High Energy Physics (Phenomenology)
Analysis of p-Wave Sommerfeld Resonance Behavior in Finite-Size Dark Matter
Wu-Long Xu, Jin Min Yang and Rui Zhu
Different stages of
cosmic evolution impose different requirements on the dark matter annihilation cross section. Sommerfeld enhancement provides a possible way to accommodate them. However, in the point-like dark matter scenario, satisfying these requirements with either $s$-wave or $p$-wave Sommerfeld enhancement can strongly constrain the dark matter and mediator masses and their coupling. A finite dark matter size introduces an additional parameter and may relax these constraints. Motivated by this possibility, in this work we study the $p$-wave Sommerfeld resonances of finite-size dark matter (like
proton or
neutron) without specifying its internal structure. We find that the $p$-wave contribution can exceed the $s$-wave contribution. Nevertheless, the finite-size $p$-wave resonances are weaker than those in the point-like case. Despite this suppression, their velocity dependence remains similar to that of point-like dark matter. We then extend our analysis to nugget dark matter composed of a small number of constituents. In this case, the $p$-wave Sommerfeld enhancement exhibits behavior similar to that of point-like dark matter.
Read the full abstract ▾
Machine Learning
CARE: A Lightweight Plug-in Gated Correction and Uncertainty-aware Module for Long-term Time Series Forecasting
Guo Cheng, Changlong Lv and Jingyi Hou
Multivariate long-horizon
forecasting is critical to electricity load scheduling and traffic flow management, and to financial risk control. Existing deterministic backbones output a single trajectory, masking heterogeneous prediction difficulty across horizons and channels and providing no localized reliability signal. We present CARE (Corrective branch with Aligned context and Relative-error Estimation), a lightweight plug-in that enhances any deterministic forecaster without architectural redesign. Operating in parallel with the base model, CARE resamples historical context to match the forecast horizon, learns residual correction patterns from this aligned history, and applies scale-aware bounded updates modulated by per-coordinate sigmoid risk gates. A multi-objective loss jointly optimizes forecast accuracy, residual tracking, risk
alignment, and base-model anchoring. Across eight
benchmarks with three representative backbones, CARE improves accuracy with marginal parameter and latency overhead. Its risk gates reliably identify high-error regions: on Weather, the highest-gate tertile exhibits nearly four times the error of the lowest-gate tertile, offering planners an interpretable per-step trust signal. Code is available at https://github.com/CG-BNYC/CARE.
Read the full abstract ▾
Machine Learning
RideBench: A Large-Scale Exogenous-Aware Benchmark for Ride-Hailing Time Series Forecasting
Shengsheng Lin, Jing Hu, Zhengyang Hu et al. (+8 more)
We release Ride-Hailing, a large-scale ride-hailing time series
dataset synthesized from DiDi's marketplace data across 200 spatial areas. Ride-Hailing spans four consecutive years at half-hourly granularity and covers three representative exogenous scenarios: Weather Disturbance, Holiday Effect, and Large-scale Event Impact. Built upon Ride-Hailing, we introduce RideBench, a comprehensive
benchmark for exogenous-aware ride-hailing
forecasting, covering both regular week-ahead
forecasting and long-horizon 8-week-ahead
forecasting with up to 2,688 prediction steps. RideBench evaluates over 30 representative
forecasting methods, including endogenous-only models, exogenous-aware models, and time series foundation models. Our results show that future-known exogenous variables provide clear benefits in regular week-ahead
forecasting, especially under weather, holiday, and large-scale event (e.g., major sporting events and concerts) scenarios. However, current exogenous-aware models still struggle to fully capture disturbance-induced pattern changes under complex external contexts. For long-horizon
forecasting, existing models cannot simultaneously achieve low pointwise errors, accurate broad trends, and reliable near-term forecasts. These findings reveal a clear mismatch between existing
forecasting models and real-world ride-hailing requirements, highlighting the need for models that can better exploit future-known exogenous information, scale across heterogeneous areas, and support long-horizon planning. By introducing Ride-Hailing and RideBench, we aim to encourage the community to study these practical challenges in real-world ride-hailing
forecasting.
Read the full abstract ▾
All authors Shengsheng Lin, Jing Hu, Zhengyang Hu, Jiazheng Sun, Zichun Cao, Siwei Sun, Zhichao Zou, Enyun Yu, Dongdong Li, Xinyi Hu, Weiwei Lin
Cryptography and Security
Characterizing Statistical Separability in TP-CRIV for Probabilistic AI Models
Teruki Sano, Minoru Kuribayashi, Masao Sakai et al. (+4 more)
Third-party challenge-response identity verification (TP-CRIV) enables an independent verifier to assess whether a claimant possesses a model identical to a remotely deployed model without directly accessing the reference model. However, for probabilistic AI models, repeated executions of the same query may produce different outputs and therefore different verification observations. This raises the question of how such
stochastic evidence should be accumulated and how much evidence is required for reliable verification. In this work, we characterize statistical separability in TP-CRIV of probabilistic AI models. Specifically, we relate challenge-wise behavior of matching and non-matching provers to verification-level separability. The characterization explicitly describes how the numbers of independent challenges and repeated responses affect detection performance and enables the verification budget required for a target AUC to be estimated. We instantiate the proposed characterization for LLMs using open-ended challenges. The experiments demonstrate matching-non-matching separation, close agreement between theoretical and empirical AUCs, and consistent estimates of the minimum verification budgets. These results provide a statistical basis for relating probabilistic model behavior to verification-level separability and the evidence required for third-party verification.
