跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 06:08 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 06:16 — 2026-11-08 06:16（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-08 06:08最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 12,919 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 06:06（北京时间）
版本更新 · v3arXiv:2601.15738

EvoDR: Evolving Dispatching Rules via Large Language Model for Dynamic Flexible Assembly Flow Shop Scheduling

Junhao Qiu, Haoyang Zhuang, Fei Liu, Jianjun Liu, Qingfu Zhang

原文摘要

Dynamic flexible assembly flow shop scheduling with multi-product delivery, often with kitting supply and machine-level flexibility, can be found in many applications. It is difficult to design rules manually for it. Genetic programming (GP) has been used to automatically generate dispatching rules, enabling responsive scheduling while meeting high responsiveness demands. However, GP methods are dependent on fixed terminal sets and have poor interpretability. In this work, we develop an evolving dispatching rules framework (EvoDR) that leverages the semantic understanding and generation capabilities of large language models to achieve cross-domain integration of rule design and scheduling knowledge. In our proposed framework, multi-stage assembly supply decisions are modeled as priority sorting of directed edges based on heterogeneous graphs. A dual-expert co-evolution mechanism is proposed, which allows LLM-A to generate code and LLM-S conduct scheduling analysis and reflection. Guided by improvements in hybrid evaluation, adaptive rules that fit dynamic features are continuously evolved. Experimental results show that EvoDR can achieve lower average tardiness than other automatically designed state-of-the-art approaches. It also outperforms expert-designed competitors across 480 instances over 24 distinct scenarios with varying resource configurations and disturbance levels, and EvoDR demonstrates robust adaptability across diverse operating conditions.

cs.NE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08203

Common zeros of homogeneous polynomials and the weight hierarchy of projective Reed-Muller codes

Rodrigo San-José

原文摘要

We determine the maximum number of common zeros in projective space of any set of linearly independent homogeneous polynomials of the same degree, when the degree is smaller than the cardinality of the finite field. This proves the conjecture of Beelen, Datta and Ghorpade and determines the complete weight hierarchy of the corresponding projective Reed-Muller codes. The proof uses Green's hyperplane restriction bound, combined with a footprint argument that reduces the problem to the affine case solved by Heijnen and Pellikaan. Wei duality then determines the hierarchy in sufficiently large degrees, recovering the complete hierarchy in every degree for the projective plane. Finally, we prove an upper bound valid in every degree, and conjecture that it is always sharp.

cs.IT · math.AC · math.AG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.17168

Can LLMs Reason in a Legally Meaningful Manner? A Small-scale Study on European Court of Human Rights Cases

Amogh Raina, Ilias Chalkidis, Daniel Hershcovich, Henrik Palmer Olsen

原文摘要

Reasoning has become a standard technique and feature for contemporary LLMs; however, its application and quality in the context of demanding legal-oriented tasks, such as legal case forecasting, remain under explored. We investigate how LLMs reason in the context of legal case forecasting, using legal cases from the European Court of Human Rights (ECtHR) as a testbed. We evaluate OpenAI GPT 5.4, a recent top-tier LLM, by exploring alternative prompting strategies that are more or less suggestive of what counts as legally meaningful reasoning in the context of ECtHR jurisprudence. We present our findings derived from assessing the model's responses with both human and LLM evaluation. We find that the examined model scores far from ideal in legal reasoning, the model produces structurally complete but substantively shallow analyses, and that LLM-as-a-Judge evaluators are internally consistent yet align only weakly with our trained annotators, i.e., reliable but not a valid substitute for human evaluation. Overall, the expert-curated prompt leads to more comprehensive reasoning, which does not result in more accurate predictions compared to the other examined settings. Based on our findings, we urge the community not to rely solely on automated LLM-based evaluation and to avoid using task accuracy as an appropriate proxy for reasoning quality.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08200

Zirah: A Post-Quantum True Random Number Generator Hardware Signer With an Avalanche Noise

