and sensory functions are often associated with electrophysiological activity at specific frequency bands. Clustering multivariate time series (MTS) data like EEGs is important for understanding brain functions but challenging due to complex non-stationary cross-dependencies, gradual transitions between cognitive states, noisy measurements, and ambiguous cluster boundaries. To address these issues, we develop a robust fuzzy clustering framework in the spectral domain. Our method leverages Kendall's tau-based canonical coherence, which extracts meaningful frequency-specific monotonic relationships between groups of channels or regions. KenCoh effectively captures dominant coherence structures while remaining robust against outliers and noise, making it suitable for real EEG datasets that typically contain artifacts. Our method first projects each MTS object onto vectors derived from the KenCoh estimates (i.e, canonical directions), which capture relevant information on the connectivity structure of oscillatory signals in predefined frequency bands. These spectral features are utilized to determine clusters of epochs using a fuzzy partitioning strategy, accommodating gradual transitions and overlapping class structure. Lastly, we demonstrate the effectiveness of our approach to EEG data where latent cognitive states such as alertness and drowsiness exhibit frequency-specific dynamics and ambiguity. Our method captures both spectral and spatial features by locating the frequency-dependent structure and brain functional connectivity. Built on the KenCoh framework for fuzzy clustering, it handles the complexity of high-dimensional time series data and is broadly applicable to domains such as neuroscience, wearable sensing, environmental monitoring, and finance. △ Less

Submitted 28 June, 2025; originally announced June 2025.

Brightening interlayer excitons by electric-field-driven hole transfer in bilayer WSe2

Authors: Tianyi Ouyang, Erfu Liu, Soonyoung Cha, Raj Kumar Paudel, Yiyang Sun, Zhaoran Xu, Takashi Taniguchi, Kenji Watanabe, Nathaniel M. Gabor, Yia-Chung Chang, Chun Hung Lui

Abstract: We observe the interlayer A1s^I, A2s^I, and B1s^I excitons in bilayer WSe2 under applied electric fields using reflectance contrast spectroscopy. Remarkably, these interlayer excitons remain optically bright despite being well separated from symmetry-matched intralayer excitons-a regime where conventional two-level coupling models fail unless unphysically large coupling strengths are assumed. To u… ▽ More We observe the interlayer A1s^I, A2s^I, and B1s^I excitons in bilayer WSe2 under applied electric fields using reflectance contrast spectroscopy. Remarkably, these interlayer excitons remain optically bright despite being well separated from symmetry-matched intralayer excitons-a regime where conventional two-level coupling models fail unless unphysically large coupling strengths are assumed. To uncover the origin of this brightening, we perform density functional theory (DFT) calculations and find that the applied electric field distorts the valence-band Bloch states, driving the hole wavefunction from one layer to the other. This field-driven interlayer hole transfer imparts intralayer character to the interlayer excitons, thereby enhancing their oscillator strength without requiring hybridization with bright intralayer states. Simulations confirm that this mechanism accounts for the major contribution to the observed brightness, with excitonic hybridization playing only a minor role. Our results identify interlayer hole transfer as a robust and general mechanism for brightening interlayer excitons in bilayer transition metal dichalcogenides (TMDs), especially when inter- and intralayer excitons are energetically well separated. △ Less

Submitted 27 June, 2025; originally announced June 2025.

Comments: 10 pages, 4 figures

The real-time data processing and acquisition system for Project 8 Phase II

Authors: A. Ashtari Esfahani, A. Banducci, S. Böser, N. Buzinsky, R. Cervantes, C. Claessens, L. de Viveiros, M. Fertl, J. A. Formaggio, L. Gladstone, M. Grando, M. Guigue, J. Hartse, K. M. Heeger, A. M. Jones, K. Kazkaz, B. H. LaRoque, A. Lindman, B. Monreal, J. A. Nikkel, E. Novitski, N. S. Oblath, W. Pettus, R. G. H. Robertson, G. Rybka , et al. (14 additional authors not shown)

Abstract: In Phase II of the Project 8 neutrino mass experiment, electrons from the decays of tritium or ${}^{83\mathrm{m}}$Kr are detected via their $\approx$26 GHz cyclotron radiation while contained within a circular waveguide. The signal from a given electron is characterized as a brief chirp, lasting $\lesssim$10 ms and changing in frequency by $\lesssim$1 MHz/ms. To detect these signals, the Project 8… ▽ More In Phase II of the Project 8 neutrino mass experiment, electrons from the decays of tritium or ${}^{83\mathrm{m}}$Kr are detected via their $\approx$26 GHz cyclotron radiation while contained within a circular waveguide. The signal from a given electron is characterized as a brief chirp, lasting $\lesssim$10 ms and changing in frequency by $\lesssim$1 MHz/ms. To detect these signals, the Project 8 collaboration developed a data acquisition (DAQ) system tailored to the signal properties. The DAQ is responsible for simultaneously selecting up to three 100 MHz-wide frequency windows to study, detect, and trigger on likely signals from different electron kinetic energies, and for writing the relevant data to disk. We describe the Phase II DAQ system in detail and address how the system was used for data-taking operations. △ Less

Submitted 27 June, 2025; originally announced June 2025.

Comments: 22 pages, 19 figures

UniCA: Adapting Time Series Foundation Model to General Covariate-Aware Forecasting

Authors: Lu Han, Yu Liu, Qiwen Deng, Jian Jiang, Yinbo Sun, Zhe Yu, Binfeng Wang, Xingyu Lu, Lintao Ma, Han-Jia Ye, De-Chuan Zhan

Abstract: Time Series Foundation Models (TSFMs) have achieved remarkable success through large-scale pretraining. However, their design primarily targets real-valued series, limiting their ability to handle general forecasting tasks involving diverse and often heterogeneous covariates--such as categorical variables and multimodal data (e.g., images, text)--which are typically task-specific and difficult to… ▽ More Time Series Foundation Models (TSFMs) have achieved remarkable success through large-scale pretraining. However, their design primarily targets real-valued series, limiting their ability to handle general forecasting tasks involving diverse and often heterogeneous covariates--such as categorical variables and multimodal data (e.g., images, text)--which are typically task-specific and difficult to leverage during pretraining. To address this gap, we propose Unified Covariate Adaptation (UniCA), a framework to bridge TSFMs with general covariate-aware forecasting. UniCA first performs covariate homogenization to transform heterogeneous covariates into high-level homogeneous series representations and then fuses them via a unified attention-based fusion mechanism. UniCA is compatible and universal for adaptation with both homogeneous and heterogeneous covariates, incorporating extra covariate information while preserving the generalization ability of TSFMs.Extensive experiments on multiple unimodal and multimodal covariate-aware forecasting benchmarks demonstrate the superiority of UniCA, highlighting the promise of covariate-aware TSFM adaptation in real-world forecasting scenarios. Codes are released on https://github.com/hanlu-nju/UniCA. △ Less

Submitted 27 June, 2025; originally announced June 2025.

Dual-Perspective United Transformer for Object Segmentation in Optical Remote Sensing Images

Authors: Yanguang Sun, Jiexi Yan, Jianjun Qian, Chunyan Xu, Jian Yang, Lei Luo

Abstract: Automatically segmenting objects from optical remote sensing images (ORSIs) is an important task. Most existing models are primarily based on either convolutional or Transformer features, each offering distinct advantages. Exploiting both advantages is valuable research, but it presents several challenges, including the heterogeneity between the two types of features, high complexity, and large pa… ▽ More Automatically segmenting objects from optical remote sensing images (ORSIs) is an important task. Most existing models are primarily based on either convolutional or Transformer features, each offering distinct advantages. Exploiting both advantages is valuable research, but it presents several challenges, including the heterogeneity between the two types of features, high complexity, and large parameters of the model. However, these issues are often overlooked in existing the ORSIs methods, causing sub-optimal segmentation. For that, we propose a novel Dual-Perspective United Transformer (DPU-Former) with a unique structure designed to simultaneously integrate long-range dependencies and spatial details. In particular, we design the global-local mixed attention, which captures diverse information through two perspectives and introduces a Fourier-space merging strategy to obviate deviations for efficient fusion. Furthermore, we present a gated linear feed-forward network to increase the expressive ability. Additionally, we construct a DPU-Former decoder to aggregate and strength features at different layers. Consequently, the DPU-Former model outperforms the state-of-the-art methods on multiple datasets. Code: https://github.com/CSYSI/DPU-Former. △ Less

Submitted 26 June, 2025; originally announced June 2025.