Read the full abstract ▾
All authors Teruki Sano, Minoru Kuribayashi, Masao Sakai, Shuji Isobe, Eisuke Koizumi, Zhang Zhang, Satoru Matsumoto
Computer Vision
AutoAdapt: Reliable Few-Shot Adaptation under Clinical Distribution Shifts
Song Wang, Jie Peng, Davis Hobley et al. (+2 more)
Large pretrained clinical models provide a practical way to reuse learned prior knowledge across hospitals by adapting models to them. In practice, a target hospital may only have a small labeled patient cohort, a setting commonly referred to as few-shot adaptation. This requires making multiple decisions, such as which pretrained model to adapt, how much of the model to update, and which patients to use. Nevertheless, this process faces two primary challenges. First, the best adaptation strategy varies across clinical tasks. Second, evaluating and comparing candidate strategies becomes unreliable due to the small patient cohort. In this work, we introduce AutoAdapt with two core designs to deal with these challenges. The Adapter defines an extensible space of adaptation recipes, and the Automator forms a weighted recipe combination from evidence within the adaptation patients. We propose a reliability rule to ensure that only the most effective strategy on most available patients will be selected. These selected strategies then form a combination for effective few-shot adaptation. We conduct extensive experiments across critical care, emergency care, and diagnostic
datasets, and the results show that AutoAdapt consistently achieves state-of-the-art performance using only a few patients for adaptation.
Read the full abstract ▾
All authors Song Wang, Jie Peng, Davis Hobley, Zachary Plotkin, Tianlong Chen
Computer Vision
VGGTWorld-VLA: Intent-Conditioned 3D World Evolution for Autonomous Driving
Zhaoyang Liu, Kun Jiang, Ziying Song et al. (+1 more)
VGGT provides a strong foundation for geometry-centric world models by recovering unified 3D scene geometry from visual observations. Although recent extensions enable temporal 3D prediction, their future
evolution remains weakly conditioned on driving intentions and actions, limiting their ability to model alternative action-dependent futures. We propose VGGTWorld-VLA, an intention-conditioned extension of VGGT-World for controllable 3D world
evolution in autonomous driving. First, we introduce an action–semantic conditioning mechanism that injects complementary driving semantics and ego-motion representations into the future-
token stream, enabling different future geometry predictions for the same observed scene under alternative ego actions. Second, we develop a geometry–
language–action bridge that adapts historical geometry, VLA semantic features, and maneuver and trajectory representations for joint conditioning of future geometry prediction. We evaluate future geometry prediction on NAVSIM, while conditioning ablations further examine the contributions of semantic and action information. Compared with the baseline, our method demonstrates competitive geometry prediction performance. Ablation studies further support the effectiveness of semantic and action conditioning. These results demonstrate the potential of semantic and action conditioning for controllable VGGT-based world prediction in autonomous driving.
Read the full abstract ▾
All authors Zhaoyang Liu, Kun Jiang, Ziying Song, Diange Yang
Computation and Language
LadderEdit: Edit-Level Residual Compression for Memory-Efficient Lifelong Editing of LLMs
Xiaobing Yu, Peijie Qiu, Jin Yang et al. (+5 more)
Lifelong editing of LLMs requires storing thousands of edits after acquisition. A widely used family of approaches attaches one LoRA adapter per edit, which preserves behavior but grows linearly in storage. To address this challenge, we propose LadderEdit, a method that compresses each LoRA adapter after it is acquired. Each edit is first stored at low rank as a cheap sketch. We then check whether this sketch still satisfies the rewrite, generalization, and locality contract on probe
prompts. Edits that pass keep the sketch; those that fail are promoted to a higher rank along a ladder until the contract is met. Because every edit retains some representation, coverage is maintained, and only hard edits consume more rank. Across ZsRE, CounterFact, and WikiBigEdit
benchmarks on LLaMA-3-8B, Mistral-7B, and Qwen2.5-7B, LadderEdit tracks exact LoRA storage at 5.2x less
memory and remains effective at 50,000 sequential edits.