Muhammad Shaheer Bin Junaid

原文摘要

Zirah is a hardware signer built around an STM32F407 microcontroller, and its purpose is to find out, on inexpensive hardware, where a post-quantum signing key is exposed and what actually protects it. The device draws every random bit from a reverse-biased 2N3904 junction in avalanche breakdown, amplified by an LM358 and screened by SP 800-90B health tests, computes ML-DSA-65 (FIPS 204, hedged) on the STM32 with two-share arithmetic masking of the secret-key multiplications, and adds ECDSA P-256 from an ATECC608 secure element over the same digest, once a person has matched an eight-digit digest prefix on its OLED with the PC and pressed a button. A desktop application and a command-line tool drive the board and verify its output, and because only a 32-byte manifest digest reaches the device, it signs files of any type and size, returning signed copies for PDF, Office Open XML, ZIP, PNG and JPEG files and detached records for every other format. NIST's SP 800-90B tool rejected the IID assumption for 1,000,000 raw samples and assessed 6.898 bits of min-entropy per byte on the non-IID track, against the 1 bit the firmware credits, while spectral lines near 116 Hz that hold about 5 % of the variance remain unexplained. At 168 MHz the masked signature took a median of 157 ms over 20 runs and a complete signing operation under 0.8 s, and the signer matched the pq-crystals reference in 1,976 checks natively and on an emulated Cortex-M4. The ATECC608 can neither store the 4,032-byte ML-DSA-65 key nor compute with it, so that key sits in ordinary flash behind readout protection, and on an earlier board, before that protection was enabled, a debugger copied it out and the copy produced a valid ML-DSA-65 signature without the device, although the leakage results come from an instruction-level emulator and nothing here is certified.

cs.CR · cs.AR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08199

Do sEMG Foundation Models Improve Cross-Subject Generalisation?

William Raftery, Dario Farina

原文摘要

sEMG Foundation Models aim to learn general purpose representations over diverse subjects and recording conditions that boost performance on a variety of downstream tasks. However, existing evaluations make it difficult to discern whether pretraining alone is sufficient to combat the cross-subject overfitting which makes machine learning on sEMG so challenging. We conduct a systematic evaluation of three sEMG foundation models across three gesture classification datasets under both intra-session and inter-subject splits, using three fine-tuning strategies designed to isolate the contribution of pretraining. We find that pretraining boosts performance when train and test samples are drawn from the same recording session, but this benefit largely disappears under inter-subject evaluation. In low subject count datasets, pretraining provides little to no benefit and classical ML baselines match or exceed foundation model performance.

cs.LG · q-bio.NC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.05578

Whose Values Are Generated? Measuring Visual Value Leakage in Multilingual Text-to-Image Generation

Zucan Lyu, Binwei Yao, Rheeya Uppaal, Jing Yao, Xiaoyuan Yi, Junjie Hu

原文摘要

Text-to-image (T2I) systems serve users across languages and cultural contexts. However, evaluations of cultural representation focus mainly on recognizable elements such as landmarks, clothing, and activities, overlooking the cultural values that generated images convey. To bridge this gap, we introduce VisionValueBench, a multilingual benchmark that operationalizes six of Hofstede's cultural value dimensions (e.g., individualism versus collectivism) to investigate how T2I systems frame neutral social situations through a particular cultural orientation. We find that value-neutral prompts, which admit diverse cultural interpretations, nonetheless yield images that favor particular value orientations, a phenomenon we call visual value leakage. We evaluate prompts varying in language and geographic cues across 960 social scenarios and six T2I configurations. Generated images consistently favor the same value orientations across all six dimensions, for example, equality over hierarchy (low power distance), individual autonomy over group obligation (individualism), and enjoyment over restraint (indulgence). Prompt language has limited influence on these orientations, whereas geographic cues shift some dimensions toward the associated cultural values while largely preserving the prevailing orientations. These findings reveal substantial homogeneity in the cultural values conveyed by T2I systems worldwide.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2512.01707

StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos

Daeun Lee, Subhojyoti Mukherjee, Branislav Kveton, Ryan A. Rossi, Viet Dac Lai, Seunghyun Yoon, Trung Bui, Franck Dernoncourt 等 9 位作者

原文摘要

Streaming video understanding requires models not only to process temporally incoming frames, but also to anticipate user intent for realistic applications such as Augmented Reality (AR) glasses. While prior streaming benchmarks evaluate temporal reasoning, none measure whether Multimodal Large Language Models (MLLMs) can interpret or leverage human gaze signals within a streaming setting. To fill this gap, we introduce StreamGaze, the first benchmark designed to evaluate how effectively MLLMs utilize gaze for temporal and proactive reasoning in streaming videos. StreamGaze introduces gaze-guided past, present, and proactive tasks that comprehensively assess streaming video understanding. Past and present tasks require immediate responses based on observations available at query time, whereas proactive tasks require models to continuously process incoming frames and respond at the appropriate future moment. To build StreamGaze, we develop a gaze-video Question Answering (QA) generation pipeline that aligns egocentric videos with raw gaze trajectories through fixation extraction, region-specific visual prompting, and scanpath construction. This pipeline produces spatio-temporally grounded QA pairs that reflect human perceptual dynamics. Across all StreamGaze tasks, we observe substantial performance gaps between state-of-the-art MLLMs and human performance, highlighting key limitations in gaze-based temporal reasoning, intent modeling, and proactive prediction. We further provide detailed analyses of gaze prompting strategies, reasoning behaviors, and task-specific failure modes, offering insights into current limitations and directions for future research. All data and code are publicly available to support research in gaze-guided streaming video understanding.

cs.CV · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v6arXiv:2603.10733

The complexity of smooth words over binary alphabets

Julien Cassaigne, Raphaël Henry

原文摘要

Smooth sequences over an alphabet of positive integers $\{a,b\}$ are sequences that are infinitely derivable, the emblematic example being the Oldenburger-Kolakoski sequence $κ$ over $\{1,2\}$. The main way to study their language is to consider a finite version of smooth sequences called smooth words. In this paper we prove that the smooth words are exactly the factors of smooth sequences and we make progress towards the conjecture that the complexity of smooth words over $\{a,b\}$ grows like $Θ\left(n^{\log(a+b)/\log((a+b)/2)}\right)$: we prove the lower bound over any alphabet and the upper bound over even alphabets, and we improve the known upper bound over odd and mixed alphabets. We also provide a dichotomy that links the language, the morphicity and the factor complexity of $κ$.

cs.FL · math.CO · math.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.24207

The Stability of Online Algorithms in Performative Prediction

Gabriele Farina, Juan Carlos Perdomo

原文摘要

The use of algorithmic predictions in decision-making leads to a feedback loop where the models we deploy actively influence the data distributions we see, and later use to retrain on. This dynamic was formalized by Perdomo et al. 2020 in their work on performative prediction. Our main result is an unconditional reduction showing that any no-regret algorithm deployed in performative settings converges to a (mixed) performatively stable equilibrium: a solution in which models actively shape data distributions in ways that their own predictions look optimal in hindsight. Prior to our work, all positive results in this area imposed strong restrictions on how models influenced distributions. By using a martingale argument and allowing randomization, we avoid any assumption on how populations respond to predictions and sidestep recent hardness results showing that deterministic stable models are in general PPAD-hard to compute. Lastly, on a more conceptual note, our connection sheds light on why common algorithms, like gradient descent, are naturally stabilizing and prevent runaway feedback loops. We hope our work enables future technical transfer of ideas between online optimization and performativity.

cs.LG · cs.CY · cs.GT · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.20429