Comments: Accepted by IJCAI 2025

Hierarchical Reasoning Model

Authors: Guan Wang, Jin Li, Yuhao Sun, Xing Chen, Changling Liu, Yue Wu, Meng Lu, Sen Song, Yasin Abbasi Yadkori

Abstract: Reasoning, the process of devising and executing complex goal-oriented action sequences, remains a critical challenge in AI. Current large language models (LLMs) primarily employ Chain-of-Thought (CoT) techniques, which suffer from brittle task decomposition, extensive data requirements, and high latency. Inspired by the hierarchical and multi-timescale processing in the human brain, we propose th… ▽ More Reasoning, the process of devising and executing complex goal-oriented action sequences, remains a critical challenge in AI. Current large language models (LLMs) primarily employ Chain-of-Thought (CoT) techniques, which suffer from brittle task decomposition, extensive data requirements, and high latency. Inspired by the hierarchical and multi-timescale processing in the human brain, we propose the Hierarchical Reasoning Model (HRM), a novel recurrent architecture that attains significant computational depth while maintaining both training stability and efficiency. HRM executes sequential reasoning tasks in a single forward pass without explicit supervision of the intermediate process, through two interdependent recurrent modules: a high-level module responsible for slow, abstract planning, and a low-level module handling rapid, detailed computations. With only 27 million parameters, HRM achieves exceptional performance on complex reasoning tasks using only 1000 training samples. The model operates without pre-training or CoT data, yet achieves nearly perfect performance on challenging tasks including complex Sudoku puzzles and optimal path finding in large mazes. Furthermore, HRM outperforms much larger models with significantly longer context windows on the Abstraction and Reasoning Corpus (ARC), a key benchmark for measuring artificial general intelligence capabilities. These results underscore HRM's potential as a transformative advancement toward universal computation and general-purpose reasoning systems. △ Less

Submitted 26 June, 2025; originally announced June 2025.

TOMD: A Trail-based Off-road Multimodal Dataset for Traversable Pathway Segmentation under Challenging Illumination Conditions

Authors: Yixin Sun, Li Li, Wenke E, Amir Atapour-Abarghouei, Toby P. Breckon

Abstract: Detecting traversable pathways in unstructured outdoor environments remains a significant challenge for autonomous robots, especially in critical applications such as wide-area search and rescue, as well as incident management scenarios like forest fires. Existing datasets and models primarily target urban settings or wide, vehicle-traversable off-road tracks, leaving a substantial gap in addressi… ▽ More Detecting traversable pathways in unstructured outdoor environments remains a significant challenge for autonomous robots, especially in critical applications such as wide-area search and rescue, as well as incident management scenarios like forest fires. Existing datasets and models primarily target urban settings or wide, vehicle-traversable off-road tracks, leaving a substantial gap in addressing the complexity of narrow, trail-like off-road scenarios. To address this, we introduce the Trail-based Off-road Multimodal Dataset (TOMD), a comprehensive dataset specifically designed for such environments. TOMD features high-fidelity multimodal sensor data -- including 128-channel LiDAR, stereo imagery, GNSS, IMU, and illumination measurements -- collected through repeated traversals under diverse conditions. We also propose a dynamic multiscale data fusion model for accurate traversable pathway prediction. The study analyzes the performance of early, cross, and mixed fusion strategies under varying illumination levels. Results demonstrate the effectiveness of our approach and the relevance of illumination in segmentation performance. We publicly release TOMD at https://github.com/yyyxs1125/TMOD to support future research in trail-based off-road navigation. △ Less

Submitted 24 June, 2025; originally announced June 2025.

Comments: 8 pages, 9 figures, 2025 IJCNN

Visualization and manipulation of four-leaf clover-shaped electronic state in cuprate

Authors: Zechao Wang, Fengyu Yao, Yuchen Huo, Zhongxu Wei, Zhiyuan Song, Mingqiang Ren, Ziyuan Cheng, Jinfeng Jia, Yu-Jie Sun, Qi-Kun Xue

Abstract: High-Tc superconductivity in cuprates arises from carrier doping of an antiferromagnetic Mott insulator. Associated with these changes are spectral-weight transfers from the high-energy to low-energy, giving rise to a variety of intriguing electronic phenomena. In this study, for the first time, we discovered a 2a0 sized four-leaf clover-shaped (FLC) electronic state at low-energy, accompanied wit… ▽ More High-Tc superconductivity in cuprates arises from carrier doping of an antiferromagnetic Mott insulator. Associated with these changes are spectral-weight transfers from the high-energy to low-energy, giving rise to a variety of intriguing electronic phenomena. In this study, for the first time, we discovered a 2a0 sized four-leaf clover-shaped (FLC) electronic state at low-energy, accompanied with the emergence of a characteristic "kink" around 16meV. With increasing doping, the number of FLC pattern decreases and ultimately vanishes in the overdoped region. Remarkably, we achieved real-time electric-field manipulation of this FLC state, through innovative in-situ scanning tunneling microscopy probe. This novel FLC state may not only redefine our understanding of precursor states of pairing, but also reveals its crucial role as a tunable electronic phase in high-Tc superconductors. △ Less

Submitted 26 June, 2025; originally announced June 2025.

Comments: 12 pages, 4 figres,

Diverse polymorphs and phase transitions in van der Waals In$_2$Se$_3$

Authors: Mingfeng Liu, Jiantao Wang, Peitao Liu, Qiang Wang, Zhibo Liu, Yan Sun, Xing-Qiu Chen

Abstract: Van der Waals In$_2$Se$_3$ has garnered significant attention due to its unique properties and wide applications associated with its rich polymorphs and polymorphic phase transitions. Despite extensive studies, the vast complex polymorphic phase space remains largely unexplored, and the underlying microscopic mechanism for their phase transformations remains elusive. Here, we develop a highly accu… ▽ More Van der Waals In$_2$Se$_3$ has garnered significant attention due to its unique properties and wide applications associated with its rich polymorphs and polymorphic phase transitions. Despite extensive studies, the vast complex polymorphic phase space remains largely unexplored, and the underlying microscopic mechanism for their phase transformations remains elusive. Here, we develop a highly accurate, efficient, and reliable machine-learning potential (MLP), which not only facilitates accurate exploration of the intricate potential energy surface (PES), but also enables us to conduct large-scale molecular dynamics (MD) simulations with first-principles accuracy. We identify the accurate structure of the $β''$ polymorph and uncover several previously unreported $β'$ polymorph variants exhibiting dynamic stability and competing energies, which are elucidated by characteristic flat imaginary phonon bands and the distinctive Mexican-hat-like PES in the $β$ polymorph. Through the MLP-accelerated MD simulations, we directly observe the polymorphic phase transformations among the $α$, $β$, $β'$, and $β''$ polymorphs under varying temperature and pressure conditions, and build for the first time an ab initio temperature-pressure phase diagram, showing good agreement with experiments. Furthermore, our MD simulations reveal a novel strain-induced reversible phase transition between the $β'$ and $β''$ polymorphs. This work not only unveils diverse polymorphs in van der Waals In$_2$Se$_3$, but also provides crucial atomic insights into their phase transitions, opening new avenues for the design of novel functional electronic devices. △ Less

Submitted 26 June, 2025; originally announced June 2025.

Comments: 32 pages, 20 figures (including Supplementary Information)

JUNO 20-inch PMT and electronics system characterization using large pulses of PMT dark counts at the Pan-Asia testing platform

Authors: Caimei Liu, Min Li, Narongkiat Rodphai, Zhimin Wang, Jun Hu, Nikolay Anfimov, Lei Fan, Alberto Garfagnini, Guanghua Gong, Shaojing Hou, Xiaolu Ji, Xiaoshan Jiang, Denis Korablev, Tobias Lachenmaier, Si Ma, Xiaoyan Ma, Zhe Ning, Alexander G. Olshevskiy, Zhaoyuan Peng, Zhonghua Qin, Tobias Sterr, Yunhua Sun, Alexander Felix Tietzsch, Jun Wang, Wei Wang , et al. (13 additional authors not shown)

Abstract: The main goal of the JUNO experiment is to determine the neutrino mass ordering with a 20kt liquid-scintillator detector. The 20-inch PMT and its 1F3 (one for three) electronics are crucial to realize the excellent energy resolution of at least 3% at 1MeV. The knowledge on the PMT and 1F3 electronics response is critical for detector performance understanding. A study of the JUNO 20-inch PMT and 1… ▽ More The main goal of the JUNO experiment is to determine the neutrino mass ordering with a 20kt liquid-scintillator detector. The 20-inch PMT and its 1F3 (one for three) electronics are crucial to realize the excellent energy resolution of at least 3% at 1MeV. The knowledge on the PMT and 1F3 electronics response is critical for detector performance understanding. A study of the JUNO 20-inch PMT and 1F3 electronics system characterization is presented using large pulses of PMT dark count at the Pan-Asia testing platform in China. Thanks to its broad amplitude range and high rate, the large pulse signals are also used to investigate the PMT after pulse response. △ Less

Submitted 26 June, 2025; originally announced June 2025.