Read the full abstract ▾
All authors Xiaobing Yu, Peijie Qiu, Jin Yang, Xuanzhao Dong, Weiwei Ma, Zhaoqi An, Xiaoqi Zhao, Xiaofeng Liu
Computation and Language
Local Prototype Reconstruction for Text-Compatible Speech-to-LLM Bridge Pretraining
Xinnian Zhao, Chia-Hua Wu, Pu Wang et al. (+1 more)
Speech-to-LLM systems often connect a frozen
speech encoder to a frozen large
language model (LLM) through a small trainable bridge. The bridge is usually treated as plumbing, but it in fact defines the geometry of the
speech-to-LLM interface, and the pretraining objective decides whether that interface provides a reusable initialization for downstream tasks. We study a transferable bridge through two complementary properties: global
alignment with the text side, and local lexical
manifold compatibility, where bridge
embeddings remain close to the frozen LLM's input-
embedding neighbourhoods. We make this property measurable with a fixed, head-free, timestamp-free diagnostic that applies to any objective, and show that next-word prediction (NWP) and sentence-level contrastive pretraining do not fully capture
token-level lexical compatibility. We then introduce Local Prototype Reconstruction (LPR), a lightweight training-only regularizer that requires each aligned bridge
token to be reconstructable from a small neighbourhood of frozen LLM
token embeddings, with a hard single-prototype anchor as its limiting case. On
multilingual ASR and
speech translation, LPR improves transfer, with the largest gains on translation and low-resource adaptation. Crucially, our independent diagnostic correlates with downstream gains across objectives, suggesting that lexical
manifold compatibility is predictive of reusability for
speech-to-LLM bridges.
Read the full abstract ▾
All authors Xinnian Zhao, Chia-Hua Wu, Pu Wang, Hugo Van Hamme
Distributed Computing
Zepp: Accelerating Distributed MoE Serving under Relaxed Balance Constraints
Chang Chen, Andrew Yang, Tiancheng Chen et al. (+5 more)
As Mixture-of-Experts (MoE) models continue to scale, serving them increasingly relies on expert parallelism (EP) across a growing number of devices. Yet skewed expert workloads create imbalance across computation, communication, and
memory, making load balancing a central optimization objective in distributed MoE serving. We observe that balance is not free: operations introduced to balance one dimension can themselves be expensive or imbalanced. This motivates us to rethink balance as a constraint rather than an optimization objective. We present Zepp, which directly optimizes the bottleneck communication in distributed MoE serving subject to simplified balance constraints on physical resources, i.e., GPUs and NICs. Zepp progressively optimizes inter-node communication across placement, routing, and execution. It first places expert replicas to reduce
token communication under GPU constraints, then reshapes communication flows through split and merge primitives under NIC constraints, and finally partitions and schedules ex- pert computation to overlap the resulting communication. To adapt to dynamic workloads, Zepp jointly coordinates computation,
token communication, and expert-weight movement at each iteration. Together, these designs allow Zepp to pursue the most efficient execution rather than a single-dimension balanced one. We implement Zepp and evaluate it against 7 state-of-the-art MoE serving systems, achieving up to 6.68$\times$ MoE layer speedup and a
geometric mean speedup of 1.86$\times$ over the fastest competing baseline.
Read the full abstract ▾
All authors Chang Chen, Andrew Yang, Tiancheng Chen, Jiangfei Duan, Xinwei Qiang, Zhongkai Yu, Xiang Fang, Yufei Ding
Mathematical Physics
Uniformity theory of weighted composites
Marcelo Epstein and Mohammadjavad Javadi
By including spatially varying volume fractions of the constituents, composites are obtained that are akin to functionally graded media. An extension of the mathematical apparatus of double groupoids is proposed to incorporate these materials with the aim of eventually classifying defects of misalignment and their time
evolution.
Read the full abstract ▾
Sound
MiDashengLM-Spatial: Unifying General Audio Understanding and Spatial Awareness
Jinbo Hu, Hang Su, Lichun Fan et al. (+10 more)
Large audio-
language models (LALMs) have achieved strong performance in general audio understanding, yet most are designed for monaural input and discard the inter-channel cues essential for spatial perception. In contrast, existing spatial audio-
language models are purpose-built for spatial tasks and fail to capitalize on the general understanding capabilities of monaural LALMs. We present MiDashengLM-Spatial, the first open-source end-to-end unified audio-
language model, to our knowledge, which supports both general audio understanding and spatial awareness within a single architecture. It extends MiDashengLM with a spatial audio encoder, Spatial-Dasheng, integrated through a hierarchical semantic-to-spatial conditioning module that injects intermediate semantic representations into the spatial branch at multiple depths while preserving the original semantic pathway. To provide spatial audio-
language supervision at scale, we develop a data synthesis pipeline that renders diverse spatial acoustic scenes with scene-level spatial descriptions and question-answer pairs. Experiments show that Spatial-Dasheng achieves strong performance on sound event localization and detection in real-world scenes, and that MiDashengLM-Spatial substantially outperforms existing LALMs on spatial understanding and
reasoning benchmarks. Meanwhile, it remains competitive with state-of-the-art 8B-scale LALMs on diverse monaural
benchmarks, demonstrating that spatial awareness can be acquired without compromising general audio understanding. The source code and model checkpoint are available at https://github.com/xiaomi-research/midashenglm-spatial and https://huggingface.co/mispeech/midashenglm-spatial.