Robust Mechanism Design with Anonymous Information

Zhihao Gavin Tang, Shixin Wang

原文摘要

In practice, auction data are often endogenously censored and anonymous, revealing only limited outcome statistics rather than full bid profiles. We study robust auction design when the seller observes only the distribution of a single anonymous order statistic of the bidders' values and seeks to maximize worst-case expected revenue over all product distributions consistent with the observed statistic. We show that simple and widely used mechanisms are robustly optimal. Specifically, posted pricing is robustly optimal given the distribution of the highest value; the Myerson auction designed for the unique consistent i.i.d. distribution, with uniformly random tie-breaking, is robustly optimal given the lowest value distribution; and the second-price auction with an optimal reserve is robustly optimal when an intermediate order statistic is observed and the implied i.i.d. distribution is regular above its reserve. Without any regularity assumption, when the second-highest value is observed, the best worst-case revenue of a second-price auction with a reserve is still at least a $2-\sqrt{2}\approx 0.586$ fraction of the optimal worst-case revenue. More generally, for a broad class of monotone symmetric mechanisms depending only on the top $k$ order statistics, including multi-unit and position auctions, the worst-case revenue is attained under the i.i.d. distribution consistent with the observed $k$-th order statistic. Our results provide a tractable foundation for non-discriminatory auction design, where fairness and privacy are intrinsic consequences of the information structure rather than imposed constraints.

econ.TH · cs.GT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.31429

PhysTrace: Interpretable Temporal Evaluation of Physical Consistency in Video Generative Models

Taekoan Yoo, Wonkyung Jung, Kyunghun Kim, Kyeongbo Kong

原文摘要

World action models increasingly rely on pretrained diffusion/flow-based video generators assumed to capture physical dynamics for prediction, planning, and action generation. Existing evaluations assess plausibility, probe representations, or measure predictive surprise, yet physical consistency is history-dependent: preceding events constrain what can physically occur later. We introduce PhysTrace, a training-free framework that uses MLLMs to formulate history-conditioned physical expectations and tracks their agreement with observed video windows through temporal video--language alignment, rather than relying on direct plausibility judgments or task-specific probes. On IntPhys2, PhysTrace achieves 67.2% possible--impossible discrimination accuracy, outperforming the evaluated direct MLLM baselines. We further introduce reference-guided masked denoising for controlled reconstruction from mixed possible--impossible video latents. To support these reconstructions and evaluate temporal localization as an additional capability, we introduce IntPhys2-Timing, adding violation intervals to IntPhys2, with PhysTrace achieving a Hit Rate of up to 77.4%. On these reconstructions, human evaluations reveal model-dependent differences in physical consistency and fewer physically impossible outcomes at higher initial noise levels, trends broadly captured by PhysTrace.

cs.AI · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.24317

Don't Pause! Every prediction matters in a streaming video

Dibyadip Chatterjee, Zhanzhong Pang, Fadime Sener, Yale Song, Angela Yao

原文摘要

Streaming video models should respond at the moment an event unfolds, not after the moment has passed. Yet existing online VideoQA benchmarks remain largely retrospective. They pause the video at fixed timestamps, pose questions about current or past events, and score models only at those moments. This protocol leaves streaming outputs untested. To close this gap, we introduce SPOT-Bench, featuring multi-turn proactive queries that evaluate general streaming perception required by an always-on, real-time assistant. SPOT-Bench comes with Timeliness-F1, a consolidated metric that measures streaming outputs by their temporal precision and balanced coverage across the entire video. Our benchmark reveals that during streaming inference: (i) MLLMs detect events reliably in a stream but spam predictions unprompted; (ii) post-training MLLMs for silence reduces spamming but induces unresponsiveness; (iii) half of the streaming video expects no response, which we term dead-time - compute spent here does not affect response latency. These findings motivate Ctrl-SPOT, a training-free streaming controller for MLLMs, that retains their event perception while controlling their streaming outputs for balanced coverage. This establishes a strong baseline on SPOT-Bench.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.08818