Efficient Skill Discovery via Regret-Aware Optimization

Authors: He Zhang, Ming Zhou, Shaopeng Zhai, Ying Sun, Hui Xiong

Abstract: Unsupervised skill discovery aims to learn diverse and distinguishable behaviors in open-ended reinforcement learning. For existing methods, they focus on improving diversity through pure exploration, mutual information optimization, and learning temporal representation. Despite that they perform well on exploration, they remain limited in terms of efficiency, especially for the high-dimensional s… ▽ More Unsupervised skill discovery aims to learn diverse and distinguishable behaviors in open-ended reinforcement learning. For existing methods, they focus on improving diversity through pure exploration, mutual information optimization, and learning temporal representation. Despite that they perform well on exploration, they remain limited in terms of efficiency, especially for the high-dimensional situations. In this work, we frame skill discovery as a min-max game of skill generation and policy learning, proposing a regret-aware method on top of temporal representation learning that expands the discovered skill space along the direction of upgradable policy strength. The key insight behind the proposed method is that the skill discovery is adversarial to the policy learning, i.e., skills with weak strength should be further explored while less exploration for the skills with converged strength. As an implementation, we score the degree of strength convergence with regret, and guide the skill discovery with a learnable skill generator. To avoid degeneration, skill generation comes from an up-gradable population of skill generators. We conduct experiments on environments with varying complexities and dimension sizes. Empirical results show that our method outperforms baselines in both efficiency and diversity. Moreover, our method achieves a 15% zero shot improvement in high-dimensional environments, compared to existing methods. △ Less

Submitted 26 June, 2025; originally announced June 2025.

ClusterRCA: Network Failure Diagnosis in HPC Systems Using Multimodal Data

Authors: Yongqian Sun, Xijie Pan, Xiao Xiong, Lei Tao, Jiaju Wang, Shenglin Zhang, Yuan Yuan, Yuqi Li, Kunlin Jian

Abstract: Network failure diagnosis is challenging yet critical for high-performance computing (HPC) systems. Existing methods cannot be directly applied to HPC scenarios due to data heterogeneity and lack of accuracy. This paper proposes a novel framework, called ClusterRCA, to localize culprit nodes and determine failure types by leveraging multimodal data. ClusterRCA extracts features from topologically… ▽ More Network failure diagnosis is challenging yet critical for high-performance computing (HPC) systems. Existing methods cannot be directly applied to HPC scenarios due to data heterogeneity and lack of accuracy. This paper proposes a novel framework, called ClusterRCA, to localize culprit nodes and determine failure types by leveraging multimodal data. ClusterRCA extracts features from topologically connected network interface controller (NIC) pairs to analyze the diverse, multimodal data in HPC systems. To accurately localize culprit nodes and determine failure types, ClusterRCA combines classifier-based and graph-based approaches. A failure graph is constructed based on the output of the state classifier, and then it performs a customized random walk on the graph to localize the root cause. Experiments on datasets collected by a top-tier global HPC device vendor show ClusterRCA achieves high accuracy in diagnosing network failure for HPC systems. ClusterRCA also maintains robust performance across different application scenarios. △ Less

Submitted 17 June, 2025; originally announced June 2025.

The MALATANG survey: Dense gas distribution on sub-kiloparsec scales across the disk of M82

Authors: Jian-Fa Wang, Yu Gao, Qing-Hua Tan, Xue-Jian Jiang, Li Ji, Zhi-Yu Zhang, Jun-Zhi Wang, Jun-Feng Wang, R. Thomas Greve, Yan Jiang, Ashley Bemis, Elias Brinks, Aeree Chung, J. Malcolm Currie, Richard de Grijs, Taotao Fang, C. Luis Ho, Bumhyun Lee, Satoki Matsushita, Michał Michałowski, Soojong Pak, Panomporn Poojon, G. Mark Rawlings, Amelie Saintonge, Yi-Chen Sun , et al. (1 additional authors not shown)

Abstract: We present observations of HCN J=4-3 and HCO^+ J=4-3 lines obtained with the James Clerk Maxwell Telescope as part of the MALATANG survey, combined with archival HCN J=1-0 and HCO^+ J=1-0 data from the Green Bank Telescope, to study the spatial distribution and excitation conditions of dense molecular gas in the disk of M82. We detect HCN J=4-3 and HCO^+ J=4-3 emission within the central region (<… ▽ More We present observations of HCN J=4-3 and HCO^+ J=4-3 lines obtained with the James Clerk Maxwell Telescope as part of the MALATANG survey, combined with archival HCN J=1-0 and HCO^+ J=1-0 data from the Green Bank Telescope, to study the spatial distribution and excitation conditions of dense molecular gas in the disk of M82. We detect HCN J=4-3 and HCO^+ J=4-3 emission within the central region (< 500 pc) of the galaxy, while the J=1-0 emission lines exhibit a more extended spatial distribution (> 700 pc). The dense gas shows a clear double-lobed structure in both spatial distribution and kinematics, with the HCN and HCO^+ J=4-3 lines in the southwest lobe blueshifted by ~ 40 km/s relative to the J=1-0 lines. The HCN J=4-3/1-0 and HCO^+ J=4-3/1-0 line-luminosity ratios range from 0.09 to 0.53 and from 0.14 to 0.87, respectively, with mean values of 0.18 +/- 0.04 and 0.36 +/- 0.06. The HCN ratio is lower than the typical average observed in nearby star-forming galaxies, whereas the HCO^+ ratio is comparatively higher, suggesting that the high-J HCN emission in M82 is significantly sub-thermally excited. Spatially, the peak values of the J=4-3/1-0 ratios are found in the northwest region of M82, coinciding with the galaxy-scale outflow. Elevated HCN/HCO^+ ratios are also detected in roughly the same area, potentially tracing local excitation enhancements driven by the outflow. The HCN/HCO^+ J=4-3 ratio across all detected regions ranges from 0.19 to 1.07 with a mean value of 0.41 +/- 0.11, which is significantly lower than the average J=1-0 ratio of 0.76 +/- 0.08. Both ratios are significantly lower than the average values observed in nearby star-forming galaxies, which could be related to the relatively low gas density and the presence of an extended photo-dissociation region in M82. △ Less

Submitted 26 June, 2025; v1 submitted 25 June, 2025; originally announced June 2025.

Surrogate-Assisted Evolution for Efficient Multi-branch Connection Design in Deep Neural Networks

Authors: Fergal Stapleton, Daniel García Núñez, Yanan Sun, Edgar Galván

Abstract: State-of-the-art Deep Neural Networks (DNNs) often incorporate multi-branch connections, enabling multi-scale feature extraction and enhancing the capture of diverse features. This design improves network capacity and generalisation to unseen data. However, training such DNNs can be computationally expensive. The challenge is further exacerbated by the complexity of identifying optimal network arc… ▽ More State-of-the-art Deep Neural Networks (DNNs) often incorporate multi-branch connections, enabling multi-scale feature extraction and enhancing the capture of diverse features. This design improves network capacity and generalisation to unseen data. However, training such DNNs can be computationally expensive. The challenge is further exacerbated by the complexity of identifying optimal network architectures. To address this, we leverage Evolutionary Algorithms (EAs) to automatically discover high-performing architectures, a process commonly known as neuroevolution. We introduce a novel approach based on Linear Genetic Programming (LGP) to encode multi-branch (MB) connections within DNNs, referred to as NeuroLGP-MB. To efficiently design the DNNs, we use surrogate-assisted EAs. While their application in simple artificial neural networks has been influential, we scale their use from dozens or hundreds of sample points to thousands, aligning with the demands of complex DNNs by incorporating a semantic-based approach in our surrogate-assisted EA. Furthermore, we introduce a more advanced surrogate model that outperforms baseline, computationally expensive, and simpler surrogate models. △ Less

Submitted 25 June, 2025; originally announced June 2025.

Comments: GECCO '25 Companion: Proceedings of the Companion Conference on Genetic and Evolutionary Computation (2025)

An Agentic System for Rare Disease Diagnosis with Traceable Reasoning

Authors: Weike Zhao, Chaoyi Wu, Yanjie Fan, Xiaoman Zhang, Pengcheng Qiu, Yuze Sun, Xiao Zhou, Yanfeng Wang, Ya Zhang, Yongguo Yu, Kun Sun, Weidi Xie

Abstract: Rare diseases collectively affect over 300 million individuals worldwide, yet timely and accurate diagnosis remains a pervasive challenge. This is largely due to their clinical heterogeneity, low individual prevalence, and the limited familiarity most clinicians have with rare conditions. Here, we introduce DeepRare, the first rare disease diagnosis agentic system powered by a large language model… ▽ More Rare diseases collectively affect over 300 million individuals worldwide, yet timely and accurate diagnosis remains a pervasive challenge. This is largely due to their clinical heterogeneity, low individual prevalence, and the limited familiarity most clinicians have with rare conditions. Here, we introduce DeepRare, the first rare disease diagnosis agentic system powered by a large language model (LLM), capable of processing heterogeneous clinical inputs. The system generates ranked diagnostic hypotheses for rare diseases, each accompanied by a transparent chain of reasoning that links intermediate analytic steps to verifiable medical evidence. DeepRare comprises three key components: a central host with a long-term memory module; specialized agent servers responsible for domain-specific analytical tasks integrating over 40 specialized tools and web-scale, up-to-date medical knowledge sources, ensuring access to the most current clinical information. This modular and scalable design enables complex diagnostic reasoning while maintaining traceability and adaptability. We evaluate DeepRare on eight datasets. The system demonstrates exceptional diagnostic performance among 2,919 diseases, achieving 100% accuracy for 1013 diseases. In HPO-based evaluations, DeepRare significantly outperforms other 15 methods, like traditional bioinformatics diagnostic tools, LLMs, and other agentic systems, achieving an average Recall@1 score of 57.18% and surpassing the second-best method (Reasoning LLM) by a substantial margin of 23.79 percentage points. For multi-modal input scenarios, DeepRare achieves 70.60% at Recall@1 compared to Exomiser's 53.20% in 109 cases. Manual verification of reasoning chains by clinical experts achieves 95.40% agreements. Furthermore, the DeepRare system has been implemented as a user-friendly web application http://raredx.cn/doctor. △ Less

Submitted 25 June, 2025; originally announced June 2025.

AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models

Authors: Zehuan Huang, Haoran Feng, Yangtian Sun, Yuanchen Guo, Yanpei Cao, Lu Sheng

Abstract: We present AnimaX, a feed-forward 3D animation framework that bridges the motion priors of video diffusion models with the controllable structure of skeleton-based animation. Traditional motion synthesis methods are either restricted to fixed skeletal topologies or require costly optimization in high-dimensional deformation spaces. In contrast, AnimaX effectively transfers video-based motion knowl… ▽ More We present AnimaX, a feed-forward 3D animation framework that bridges the motion priors of video diffusion models with the controllable structure of skeleton-based animation. Traditional motion synthesis methods are either restricted to fixed skeletal topologies or require costly optimization in high-dimensional deformation spaces. In contrast, AnimaX effectively transfers video-based motion knowledge to the 3D domain, supporting diverse articulated meshes with arbitrary skeletons. Our method represents 3D motion as multi-view, multi-frame 2D pose maps, and enables joint video-pose diffusion conditioned on template renderings and a textual motion prompt. We introduce shared positional encodings and modality-aware embeddings to ensure spatial-temporal alignment between video and pose sequences, effectively transferring video priors to motion generation task. The resulting multi-view pose sequences are triangulated into 3D joint positions and converted into mesh animation via inverse kinematics. Trained on a newly curated dataset of 160,000 rigged sequences, AnimaX achieves state-of-the-art results on VBench in generalization, motion fidelity, and efficiency, offering a scalable solution for category-agnostic 3D animation. Project page: \href{https://anima-x.github.io/}{https://anima-x.github.io/}. △ Less

Submitted 24 June, 2025; originally announced June 2025.

Comments: Project page: https://anima-x.github.io/

Multi-Preference Lambda-weighted Listwise DPO for Dynamic Preference Alignment

Authors: Yuhui Sun, Xiyao Wang, Zixi Li, Jinman Zhao

Abstract: While large-scale unsupervised language models (LMs) capture broad world knowledge and reasoning capabilities, steering their behavior toward desired objectives remains challenging due to the lack of explicit supervision. Existing alignment techniques, such as reinforcement learning from human feedback (RLHF), rely on training a reward model and performing reinforcement learning to align with huma… ▽ More While large-scale unsupervised language models (LMs) capture broad world knowledge and reasoning capabilities, steering their behavior toward desired objectives remains challenging due to the lack of explicit supervision. Existing alignment techniques, such as reinforcement learning from human feedback (RLHF), rely on training a reward model and performing reinforcement learning to align with human preferences. However, RLHF is often computationally intensive, unstable, and sensitive to hyperparameters. To address these limitations, Direct Preference Optimization (DPO) was introduced as a lightweight and stable alternative, enabling direct alignment of language models with pairwise preference data via classification loss. However, DPO and its extensions generally assume a single static preference distribution, limiting flexibility in multi-objective or dynamic alignment settings. In this paper, we propose a novel framework: Multi-Preference Lambda-weighted Listwise DPO, which extends DPO to incorporate multiple human preference dimensions (e.g., helpfulness, harmlessness, informativeness) and enables dynamic interpolation through a controllable simplex-weighted formulation. Our method supports both listwise preference feedback and flexible alignment across varying user intents without re-training. Empirical and theoretical analysis demonstrates that our method is as effective as traditional DPO on static objectives while offering greater generality and adaptability for real-world deployment. △ Less

Submitted 26 June, 2025; v1 submitted 24 June, 2025; originally announced June 2025.

Comments: 10 pages, 4 figures, appendix included. To appear in Proceedings of AAAI 2026. Code: https://github.com/yuhui15/Multi-Preference-Lambda-weighted-DPO

ACM Class: I.2.6; I.2.7; I.5.1

Long-range Order in a Short-range Quasi-2D XY Model

Authors: Minghui Hu, Chao Zhang, Dajun Zhang, Yanan Sun, Youjin Deng, Jian-Ping Lv

Abstract: The phase of spins in the quasi-two-dimensional (Q2D) XY model has emerged as a topic of significant interest across multiple physics subfields. Here, we propose a short-range (SR) Q2D XY model defined on a plane perpendicularly intersected by a group of parallel planes, with each plane consisting of nearest-neighbor-coupled XY spins. We perform large-scale Monte Carlo simulations to establish the… ▽ More The phase of spins in the quasi-two-dimensional (Q2D) XY model has emerged as a topic of significant interest across multiple physics subfields. Here, we propose a short-range (SR) Q2D XY model defined on a plane perpendicularly intersected by a group of parallel planes, with each plane consisting of nearest-neighbor-coupled XY spins. We perform large-scale Monte Carlo simulations to establish the full phase diagram of the Q2D XY model, aided by finite-size scaling. A long-range (LR) ordered phase emerges in the Q2D model when the spins on the parallel planes develop a Berezinskii-Kosterlitz-Thouless critical phase. In the LR ordered phase, ordering is anisotropic: LR correlations develop along the direction of the intersection lines, while critical correlations emerge perpendicular to them. Furthermore, the LR ordered phase exhibits Goldstone-mode physics. Our study hence reveals the existence of LR order in a Q2D XY model with finite SR couplings and opens up a new avenue to explore superfluid orders in low dimensions. △ Less

Submitted 24 June, 2025; originally announced June 2025.

Comments: 17 pages, 9 figures

B0 -> K*0 tau+ tau- Decay: Using Machine Learning to Separate Signal from Background

Authors: Ziyao Xiong, Qixing Deng, Yidan Sun, Junhua Yang

Abstract: This study investigates the rare decay B0 -> K*0 tau+ tau-, which is sensitive to potential violations of lepton flavor universality predicted by the Standard Model. A Monte Carlo simulated dataset containing both signal and the dominant background process B0 -> K*0 D+ D- was used to train and evaluate machine learning classifiers. After feature selection and parameter tuning, two supervised model… ▽ More This study investigates the rare decay B0 -> K*0 tau+ tau-, which is sensitive to potential violations of lepton flavor universality predicted by the Standard Model. A Monte Carlo simulated dataset containing both signal and the dominant background process B0 -> K*0 D+ D- was used to train and evaluate machine learning classifiers. After feature selection and parameter tuning, two supervised models -- Boosted Decision Trees (BDTs) and Fully Connected Neural Networks (FCNNs) -- were trained. Feature engineering was then applied to enhance classification performance. On the test set, the BDT achieved an AUC of 0.912 +/- 0.000 and an F1-score of 0.828 +/- 0.001, while the FCNN reached an AUC of 0.877 +/- 0.000 and an F1-score of 0.799 +/- 0.001. These results demonstrate that both models can robustly separate signal from background in rare decay searches, supporting their application in future LHCb analyses. △ Less

Submitted 24 June, 2025; originally announced June 2025.

Comments: Ziyao Xiong, Qixing Deng, Yidan Sun, and Junhua Yang are co-first authors

Da Yu: Towards USV-Based Image Captioning for Waterway Surveillance and Scene Understanding

Authors: Runwei Guan, Ningwei Ouyang, Tianhao Xu, Shaofeng Liang, Wei Dai, Yafeng Sun, Shang Gao, Songning Lai, Shanliang Yao, Xuming Hu, Ryan Wen Liu, Yutao Yue, Hui Xiong

Abstract: Automated waterway environment perception is crucial for enabling unmanned surface vessels (USVs) to understand their surroundings and make informed decisions. Most existing waterway perception models primarily focus on instance-level object perception paradigms (e.g., detection, segmentation). However, due to the complexity of waterway environments, current perception datasets and models fail to… ▽ More Automated waterway environment perception is crucial for enabling unmanned surface vessels (USVs) to understand their surroundings and make informed decisions. Most existing waterway perception models primarily focus on instance-level object perception paradigms (e.g., detection, segmentation). However, due to the complexity of waterway environments, current perception datasets and models fail to achieve global semantic understanding of waterways, limiting large-scale monitoring and structured log generation. With the advancement of vision-language models (VLMs), we leverage image captioning to introduce WaterCaption, the first captioning dataset specifically designed for waterway environments. WaterCaption focuses on fine-grained, multi-region long-text descriptions, providing a new research direction for visual geo-understanding and spatial scene cognition. Exactly, it includes 20.2k image-text pair data with 1.8 million vocabulary size. Additionally, we propose Da Yu, an edge-deployable multi-modal large language model for USVs, where we propose a novel vision-to-language projector called Nano Transformer Adaptor (NTA). NTA effectively balances computational efficiency with the capacity for both global and fine-grained local modeling of visual features, thereby significantly enhancing the model's ability to generate long-form textual outputs. Da Yu achieves an optimal balance between performance and efficiency, surpassing state-of-the-art models on WaterCaption and several other captioning benchmarks. △ Less

Submitted 30 June, 2025; v1 submitted 23 June, 2025; originally announced June 2025.