Read the full abstract ▾
All authors Jinbo Hu, Hang Su, Lichun Fan, Heinrich Dinkel, Gang Li, Zhanchen Dai, Yiru Zhang, Chang Liu, Peng Wang, Junnan Wu, Jian Luan, Cong Zou, Heng Qu
Artificial Intelligence
Social Pain Disrupts Emotion-Action Brain-State Dynamics in Adolescents with Non-Suicidal Self-Injury
Ying Xu, Xiaojun Liang, Li Zhang et al. (+4 more)
Non-suicidal self-injury (NSSI) is prevalent among adolescents with depression, but the rapid
brain-state dynamics linking social distress to maladaptive behavior remain unclear. We combine an experimental pain paradigm, electroencephalography (
EEG) microstate analysis, and interpretable deep sequence modeling to investigate NSSI-related neurodynamics in 106 adolescents with depression, including 67 with NSSI (DN+) and 39 without NSSI (DN-), during social pain, physical pain, and resting-state conditions. A model integrating disease-specific, domain-
adversarial, consistency, and contrastive learning captures higher-order dependencies in microstate sequences. Social pain yields the strongest NSSI discrimination, with 68.55% accuracy, outperforming the best baseline by 8.94% points. Model interpretation and conventional microstate analyses reveal weakened bidirectional transitions between MS3 and MS5 in DN+ adolescents during social pain. Source reconstruction associates MS3 with emotional/interoceptive processing and MS5 with action preparation, suggesting disrupted
emotion-action coupling. Time-resolved analyses show greater early-to-middle action-state recruitment and later
emotion-state recruitment in DN+ adolescents. In DN- adolescents, MS5-to-MS3 dynamics mediate associations between social-evaluation sensitivity and affective outcomes, whereas this mediation is absent in DN+; conversely, MS3-to-MS5 transitions are associated with greater negative affect in DN+. Together, these findings identify disrupted
emotion-action coupling as a key neurodynamic mechanism underlying altered social pain processing in adolescents with NSSI, providing a mechanistically interpretable neural signature for objective identification of NSSI.
Read the full abstract ▾
All authors Ying Xu, Xiaojun Liang, Li Zhang, Yixuan Yuan, Gan Huang, Yongjie Zhou, Zhen Liang
Optimization and Control
Exact Convex Reformulations of Binary Quadratic Programs from Facially Reduced Semidefinite Relaxations
Hao Hu and Mingming Xu
We develop MIQCR-FR, a framework for exact convex reformulation from facially reduced semidefinite relaxations of equality-constrained binary quadratic problems. Standard mixed-integer quadratic convex reformulation (MIQCR) uses dual multipliers of the original relaxation. Facial reduction (FR) reduces the semidefinite
matrix order, but recovery of the original dual multipliers is not guaranteed in general. For this class of problems, we identify how retaining the linear equalities and their products with each binary variable enables this recovery. An established dual recovery formula gives an explicit extension of every feasible solution of the reduced dual to the original dual, preserving its bound. For approximate multiplier estimates, we give a spectral shift restoring dual feasibility and two constructions optimizing different bounds within a restricted multiplier family. Maximizing the dual bound yields a trust-region subproblem; maximizing the continuous MIQCR bound requires only a reduced
eigenvalue calculation. The latter construction enforces convexity directly, rather than full dual feasibility. We implement it using multiplier estimates from the alternating direction method of multipliers (ADMM). On 431 instances from six problem families, the complete method certifies 296 optima, compared with 156 for the conic-bundle method MIQCR-CB and 187 for direct Gurobi under a common time budget.
Read the full abstract ▾
Computer Vision
CARE: Constrained Attention Refinement for Fine-Grained Visual Classification via Teacher-Student Distillation
Ruibo Wen, Hang Shao and Yiming Lei
Fine-grained visual classification requires models to recognize subtle local traits while exposing the visual evidence behind their predictions. Class-specific
attention pathways provide a natural basis for interpretable recognition, but their constrained prediction structure limits discriminative capacity and underuses intermediate representations from strong pretrained backbones. To address this problem, we propose CARE, a constrained
attention refinement framework for interpretable fine-grained recognition via teacher-student
distillation. CARE keeps the final prediction and explanation within a class-specific
attention student, while introducing a training-only auxiliary query teacher that reads selected intermediate DINOv2 layers with learnable queries. The teacher fuses multi-level representations and transfers logit-standardized class-discriminative knowledge to the student. To further refine the explanation pathway, we design diversity and sparsity terms to regularize student
attention heads, reducing redundancy and encouraging compact trait localization. Experiments on CUB, Oxford-IIIT Pet, Stanford Dogs, and Stanford Cars show that CARE achieves strong classification performance under an interpretable frozen-backbone setting, reaching 78.5% Top-1 accuracy on CUB. Faithfulness analysis with insertion and deletion metrics further indicates that the top-ranked
attention regions retain class-relevant evidence for explanation.
Read the full abstract ▾
Machine Learning
Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context RL
Minchan Kwon, Seunghee Koh, Sunghyun Baek et al. (+2 more)
LLM
agents increasingly improve at inference time by accumulating experience in context rather than by updating parameters. This process is often described as in-context reinforcement learning (ICRL). Whether in-context learning (ICL) can actually play the role of RL, however, has not been tested. We study this question in its simplest form, direct ICRL, where the model conditions directly on raw trajectory-reward pairs, and ask whether the reward acts as a learning signal. Through controlled experiments on four
benchmarks across six models, we find that the reward is read, but its effect is small: flipping, randomizing, or removing the reward leaves the improvement curve almost unchanged, and this holds even under meta-
prompts that explicitly instruct the model to explore, exploit, or reason over rewards. Trajectories drive improvement, but not through their semantic content: shuffled or corrupted trajectories work as well as real ones. These patterns closely mirror those known in ICL, suggesting that direct ICRL is better understood as a special case of ICL than as inference-time RL. This reframing has implications for
agent memory design: ICL factors such as input distribution and demonstrations may matter more than RL elements such as reward shaping and exploration.
Read the full abstract ▾
All authors Minchan Kwon, Seunghee Koh, Sunghyun Baek, Minsung Bae, Junmo Kim
Combinatorics
Star-critical Ramsey numbers involving large generalized books
Peiyu Huang, Qizhong Lin and Lin Niu
For graphs $F$, $G$, and $H$, we write $F \to (G, H)$ if every red/blue edge-coloring of $F$ contains either a red copy of $G$ or a blue copy of $H$. The Ramsey number $R(G, H)$ is the smallest integer $N$ such that $K_N \to (G, H)$. Let $H := K_k + nK_h$ be the generalized book graph, and let $G := K_{p+1}(a_1, a_2, \dots, a_{p+1})$ be a complete $(p+1)$-partite graph satisfying $a_1 = 1$, $a_2 \mid (nh-1)$, and $a_i \le a_{i+1}$. In this paper, avoiding the use of Szemerédi's regularity lemma, we prove that for any fixed $h, p \ge 1$, $k \ge 2$, and sufficiently large $n$, $K_{p(nh + a_2k - 1) + 1} \setminus K_{1, nh - a_2(h-2) - 1}\to(G, H).$ This result yields the
star-critical Ramsey number $r_*(G, H) = (p-1)(nh + a_2k - 1) + a_2(k + h - 2) + 1.$
Read the full abstract ▾
Audio and Speech Processing
SmoothConv and DuplexConv: Complementary Mandarin Multi-Party Conversational Speech Corpora for Speech Interaction
Chengyou Wang, Mingchen Shao, Chunjiang He et al. (+8 more)
Recent advances in large audio
language models (LALMs) have driven the development of natural and intelligent
speech interaction systems. Such systems need to model complex conversational behaviors, including turn-taking, overlapping
speech, and speaker coordination. Multi-party conversations provide a realistic setting for studying these behaviors, yet existing Mandarin conversational corpora often lack synchronized participant-level
speech tracks and comprehensive annotations. In this work, we introduce SmoothConv and DuplexConv, two complementary Mandarin multi-party conversational
speech corpora totaling 2,100 hours. SmoothConv provides human-verified conversations for reliable analysis and evaluation, while DuplexConv offers large-scale automatically annotated conversations through a scalable pipeline for model training. Both corpora provide synchronized participant-level
speech tracks and multi-dimensional fine-grained annotations. We further release the SmoothConv
Benchmark and evaluate these resources on
speech separation, multi-speaker automatic
speech recognition (MSASR), and turn detection tasks. Experimental results demonstrate the utility of the proposed resources for multi-party
speech interaction modeling. The
datasets,
benchmark, and related resources are publicly available.
Read the full abstract ▾
All authors Chengyou Wang, Mingchen Shao, Chunjiang He, Zeyu Zhu, Jierui Guo, Bingshen Mu, Zikai Liu, Hanke Xie, Yuhang Dai, Zhou Zhu, Lei Xie
Computer Vision
A Unified Score Matching Paradigm for Video Anomaly Detection and Anticipation
Congqi Cao, Zhenhe Liang, Hanwen Zhang et al. (+4 more)
Video anomaly detection (VAD) is a fundamental and safety-critical task in computer
vision. Recent generative approaches detect anomalies from a distributional perspective, but remain limited by local anomaly modes. Meanwhile,
video anomaly anticipation (VAA), as a proactive extension beyond post-hoc detection, introduces additional challenges. In particular, the contrastive inference paradigm in VAD, which relies on ground-truth frames, is not applicable to VAA, hindering its development. To address these challenges, we propose a unified score-driven framework, termed Uni-DSM, based on denoising score matching (DSM), which models anomaly patterns through likelihood estimation and score functions over the learned data distribution. Within this unified framework, we adopt a shared noise-conditioned score
transformer backbone with scene-dependent
embeddings and motion-aware weighting for distribution-level modeling. Instead of introducing separate architectures, Uni-DSM unifies VAD and VAA through different inference and supervision paradigms built upon the same score-based formulation. For VAD, we instantiate an autoregressive denoising score matching (ADSM) mechanism, which progressively accumulates anomalous evidence via autoregressive denoising, enabling enhanced perception of local modes beyond visual cues. For VAA, we extend the same architecture by incorporating a lightweight auxiliary decoder and a novel self-distilled denoising score matching (SDSM) mechanism. By constructing supervision from output discrepancies instead of relying on unavailable future ground truth, our method achieves efficient training suitable or early anomaly anticipation. Extensive experiments on multiple
benchmark datasets demonstrate state-of-the-art performance in both VAD and VAA while maintaining high efficiency, establishing a unified and scalable pipeline from anomaly detection to anticipation.