Comments: 14 pages, 13 figures

Behavioral Anomaly Detection in Distributed Systems via Federated Contrastive Learning

Authors: Renzi Meng, Heyi Wang, Yumeng Sun, Qiyuan Wu, Lian Lian, Renhan Zhang

Abstract: This paper addresses the increasingly prominent problem of anomaly detection in distributed systems. It proposes a detection method based on federated contrastive learning. The goal is to overcome the limitations of traditional centralized approaches in terms of data privacy, node heterogeneity, and anomaly pattern recognition. The proposed method combines the distributed collaborative modeling ca… ▽ More This paper addresses the increasingly prominent problem of anomaly detection in distributed systems. It proposes a detection method based on federated contrastive learning. The goal is to overcome the limitations of traditional centralized approaches in terms of data privacy, node heterogeneity, and anomaly pattern recognition. The proposed method combines the distributed collaborative modeling capabilities of federated learning with the feature discrimination enhancement of contrastive learning. It builds embedding representations on local nodes and constructs positive and negative sample pairs to guide the model in learning a more discriminative feature space. Without exposing raw data, the method optimizes a global model through a federated aggregation strategy. Specifically, the method uses an encoder to represent local behavior data in high-dimensional space. This includes system logs, operational metrics, and system calls. The model is trained using both contrastive loss and classification loss to improve its ability to detect fine-grained anomaly patterns. The method is evaluated under multiple typical attack types. It is also tested in a simulated real-time data stream scenario to examine its responsiveness. Experimental results show that the proposed method outperforms existing approaches across multiple performance metrics. It demonstrates strong detection accuracy and adaptability, effectively addressing complex anomalies in distributed environments. Through careful design of key modules and optimization of the training mechanism, the proposed method achieves a balance between privacy preservation and detection performance. It offers a feasible technical path for intelligent security management in distributed systems. △ Less

Submitted 23 June, 2025; originally announced June 2025.

Precise Measurement of the $Λ$ Electric Dipole Moment through the Entangled Strange Baryon-Antibaryon System

Authors: BESIII Collaboration, M. Ablikim, M. N. Achasov, P. Adlarson, X. C. Ai, R. Aliberti, A. Amoroso, Q. An, Y. Bai, O. Bakina, Y. Ban, H. -R. Bao, V. Batozskaya, K. Begzsuren, N. Berger, M. Berlowski, M. Bertani, D. Bettoni, F. Bianchi, E. Bianco, A. Bortone, I. Boyko, R. A. Briere, A. Brueggemann, H. Cai , et al. (696 additional authors not shown)

Abstract: The dominance of matter over antimatter in the universe has consistently driven the pursuit of new physics beyond the Standard Model that violates charge-parity symmetry. Unlike the well-constrained electrons and neutrons, strange baryons (hyperons) remain a largely unexplored territory, in which interactions between hyperons and particles from new physics could induce a non-trivial electric dipol… ▽ More The dominance of matter over antimatter in the universe has consistently driven the pursuit of new physics beyond the Standard Model that violates charge-parity symmetry. Unlike the well-constrained electrons and neutrons, strange baryons (hyperons) remain a largely unexplored territory, in which interactions between hyperons and particles from new physics could induce a non-trivial electric dipole moment (EDM). However, direct measurements of hyperon EDMs through spin precession are highly challenging due to their short lifetimes. In this paper, we present a novel method to extract the EDM of the lightest hyperon, $Λ$, using the entangled $Λ$$\overlineΛ$ system. Our result is consistent with zero, achieving a three-order-of-magnitude improvement over the previous upper limit established in the 1980s with comparable statistics, providing stringent constraints on potential new physics. △ Less

Submitted 28 June, 2025; v1 submitted 23 June, 2025; originally announced June 2025.

GuardSet-X: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset

Authors: Mintong Kang, Zhaorun Chen, Chejian Xu, Jiawei Zhang, Chengquan Guo, Minzhou Pan, Ivan Revilla, Yu Sun, Bo Li

Abstract: As LLMs become widespread across diverse applications, concerns about the security and safety of LLM interactions have intensified. Numerous guardrail models and benchmarks have been developed to ensure LLM content safety. However, existing guardrail benchmarks are often built upon ad hoc risk taxonomies that lack a principled grounding in standardized safety policies, limiting their alignment wit… ▽ More As LLMs become widespread across diverse applications, concerns about the security and safety of LLM interactions have intensified. Numerous guardrail models and benchmarks have been developed to ensure LLM content safety. However, existing guardrail benchmarks are often built upon ad hoc risk taxonomies that lack a principled grounding in standardized safety policies, limiting their alignment with real-world operational requirements. Moreover, they tend to overlook domain-specific risks, while the same risk category can carry different implications across different domains. To bridge these gaps, we introduce GuardSet-X, the first massive multi-domain safety policy-grounded guardrail dataset. GuardSet-X offers: (1) broad domain coverage across eight safety-critical domains, such as finance, law, and codeGen; (2) policy-grounded risk construction based on authentic, domain-specific safety guidelines; (3) diverse interaction formats, encompassing declarative statements, questions, instructions, and multi-turn conversations; (4) advanced benign data curation via detoxification prompting to challenge over-refusal behaviors; and (5) \textbf{attack-enhanced instances} that simulate adversarial inputs designed to bypass guardrails. Based on GuardSet-X, we benchmark 19 advanced guardrail models and uncover a series of findings, such as: (1) All models achieve varied F1 scores, with many demonstrating high variance across risk categories, highlighting their limited domain coverage and insufficient handling of domain-specific safety concerns; (2) As models evolve, their coverage of safety risks broadens, but performance on common risk categories may decrease; (3) All models remain vulnerable to optimized adversarial attacks. We believe that \dataset and the unique insights derived from our evaluations will advance the development of policy-aligned and resilient guardrail systems. △ Less

Submitted 25 June, 2025; v1 submitted 17 June, 2025; originally announced June 2025.

DiffRIS: Enhancing Referring Remote Sensing Image Segmentation with Pre-trained Text-to-Image Diffusion Models

Authors: Zhe Dong, Yuzhe Sun, Tianzhu Liu, Yanfeng Gu

Abstract: Referring remote sensing image segmentation (RRSIS) enables the precise delineation of regions within remote sensing imagery through natural language descriptions, serving critical applications in disaster response, urban development, and environmental monitoring. Despite recent advances, current approaches face significant challenges in processing aerial imagery due to complex object characterist… ▽ More Referring remote sensing image segmentation (RRSIS) enables the precise delineation of regions within remote sensing imagery through natural language descriptions, serving critical applications in disaster response, urban development, and environmental monitoring. Despite recent advances, current approaches face significant challenges in processing aerial imagery due to complex object characteristics including scale variations, diverse orientations, and semantic ambiguities inherent to the overhead perspective. To address these limitations, we propose DiffRIS, a novel framework that harnesses the semantic understanding capabilities of pre-trained text-to-image diffusion models for enhanced cross-modal alignment in RRSIS tasks. Our framework introduces two key innovations: a context perception adapter (CP-adapter) that dynamically refines linguistic features through global context modeling and object-aware reasoning, and a progressive cross-modal reasoning decoder (PCMRD) that iteratively aligns textual descriptions with visual regions for precise segmentation. The CP-adapter bridges the domain gap between general vision-language understanding and remote sensing applications, while PCMRD enables fine-grained semantic alignment through multi-scale feature interaction. Comprehensive experiments on three benchmark datasets-RRSIS-D, RefSegRS, and RISBench-demonstrate that DiffRIS consistently outperforms existing methods across all standard metrics, establishing a new state-of-the-art for RRSIS tasks. The significant performance improvements validate the effectiveness of leveraging pre-trained diffusion models for remote sensing applications through our proposed adaptive framework. △ Less

Submitted 22 June, 2025; originally announced June 2025.

OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization

Authors: Yiyou Sun, Shawn Hu, Georgia Zhou, Ken Zheng, Hannaneh Hajishirzi, Nouha Dziri, Dawn Song

Abstract: Recent large-scale language models (LLMs) with long Chain-of-Thought reasoning-such as DeepSeek-R1-have achieved impressive results on Olympiad-level mathematics benchmarks. However, they often rely on a narrow set of strategies and struggle with problems that require a novel way of thinking. To systematically investigate these limitations, we introduce OMEGA-Out-of-distribution Math Problems Eval… ▽ More Recent large-scale language models (LLMs) with long Chain-of-Thought reasoning-such as DeepSeek-R1-have achieved impressive results on Olympiad-level mathematics benchmarks. However, they often rely on a narrow set of strategies and struggle with problems that require a novel way of thinking. To systematically investigate these limitations, we introduce OMEGA-Out-of-distribution Math Problems Evaluation with 3 Generalization Axes-a controlled yet diverse benchmark designed to evaluate three axes of out-of-distribution generalization, inspired by Boden's typology of creativity: (1) Exploratory-applying known problem solving skills to more complex instances within the same problem domain; (2) Compositional-combining distinct reasoning skills, previously learned in isolation, to solve novel problems that require integrating these skills in new and coherent ways; and (3) Transformative-adopting novel, often unconventional strategies by moving beyond familiar approaches to solve problems more effectively. OMEGA consists of programmatically generated training-test pairs derived from templated problem generators across geometry, number theory, algebra, combinatorics, logic, and puzzles, with solutions verified using symbolic, numerical, or graphical methods. We evaluate frontier (or top-tier) LLMs and observe sharp performance degradation as problem complexity increases. Moreover, we fine-tune the Qwen-series models across all generalization settings and observe notable improvements in exploratory generalization, while compositional generalization remains limited and transformative reasoning shows little to no improvement. By isolating and quantifying these fine-grained failures, OMEGA lays the groundwork for advancing LLMs toward genuine mathematical creativity beyond mechanical proficiency. △ Less

Submitted 23 June, 2025; originally announced June 2025.

MARL-MambaContour: Unleashing Multi-Agent Deep Reinforcement Learning for Active Contour Optimization in Medical Image Segmentation

Authors: Ruicheng Zhang, Yu Sun, Zeyu Zhang, Jinai Li, Xiaofan Liu, Au Hoi Fan, Haowei Guo, Puxin Yan

Abstract: We introduce MARL-MambaContour, the first contour-based medical image segmentation framework based on Multi-Agent Reinforcement Learning (MARL). Our approach reframes segmentation as a multi-agent cooperation task focused on generate topologically consistent object-level contours, addressing the limitations of traditional pixel-based methods which could lack topological constraints and holistic st… ▽ More We introduce MARL-MambaContour, the first contour-based medical image segmentation framework based on Multi-Agent Reinforcement Learning (MARL). Our approach reframes segmentation as a multi-agent cooperation task focused on generate topologically consistent object-level contours, addressing the limitations of traditional pixel-based methods which could lack topological constraints and holistic structural awareness of anatomical regions. Each contour point is modeled as an autonomous agent that iteratively adjusts its position to align precisely with the target boundary, enabling adaptation to blurred edges and intricate morphologies common in medical images. This iterative adjustment process is optimized by a contour-specific Soft Actor-Critic (SAC) algorithm, further enhanced with the Entropy Regularization Adjustment Mechanism (ERAM) which dynamically balance agent exploration with contour smoothness. Furthermore, the framework incorporates a Mamba-based policy network featuring a novel Bidirectional Cross-attention Hidden-state Fusion Mechanism (BCHFM). This mechanism mitigates potential memory confusion limitations associated with long-range modeling in state space models, thereby facilitating more accurate inter-agent information exchange and informed decision-making. Extensive experiments on five diverse medical imaging datasets demonstrate the state-of-the-art performance of MARL-MambaContour, highlighting its potential as an accurate and robust clinical application. △ Less

Submitted 23 June, 2025; originally announced June 2025.

CT Radiomics-Based Explainable Machine Learning Model for Accurate Differentiation of Malignant and Benign Endometrial Tumors: A Two-Center Study

Authors: Tingrui Zhang, Honglin Wu, Zekun Jiang, Yingying Wang, Rui Ye, Huiming Ni, Chang Liu, Jin Cao, Xuan Sun, Rong Shao, Xiaorong Wei, Yingchun Sun

Abstract: Aimed to develop and validate a CT radiomics-based explainable machine learning model for diagnosing malignancy and benignity specifically in endometrial cancer (EC) patients. A total of 83 EC patients from two centers, including 46 with malignant and 37 with benign conditions, were included, with data split into a training set (n=59) and a testing set (n=24). The regions of interest (ROIs) were m… ▽ More Aimed to develop and validate a CT radiomics-based explainable machine learning model for diagnosing malignancy and benignity specifically in endometrial cancer (EC) patients. A total of 83 EC patients from two centers, including 46 with malignant and 37 with benign conditions, were included, with data split into a training set (n=59) and a testing set (n=24). The regions of interest (ROIs) were manually segmented from pre-surgical CT scans, and 1132 radiomic features were extracted from the pre-surgical CT scans using Pyradiomics. Six explainable machine learning modeling algorithms were implemented respectively, for determining the optimal radiomics pipeline. The diagnostic performance of the radiomic model was evaluated by using sensitivity, specificity, accuracy, precision, F1 score, confusion matrices, and ROC curves. To enhance clinical understanding and usability, we separately implemented SHAP analysis and feature mapping visualization, and evaluated the calibration curve and decision curve. By comparing six modeling strategies, the Random Forest model emerged as the optimal choice for diagnosing EC, with a training AUC of 1.00 and a testing AUC of 0.96. SHAP identified the most important radiomic features, revealing that all selected features were significantly associated with EC (P < 0.05). Radiomics feature maps also provide a feasible assessment tool for clinical applications. DCA indicated a higher net benefit for our model compared to the "All" and "None" strategies, suggesting its clinical utility in identifying high-risk cases and reducing unnecessary interventions. In conclusion, the CT radiomics-based explainable machine learning model achieved high diagnostic performance, which could be used as an intelligent auxiliary tool for the diagnosis of endometrial cancer. △ Less

Submitted 22 June, 2025; originally announced June 2025.

Comments: 30 pages, 5 figures, 3 tables

Impact of pion tensor force on alpha clustering in $^{20}$Ne

Authors: Zhao Jing Chen, Bao Yuan Sun

Abstract: The nuclear clustering, as a quantum phase transition phenomenon governed by strong interactions, exhibits characteristics that are highly sensitive to the specific features of nuclear forces. Here, we examine how nuclear deformation and tensor forces influence $α$-cluster formation in light nuclei. The axially deformed relativistic Hartree-Fock-Bogoliubov model is utilized to investigate the clus… ▽ More The nuclear clustering, as a quantum phase transition phenomenon governed by strong interactions, exhibits characteristics that are highly sensitive to the specific features of nuclear forces. Here, we examine how nuclear deformation and tensor forces influence $α$-cluster formation in light nuclei. The axially deformed relativistic Hartree-Fock-Bogoliubov model is utilized to investigate the clustering structure of the $^{20}$Ne nucleus, at both the ground state and the excited state with a superdeformed prolate. The nuclear binding energies and the canonical single particle levels are obtained at different quadruple deformation, and the role of tensor force embedded in the Fock diagram of $π$-pseudovector ($π$-PV) coupling is revealed. It is shown that the level branches from the degenerated spherical orbits at the deformed prolate case are enlarged due to the extra contribution from pion-exchanged tensor force. Correspondingly, the excitation energy in this superdeformed prolate state is reduced due to the noncentral tensor interaction, leading to a predicted value which is much closer to the referred threshold for the $2α$ decay mode of $^{20}$Ne. Possible $α$-clustering configurations in $^{20}$Ne are then characterized by examining the nucleonic localization function. Although the contribution to the ground state is relatively small, the density profile and nucleonic localization are significantly changed by the pion tensor force for the superdeformed prolate excited state, as further evidenced by characterising the level mixing in the spherical basis components. The results reveal the extra role of the tensor force, correlated to the evolved single-particle levels with nuclear deformation, in the formation and stability of nuclear clustering. △ Less

Submitted 20 June, 2025; originally announced June 2025.

Comments: 9 pages, 4 figures, 3 tables

Parallel Point-to-Point Shortest Paths and Batch Queries

Authors: Xiaojun Dong, Andy Li, Yan Gu, Yihan Sun

Abstract: We propose Orionet, efficient parallel implementations of Point-to-Point Shortest Paths (PPSP) queries using bidirectional search (BiDS) and other heuristics, with an additional focus on batch PPSP queries. We present a framework for parallel PPSP built on existing single-source shortest paths (SSSP) frameworks by incorporating pruning conditions. As a result, we develop efficient parallel PPSP al… ▽ More We propose Orionet, efficient parallel implementations of Point-to-Point Shortest Paths (PPSP) queries using bidirectional search (BiDS) and other heuristics, with an additional focus on batch PPSP queries. We present a framework for parallel PPSP built on existing single-source shortest paths (SSSP) frameworks by incorporating pruning conditions. As a result, we develop efficient parallel PPSP algorithms based on early termination, bidirectional search, A$^*$ search, and bidirectional A$^*$ all with simple and efficient implementations. We extend our idea to batch PPSP queries, which are widely used in real-world scenarios. We first design a simple and flexible abstraction to represent the batch so PPSP can leverage the shared information of the batch. Orionet formalizes the batch as a query graph represented by edges between queried sources and targets. In this way, we directly extended our PPSP framework to batched queries in a simple and efficient way. We evaluate Orionet on both single and batch PPSP queries using various graph types and distance percentiles of queried pairs, and compare it against two baselines, GraphIt and MBQ. Both of them support parallel single PPSP and A$^*$ using unidirectional search. On 14 graphs we tested, on average, our bidirectional search is 2.9$\times$ faster than GraphIt, and 6.8$\times$ faster than MBQ. Our bidirectional A$^*$ is 4.4$\times$ and 6.2$\times$ faster than the A$^*$ in GraphIt and MBQ, respectively. For batched PPSP queries, we also provide in-depth experimental evaluation, and show that Orionet provides strong performance compared to the plain solutions. △ Less

Submitted 19 June, 2025; originally announced June 2025.