Read the full abstract ▾
All authors Congqi Cao, Zhenhe Liang, Hanwen Zhang, Yifan Zhao, Qinyi Lv, Lingtong Min, Yanning Zhang
Computer Vision
SP-DocReader: Difference-Aware Self-Play for Precise Document OCR
Wenjie Liao, Xiaohui Song, Liangjie Zhao et al. (+1 more)
Accurate page transcription remains difficult for
vision language models under limited input and training budgets. We present SP-DocReader, a self-play framework for optical character recognition (OCR) that targets residual errors after supervised fine-tuning. Reading Discrepancy Masking aligns reference and generated model
tokens through a longest common subsequence, then scores unmatched positions with their full conditioning prefixes. Focused Fidelity Loss adds direct negative log-likelihood supervision at unmatched ground-truth positions. Only the OCR module is trained, while the backbone remains frozen. We derive the combined gradient to distinguish relative score optimization from direct supervision. Compared with SFT-2, SP-DR-3 reduces Vary-600K character error rate on both backbones. On Qwen3-VL-4B, it reduces character error rate by approximately 54 percent and improves DocVQA Average Normalized Levenshtein Similarity (ANLS) by 3.7 points. These results show the value of focusing self-play training on the discrepancies that remain after supervised fine-tuning.
Read the full abstract ▾
All authors Wenjie Liao, Xiaohui Song, Liangjie Zhao, Haonan Lu
Physics and Society
Energy-barrier characterization of secured basins in coupled oscillators with inertia
Jaiyong Lee, Daekyung Lee, Seung-Woo Son et al. (+3 more)
The second-order Kuramoto model captures rotor dynamics relevant to synchronization in power grids. In actual power grids, violation of angle-stability limits can trigger protective actions that are not included in the model, restricting its validity to trajectories that remain within these limits. We therefore define the secured basin as the region of disturbance space comprising disturbances whose trajectories remain within the angle-stability limits throughout the transient. We then characterize the secured basin through energy barriers, quantifying their characteristic energy scale and heterogeneity across perturbation directions. Across seven power-grid models, this characterization revealed angle-stability vulnerabilities overlooked when stability is assessed solely by the final synchronization state. It also showed that the two energy-barrier measures characterizing the secured basin exhibit distinct associations with structural connectivity and dynamical parameters. This characterization further offers practical advantages, as energy thresholds derived from state-space perturbations remain effective in distinguishing secured and unsecured outcomes under short-duration power disturbances and can be estimated efficiently by concentrating simulations near the secured-basin boundary. Overall, the secured-basin framework provides a useful basis for distinguishing node-level structural and dynamical influences on transient stability in oscillator networks with synchronization constraints.
Read the full abstract ▾
All authors Jaiyong Lee, Daekyung Lee, Seung-Woo Son, Sang Hoon Lee, Mi Jin Lee, Heetae Kim
Machine Learning
What Transfers from Training-Only Priors? Separating Knowledge, Ordinal Targets, and Optimization
Qiye Lu, Jiang Ji and Liang Zhang
Training-only teacher access lets a compact student deploy with local features and exported weights. This established
distillation interface does not identify what transfers or when it helps. We separate label, query, capacity, and source-access budgets on three public credit archives and a previously unexamined bankruptcy archive. Shared tree parameters, shuffles, and optimizer interventions expose limitations of historical Ranking Prior
Alignment; no tested single repair consistently rescues it. Heldout source queries and matched warmup and mappings retain a rank-listwise advantage over mapped staged KD in 24 credit configuration means and all six teacher–capacity means of a frozen new-archive test, with explicit query failures and stronger source-weight delivery under a different interface. A pretrained TabICLv2 follow-up at 100 labels initially improves matched supervision in only one of eight means; six of nine source-predicted policy gains reverse on target. A registered seen-archive intervention adds 500 or 2,000 unlabeled queries: all eight matched AUC means become positive under selected and fixed alpha. However, outer effects are mixed and no conditional paired-draw interval for these supervised contrasts lies wholly above zero. Increasing teacher context at 500 student labels does not beat matched supervision in any of eight ordinary-context means, despite stronger direct teacher performance. Rank KD retains substantial probability errors. Independent reloads verify zero guarded external inference accesses. Results support query/context boundary diagnostics, without universal superiority, population significance, a prospective transfer rule, or an LLM-specific advantage.
Read the full abstract ▾
Data Structures and Algorithms
Tight Bounds for Equivalence Testing with Non-Adaptive Conditional Samples
Gautam Kamath
We study distribution testing with access to non-adaptive conditional samples. Specifically, we give tight bounds for equivalence testing, determining whether two unknown distributions are equal to or $\varepsilon$-far from each other in total variation distance. Our
algorithm and lower bound show that $\tilde \Theta\left(\frac{\log n}{\varepsilon^2}\right)$ queries are necessary and sufficient for this problem. These results demonstrate that the complexity of uniformity, identity, and equivalence testing with non-adaptive conditional samples are all $\tilde \Theta(\log n)$.
Read the full abstract ▾
Computer Vision
Improving Image-Based Nutrition Estimation Through Multimodal Food-Item Verification and Recovery
Jingbo Yue, Bruce Coburn, Jinge Ma et al. (+2 more)
Single-image nutrition estimation can fail silently when visible foods are missed. Even when a food is correctly identified, its proposed region may not support portion estimation. We propose a framework that uses
multimodal large
language models (MLLMs) to inventory visible foods and separately verify food identity and whether each proposed 2D region supports portion estimation. One whole-image review uses these verification results to identify unresolved gaps and omitted foods, triggering at most one targeted recovery pass. Recovered regions are re-verified without access to the recovery
prompt, then reconciled into a final item set for nutrition estimation. The framework requires no task-specific fine-tuning. Matched evaluation on common valid-output samples shows that item-level grounding improves mass accuracy across all tested settings and energy accuracy relative to an adapted
retrieval baseline, with item-identity precision and recall also improving, while post-recovery visual coverage is assessed separately at inference time without ground-truth annotations.
Read the full abstract ▾
All authors Jingbo Yue, Bruce Coburn, Jinge Ma, Jui-Feng Chi, Fengqing Zhu
Operator Algebras
Mean dimension and radius of comparison
George A. Elliott and Zhuang Niu
Consider a minimal and free topological dynamical system $(X, \Gamma)$, where $\Gamma$ is a discrete amenable group. Assume $(X, \Gamma)$ has the uniform Rokhlin property (URP) and the Cuntz comparison of open sets (COS), then it is shown that $$\mathrm{rc}(\mathrm{C}(X) \rtimes \Gamma) = \frac{1}{2} \mathrm{mdim}(X, \Gamma).$$ The same statement also holds for unital simple AH
algebras with diagonal maps. The arguments in both cases are based on the recent preprint of OpenAI dealing with $\mathbb Z$-actions and the topological ideas used in that paper.
Read the full abstract ▾
Neurons and Cognition
If the brain were so simple: Information-based drivers of intelligence and their interaction through an n-body-inspired framework
Brett J. Kagan, Johnson Zhou, Forough Habibollahi et al. (+1 more)
Theories of how the
brain processes information and returns intelligent outputs are numerous and often difficult to conclusively test. Here, we consider an approach grounded in informatics and algorithmic thermodynamics for how neural systems respond to different patterns of information in different ways, with a focus on the relationship between the information
entropy of a signal and a new proposed quantity we term information enthalpy, which represents the internal resource of structured information within a system available to be used for predictions and other forms of work. To evaluate the capacity of the external signals to increase information enthalpy in the system, we introduce the information enthalpy potential (IEP) as a defined metric. We propose and implement a method for quantifying the amount of potential information enthalpy - the IEP - in a given signal across a range of example signals. We offer a
conjecture of how information enthalpy may be treated by neural systems within a biological framework before showing how it may integrate and offer falsifiability to existing approaches such as the Free Energy Principle. This framework is also positioned in light of the role of neural criticality. Finally, we postulate a testable and falsifiable framework where the distinct mechanisms within each driver interact through a described n-body-inspired model to govern the "motion" of a neural system through a high dimensional state-space. Through these processes, it is proposed that these features form the most fundamental basis of the neural drivers that give rise to the complexity of adaptive behaviors that are commonly called: intelligence.
Read the full abstract ▾
All authors Brett J. Kagan, Johnson Zhou, Forough Habibollahi, Valentina Baccetti
Robotics
Distributed Relative Localization Based on Ultra-WideBand and LiDAR for Multi-robot with Limited Communication
Zhiqiang Cao, Ran Liu, Billy Pik Lik Lau et al. (+2 more)
Relative localization is crucial for a multi-
robot system to collaboratively perform tasks, such as exploration and formation. However, this is highly challenging for homogeneous
robots with similar appearance in GPS-denied and communication-limited environments. In this paper, we propose a fully distributed relative position estimation approach for a team of
robots based on onboard UWB and
LiDAR sensors, in which
LiDAR is utilized to obtain the position of anonymous objects in Line-of-Sight (LOS), and UWB is used for ranging between
robots. We construct two graphs, namely UWB connection graph and
LiDAR connection graph, to represent the spatial relationship among objects (
robots and obstacles) based on UWB and
LiDAR measurements. Identification and relative position estimation are formulated as a common subgraph matching problem. A falsely-matched
robot identification approach is designed to recognize the falsely-matched results caused by obstacle blockage in
LiDAR field of view. These
robots are then localized by leveraging the well-matched
robots and the UWB ranging measurements in the UWB connection graph. We conducted experiments to evaluate the performance of our approach. The results show that the proposed approach is capable of achieving satisfactory positioning accuracy for a team of
robots in a distributed manner with only exchanging limited information.
Read the full abstract ▾
All authors Zhiqiang Cao, Ran Liu, Billy Pik Lik Lau, Chau Yuen, U-Xuan Tan
Machine Learning
ActiveMedAgent: Cost-Aware Trajectory Learning for Multimodal Medical Diagnosis
Weiwei Ma, Xiaobing Yu, Peijie Qiu et al. (+5 more)
Clinical diagnosis is inherently sequential: clinicians escalate from cheap to costly tests only when additional evidence is expected to resolve diagnostic uncertainty. We present ActiveMedAgent, a framework that brings this cost-aware sequential logic to
multimodal medical AI. Given a frozen, API-accessed
vision-
language model, ActiveMedAgent tracks probability distributions over candidate diagnoses and scores each acquisition by its per-step diagnostic utility minus cost. A lightweight MLP controller is then trained offline on these scored trajectories, learning when to request additional evidence and when to commit. Across three commonly used
benchmarks, trajectory-based policy learning consistently outperforms both unguided acquisition and full-modality baselines. Notably, we identify an information overload effect. In 175 cases, the
agent produces a correct diagnosis with fewer channels while the full-modality baseline fails, showing that learning what to omit can be as important as learning what to acquire.