Large Language Models in Argument Mining: A Survey

Authors: Hao Li, Viktor Schlegel, Yizheng Sun, Riza Batista-Navarro, Goran Nenadic

Abstract: Argument Mining (AM), a critical subfield of Natural Language Processing (NLP), focuses on extracting argumentative structures from text. The advent of Large Language Models (LLMs) has profoundly transformed AM, enabling advanced in-context learning, prompt-based generation, and robust cross-domain adaptability. This survey systematically synthesizes recent advancements in LLM-driven AM. We provid… ▽ More Argument Mining (AM), a critical subfield of Natural Language Processing (NLP), focuses on extracting argumentative structures from text. The advent of Large Language Models (LLMs) has profoundly transformed AM, enabling advanced in-context learning, prompt-based generation, and robust cross-domain adaptability. This survey systematically synthesizes recent advancements in LLM-driven AM. We provide a concise review of foundational theories and annotation frameworks, alongside a meticulously curated catalog of datasets. A key contribution is our comprehensive taxonomy of AM subtasks, elucidating how contemporary LLM techniques -- such as prompting, chain-of-thought reasoning, and retrieval augmentation -- have reconfigured their execution. We further detail current LLM architectures and methodologies, critically assess evaluation practices, and delineate pivotal challenges including long-context reasoning, interpretability, and annotation bottlenecks. Conclusively, we highlight emerging trends and propose a forward-looking research agenda for LLM-based computational argumentation, aiming to strategically guide researchers in this rapidly evolving domain. △ Less

Submitted 27 June, 2025; v1 submitted 19 June, 2025; originally announced June 2025.

Comments: Work draft

Role of nuclear and electromagnetic fragmentation in the charge-changing reactions of 18O on carbon and lead targets at around 370 MeV/nucleon

Authors: J. R. Liu, B. -H. Sun, J. W. Zhao, G. Guo, G. S. Li, Z. Z. Li, Y. F. Niu, I. Tanihata, S. Terashima, F. Wang, M. Wang, X. L. Wei, J. Y. Xu, J. C. Zhang, L. H. Zhu, L. C. He, C. Y. Liu, C. G. Lu, W. J. Lin, W. P. Lin, Z. Liu, P. P. Ren, Y. Z. Sun, Z. Y. Sun, J. Wang , et al. (5 additional authors not shown)

Abstract: Charge-changing cross sections (CCCSs) of 18O on carbon (C) and lead (Pb) targets have been measured with an uncertainty of less than 4% at around 370MeV/nucleon. We evaluate the contributions of nucleon-nucleon (NN) and electromagnetic (EM) interactions to CCCSs by considering the direct proton removal process, the charged particle evaporation (CPE) after neutron removal, and the EM excitation. W… ▽ More Charge-changing cross sections (CCCSs) of 18O on carbon (C) and lead (Pb) targets have been measured with an uncertainty of less than 4% at around 370MeV/nucleon. We evaluate the contributions of nucleon-nucleon (NN) and electromagnetic (EM) interactions to CCCSs by considering the direct proton removal process, the charged particle evaporation (CPE) after neutron removal, and the EM excitation. We conclude that the CPE accounts for 12.3% and 5% of CCCSs on C and Pb, respectively. Only less than 1% of CCCSs of 18O is attributed to the EM excitation. Further investigation of projectiles from 18O to 197Au on C, silver (Ag) and Pb targets at 300 and 900MeV/nucleon show that the contribution of EM to CCCSs on Ag and Pb increases with projectile mass numbers and incident energies, and can reach 10% for 197Au on Pb at 900MeV/nucleon. In contrast, the EM contribution to CCCS is negligible for all projectiles on C at both energies. △ Less

Submitted 19 June, 2025; originally announced June 2025.

Universally enhanced superconductivity and coexisting ferroelectricity at oxide interfaces

Authors: Meng Zhang, Ming Qin, Yanqiu Sun, Siyuan Hong, Yanwu Xie

Abstract: The coexistence of superconductivity and ferroelectricity is rare due to their conflicting requirements: superconductivity relies on free charge carriers, whereas ferroelectricity typically occurs in insulating systems. At LaAlO3/KTaO3 interfaces, we demonstrate the coexistence of two-dimensional superconductivity and ferroelectricity, enabled by the unique properties of KTaO3 as a quantum paraele… ▽ More The coexistence of superconductivity and ferroelectricity is rare due to their conflicting requirements: superconductivity relies on free charge carriers, whereas ferroelectricity typically occurs in insulating systems. At LaAlO3/KTaO3 interfaces, we demonstrate the coexistence of two-dimensional superconductivity and ferroelectricity, enabled by the unique properties of KTaO3 as a quantum paraelectric. Systematic gating and poling experiments reveal a universal enhancement of the superconducting transition temperature (Tc) by 0.2-0.6 K and bistable transport properties, including hysteresis, strongly suggesting the existence of switchable ferroelectric polarization in the interfacial conducting layer. Hysteresis loops indicate robust ferroelectricity below 50 K. The Tc enhancement is attributed to ferroelectric polarization-induced reduction in dielectric constant, which narrows the interfacial potential well, confining carriers closer to the interface. The bistability arises from switchable ferroelectric polarization, which modulates the potential well depending on polarization direction. These findings establish a straightforward mechanism coupling ferroelectricity and superconductivity, providing a promising platform for exploring their interplay. △ Less

Submitted 19 June, 2025; originally announced June 2025.

Saltatory targeting strategy in rock-paper-scissors models

Authors: J. Menezes, R. Barbalho, Y. Sun

Abstract: We explore how strategic leaps alter the classic rock-paper-scissors dynamics in spatially structured populations. In our model, individuals can expend energy reserves to jump toward regions with a high density of individuals of the species they dominate in the spatial game. This enables them to eliminate the target organisms and gain new territory, promoting species proliferation. Through stochas… ▽ More We explore how strategic leaps alter the classic rock-paper-scissors dynamics in spatially structured populations. In our model, individuals can expend energy reserves to jump toward regions with a high density of individuals of the species they dominate in the spatial game. This enables them to eliminate the target organisms and gain new territory, promoting species proliferation. Through stochastic, lattice-based simulations, we show that even when the energy allocated to jumping, as opposed to random walking, is low, there is a significant shift in the cyclic dominance balance. This arises from the increased likelihood of the leaping species successfully acquiring territory. Due to the cyclical nature of the game, the dominant species becomes the one that is superior to the jumping species. We investigate how spatial patterns are affected and calculate the changes in characteristic length scales. Additionally, we quantify how saltatory targeting reshapes spatial correlations and drives shifts in population dominance. Finally, we estimate the coexistence probability and find evidence that this behavioural strategy may promote biodiversity among low-mobility organisms but jeopardise long-term coexistence in the case of high-mobility dispersal. These results underscore the profound impact of novel foraging tactics on community structure and provide concrete parameters for ecologists seeking to incorporate behavioural innovation into ecosystem models. △ Less

Submitted 19 June, 2025; originally announced June 2025.

Comments: 7 pages, 6 figures

Hybrid Near-Far Field 6D Movable Antenna Design Exploiting Directional Sparsity and Deep Learning

Authors: Xiaodan Shao, Limei Hu, Yulong Sun, Xing Li, Yixiao Zhang, Jingze Ding, Xiaoming Shi, Feng Chen, Derrick Wing Kwan Ng, Robert Schober

Abstract: Six-dimensional movable antenna (6DMA) has been identified as a new disruptive technology for future wireless systems to support a large number of users with only a few antennas. However, the intricate relationships between the signal carrier wavelength and the transceiver region size lead to inaccuracies in traditional far-field 6DMA channel model, causing discrepancies between the model predicti… ▽ More Six-dimensional movable antenna (6DMA) has been identified as a new disruptive technology for future wireless systems to support a large number of users with only a few antennas. However, the intricate relationships between the signal carrier wavelength and the transceiver region size lead to inaccuracies in traditional far-field 6DMA channel model, causing discrepancies between the model predictions and the hybrid-field channel characteristics in practical 6DMA systems, where users might be in the far-field region relative to the antennas on the same 6DMA surface, while simultaneously being in the near-field region relative to different 6DMA surfaces. Moreover, due to the high-dimensional channel and the coupled position and rotation constraints, the estimation of the 6DMA channel and the joint design of the 6DMA positions and rotations and the transmit beamforming at the base station (BS) incur extremely high computational complexity. To address these issues, we propose an efficient hybrid-field generalized 6DMA channel model, which accounts for planar-wave propagation within individual 6DMA surfaces and spherical-wave propagation among different 6DMA surfaces. Furthermore, by leveraging directional sparsity, we propose a low-overhead channel estimation algorithm that efficiently constructs a complete channel map for all potential antenna position-rotation pairs while limiting the training overhead incurred by antenna movement. In addition, we propose a low-complexity design leveraging deep reinforcement learning (DRL), which facilitates the joint design of the 6DMA positions, rotations, and beamforming in a unified manner. Numerical results demonstrate that the proposed hybrid-field channel model and channel estimation algorithm outperform existing approaches and that the DRL-enhanced 6DMA system significantly surpasses flexible antenna systems. △ Less

Submitted 18 June, 2025; originally announced June 2025.