Read the full abstract ▾
All authors Weiwei Ma, Xiaobing Yu, Peijie Qiu, Jin Yang, Zhaoqi An, Xuanzhao Dong, Xiaoqi Zhao, Xiaofeng Liu
Machine Learning (Statistics)
Accelerating Non-Smooth and Heavy-Tailed Sampling
Pervez Ali, Xiaoyu Wang, Yingli Wang et al. (+1 more)
Anchored Langevin dynamics (ALD) is useful for non-smooth sampling where the density of the target distribution is possibly non-differentiable and heavy-tailed; reflected anchored Langevin dynamics (RALD) can sample possibly non-differentiable target density on a constrained domain. In this paper, we propose and study non-reversible anchored Langevin dynamics (NALD) for sampling possibly non-differentiable and heavy-tailed target density in the Euclidean space and the non-reversible reflected anchored Langevin dynamics (NRALD) for sampling possibly non-differentiable target density in the constrained space. Our construction adds a circulation drift generated by a possibly state-dependent divergence-free skew-symmetric
matrix field and a stream potential. It preserves the target distribution without requiring derivatives of target density, admits a random-time-change representation, and applies both on the whole Euclidean space and on bounded domains with normal reflection. By breaking reversibility, we show that NALD and NRALD can converge to their target distributions faster than their reversible counterparts via finite-time non-asymptotic convergence analysis, a large deviations analysis and asymptotic variance reduction. Numerical experiments demonstrate the efficiency of the proposed
algorithms.
Read the full abstract ▾
All authors Pervez Ali, Xiaoyu Wang, Yingli Wang, Lingjiong Zhu
Computer Vision
IntrinSync: Joint Intrinsic Decomposition and Reciprocal Rendering
Zheng Gu, Rui Huang, Xilu Zhang et al. (+6 more)
Inverse rendering decomposes an image into intrinsic properties such as appearance, illumination, geometry, and material, yet these properties are inherently interdependent. A reliable decomposition should produce intrinsic maps that are not only individually plausible, but also mutually compatible in explaining the image. However, existing methods either model intrinsic channels in isolation or treat inverse and forward rendering as separate processes, leaving the interdependence underexploited. In this paper, we introduce IntrinSync, a unified framework that captures this interdependence through joint-channel modeling and reciprocal inverse-forward rendering. At the channel level, we jointly decompose an input RGB into albedo, shading, surface normal, roughness, and metallic maps through a 1-to-N mapping, enabling information exchange across channels throughout generation. At the process level, we establish inverse-forward reciprocity through a dual cycle-consistent objective that aligns corresponding predictions across a closed loop. Experiments on three
datasets demonstrate that our method achieves competitive intrinsic estimation and forward rendering performance, improving coherence and physical consistency. Beyond decomposition, IntrinSync provides a physically grounded interface for image editing, allowing intrinsic properties to be explicitly manipulated and rendered back into RGB images.
Read the full abstract ▾
All authors Zheng Gu, Rui Huang, Xilu Zhang, Jingbo Zhang, Min Lu, Zhida Sun, Dani Lischinski, Daniel Cohen-Or, Hui Huang
Quantum Gases
Universal Drude Weights in One-dimensional Repulsive Fermi Gas
Xiangguo Yin, Dawei Niu, Shuang Zhang et al. (+3 more)
Building on the Bethe ansatz and generalized hydrodynamics, we rigorously establish universal relations between Drude weights governing charge,
spin, and energy transport and thermodynamic properties for the one-dimensional repulsive two-component continuum
Fermi gas - the paradigmatic integrable Yang-Gaudin model. We analytically derive thermodynamic expressions for charge Drude weights: $D_{nn}$, $D_{nm}$, $D_{ne}$ (responses of particle, magnetization and energy currents to a chemical potential gradient) equal the particle density, magnetization, and temperature times
entropy density, respectively. These relations constitute a hallmark of ballistic transport, and can be generalized to other 1D continuum integrable systems. Furthermore, we investigate
spin Drude weight ($D_{mm}$, $D_{me}$) at zero and low temperatures. They characterize the magnetization and energy current responses to a
magnetic field gradient, revealing an essential
spin-charge coupling feature in
quantum transport. We find that the Drude weights $D_{nm}$, $D_{mm}$, and $D_{me}$ across the $\mu\text{-}H$ plane remarkably map out the zero-temperature phase boundary. This work fills a critical gap in the understanding of transport within integrable
quantum gases and furnishes a direct theoretical foundation for future ultracold-atom experiments.
Read the full abstract ▾
All authors Xiangguo Yin, Dawei Niu, Shuang Zhang, Shizhong Zhang, Yunbo Zhang, Xi-Wen Guan