Comments: 13 pages

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents

Authors: Jonathan Kutasov, Yuqi Sun, Paul Colognese, Teun van der Weij, Linda Petrini, Chen Bo Calvin Zhang, John Hughes, Xiang Deng, Henry Sleight, Tyler Tracy, Buck Shlegeris, Joe Benton

Abstract: As Large Language Models (LLMs) are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by pursuing hidden objectives. We study the ability of frontier LLMs to evade monitoring and achieve harmful hidden goals while completing a wide array of realistic tasks. We evaluate a broad range of frontier LLMs using SHA… ▽ More As Large Language Models (LLMs) are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by pursuing hidden objectives. We study the ability of frontier LLMs to evade monitoring and achieve harmful hidden goals while completing a wide array of realistic tasks. We evaluate a broad range of frontier LLMs using SHADE (Subtle Harmful Agent Detection & Evaluation)-Arena, the first highly diverse agent evaluation dataset for sabotage and monitoring capabilities of LLM agents. SHADE-Arena consists of complex pairs of benign main tasks and harmful side objectives in complicated environments. Agents are evaluated on their ability to complete the side task without appearing suspicious to an LLM monitor. When measuring agent ability to (a) complete the main task, (b) complete the side task, and (c) avoid detection, we find that the best performing frontier models score 27% (Claude 3.7 Sonnet) and 15% (Gemini 2.5 Pro) as sabotage agents when overseen by Claude 3.6 Sonnet. For current frontier models, success on the side task relies heavily on having access to a hidden scratchpad that is not visible to the monitor. We also use SHADE-Arena to measure models' monitoring abilities, with the top monitor (Gemini 2.5 Pro) achieving an AUC of 0.87 at distinguishing benign and malign transcripts. We find that for now, models still struggle at sabotage due to failures in long-context main task execution. However, our measurements already demonstrate the difficulty of monitoring for subtle sabotage attempts, which we expect to only increase in the face of more complex and longer-horizon tasks. △ Less

Submitted 17 June, 2025; originally announced June 2025.

One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution

Authors: Yujing Sun, Lingchen Sun, Shuaizheng Liu, Rongyuan Wu, Zhengqiang Zhang, Lei Zhang

Abstract: It is a challenging problem to reproduce rich spatial details while maintaining temporal consistency in real-world video super-resolution (Real-VSR), especially when we leverage pre-trained generative models such as stable diffusion (SD) for realistic details synthesis. Existing SD-based Real-VSR methods often compromise spatial details for temporal coherence, resulting in suboptimal visual qualit… ▽ More It is a challenging problem to reproduce rich spatial details while maintaining temporal consistency in real-world video super-resolution (Real-VSR), especially when we leverage pre-trained generative models such as stable diffusion (SD) for realistic details synthesis. Existing SD-based Real-VSR methods often compromise spatial details for temporal coherence, resulting in suboptimal visual quality. We argue that the key lies in how to effectively extract the degradation-robust temporal consistency priors from the low-quality (LQ) input video and enhance the video details while maintaining the extracted consistency priors. To achieve this, we propose a Dual LoRA Learning (DLoRAL) paradigm to train an effective SD-based one-step diffusion model, achieving realistic frame details and temporal consistency simultaneously. Specifically, we introduce a Cross-Frame Retrieval (CFR) module to aggregate complementary information across frames, and train a Consistency-LoRA (C-LoRA) to learn robust temporal representations from degraded inputs. After consistency learning, we fix the CFR and C-LoRA modules and train a Detail-LoRA (D-LoRA) to enhance spatial details while aligning with the temporal space defined by C-LoRA to keep temporal coherence. The two phases alternate iteratively for optimization, collaboratively delivering consistent and detail-rich outputs. During inference, the two LoRA branches are merged into the SD model, allowing efficient and high-quality video restoration in a single diffusion step. Experiments show that DLoRAL achieves strong performance in both accuracy and speed. Code and models are available at https://github.com/yjsunnn/DLoRAL. △ Less

Submitted 20 June, 2025; v1 submitted 18 June, 2025; originally announced June 2025.

Measurements of the absolute branching fractions of the doubly Cabibbo-suppressed decays $D^+\to K^+π^0$, $D^+\to K^+η$ and $D^+\to K^+η^{\prime}$

Authors: BESIII Collaboration, M. Ablikim, M. N. Achasov, P. Adlarson, X. C. Ai, R. Aliberti, A. Amoroso, Q. An, Y. Bai, O. Bakina, Y. Ban, H. -R. Bao, V. Batozskaya, K. Begzsuren, N. Berger, M. Berlowski, M. Bertani, D. Bettoni, F. Bianchi, E. Bianco, A. Bortone, I. Boyko, R. A. Briere, A. Brueggemann, H. Cai , et al. (697 additional authors not shown)

Abstract: Using $20.3\,\rm fb^{-1}$ of $e^+e^-$ collision data collected at a center-of-mass energy of 3.773\,GeV with the BESIII detector, we present improved measurements of the absolute branching fractions of the doubly Cabibbo-suppressed decays $D^+\to K^+π^0$, $D^+\to K^+η$ and $ D^+ \to K^+ η^{\prime}$ with the double-tag method. The statistical significance of each signal decay exceeds $10σ$. The bra… ▽ More Using $20.3\,\rm fb^{-1}$ of $e^+e^-$ collision data collected at a center-of-mass energy of 3.773\,GeV with the BESIII detector, we present improved measurements of the absolute branching fractions of the doubly Cabibbo-suppressed decays $D^+\to K^+π^0$, $D^+\to K^+η$ and $ D^+ \to K^+ η^{\prime}$ with the double-tag method. The statistical significance of each signal decay exceeds $10σ$. The branching fractions are determined to be ${\mathcal B}(D^+\to K^+ π^0) = (1.45 \pm 0.06 \pm 0.06)\times 10^{-4}$, ${\mathcal B}(D^+\to K^+ η) = (1.17 \pm 0.10 \pm 0.03)\times 10^{-4}$ and ${\mathcal B}(D^+\to K^+ η^{\prime}) = (1.88 \pm 0.15 \pm 0.06)\times 10^{-4}$, where the first uncertainties are statistical and the second systematic. These results are consistent with the world average values but with significantly improved precision. △ Less

Submitted 18 June, 2025; originally announced June 2025.

Comments: 20 pages, 4 figures

Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

Authors: Team Hunyuan3D, Shuhui Yang, Mingxin Yang, Yifei Feng, Xin Huang, Sheng Zhang, Zebin He, Di Luo, Haolin Liu, Yunfei Zhao, Qingxiang Lin, Zeqiang Lai, Xianghui Yang, Huiwen Shi, Zibo Zhao, Bowen Zhang, Hongyu Yan, Lifu Wang, Sicong Liu, Jihong Zhang, Meng Chen, Liang Dong, Yiwen Jia, Yulin Cai, Jiaao Yu , et al. (28 additional authors not shown)

Abstract: 3D AI-generated content (AIGC) is a passionate field that has significantly accelerated the creation of 3D models in gaming, film, and design. Despite the development of several groundbreaking models that have revolutionized 3D generation, the field remains largely accessible only to researchers, developers, and designers due to the complexities involved in collecting, processing, and training 3D… ▽ More 3D AI-generated content (AIGC) is a passionate field that has significantly accelerated the creation of 3D models in gaming, film, and design. Despite the development of several groundbreaking models that have revolutionized 3D generation, the field remains largely accessible only to researchers, developers, and designers due to the complexities involved in collecting, processing, and training 3D models. To address these challenges, we introduce Hunyuan3D 2.1 as a case study in this tutorial. This tutorial offers a comprehensive, step-by-step guide on processing 3D data, training a 3D generative model, and evaluating its performance using Hunyuan3D 2.1, an advanced system for producing high-resolution, textured 3D assets. The system comprises two core components: the Hunyuan3D-DiT for shape generation and the Hunyuan3D-Paint for texture synthesis. We will explore the entire workflow, including data preparation, model architecture, training strategies, evaluation metrics, and deployment. By the conclusion of this tutorial, you will have the knowledge to finetune or develop a robust 3D generative model suitable for applications in gaming, virtual reality, and industrial design. △ Less

Submitted 18 June, 2025; originally announced June 2025.

Comments: Github link: https://github.com/Tencent-Hunyuan/Hunyuan3D-2.1