Beyond Gait: Person Identification from Millimeter-Wave Point Clouds Across Activities of Daily Living

Xilai Wang, Zixiong Han, Saad Rhanmouni, Chenzhe Zhao, Yunze Lu, Miodrag Bolic

原文摘要

Person identification from millimeter-wave (mmWave) radar point clouds has primarily focused on gait. However, since indoor walking is typically brief and fragmented, gait-based identification is largely constrained to designated passages that support continuous walking. Meanwhile, non-gait activities of daily living (ADLs) are pervasive and also encode discriminative personal signatures. In this study, we evaluate the feasibility of ADL-based identification from sparse mmWave point clouds using mm-ADL, a dataset comprising seven core ADLs collected from 11 subjects under controlled protocols. Moving beyond uniform gait introduces significant activity-dependent variations that confound identity representations. To address this challenge, we systematically benchmark three activity-identity learning paradigms: monolithic learning, joint multi-task learning, and two-stage activity-conditioned routing, under both closed-set identification (ID) and subject-disjoint re-identification (ReID) biometric settings. In parallel, we propose Dual-Stream Static-Dynamic PointNet (DS-SDPNet), an architecture tailored to radar point clouds that captures complementary spatial morphology and motion dynamics. Across seven ADLs, DS-SDPNet achieves 70.2% mean closed-set identification accuracy and outperforms existing baselines on both mm-ADL and mmGait. Moreover, benchmarking the three paradigms without ground-truth activity labels during inference yields up to 68.0% closed-set accuracy and 75.4% ReID mAP, providing a systematic baseline and confirming the feasibility of point-cloud-based biometric identification across diverse daily activities.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08185

Multimodal Hierarchical Mixture-of-Experts for 3D Medical Vision-Language Modeling

Gizem Mert, Szymon Płotka, Pedro R. A. S. Bassi, Wenxuan Li, Zongwei Zhou, Jarosław B. Ćwikła, Arkadiusz Sitek, Ewa Szczurek

原文摘要

Medical 3D scans and reports are inherently hierarchical, with diagnostic cues concentrated in specific anatomical regions across multiple levels of organization. Yet, most medical vision-language models ignore this structure and fail to focus on clinically relevant anatomy. We introduce MedHiVE, which combines hierarchical vision-language Soft Mixture-of-Experts (SMoE) with contrastive learning to jointly model fine-grained anatomy and global scan context. To our knowledge, MedHiVE is the first framework to route both vision and text tokens through a two-level SMoE hierarchy organized by anatomical scale, coupling this with report-derived anatomy-level contrastive alignment for 3D medical imaging. This replaces the direct region-text alignment of statically pooled features and vision-only hierarchical routing of prior work with dynamic, slot-based cross-modal information flow across anatomical scales. MedHiVE operates via a two-level, learnable token-routing mechanism, where local image and text features are first routed through a local SMoE and then fused by a global SMoE into unified multimodal representations. Contrastive learning aligns both anatomy-level and global vision-language representations in a unified space. Pre-trained on 25,000+ CT scans with anatomical supervision, MedHiVE consistently surpasses 11 state-of-the-art methods across 6 datasets on 3 tasks: segmentation, classification, and detection, demonstrating the importance of hierarchical modeling. The code for MedHiVE is at github.com/szczurek-lab/MedHiVE.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08182

BUMP: Brief Unexpected Mid-Interpolation Peak

Melinda Flóra Kiss, Márton Muntag, Adrián Csiszárik, Dániel Varga

原文摘要

We identify an intriguing phenomenon when linearly interpolating between permutation-aligned neural networks: test accuracy briefly improves near the interpolation endpoints before dropping toward the midpoint, which we term BUMP (Brief Unexpected Mid-interpolation Peak). We observe that BUMP appears consistently across datasets, architectures, training regimes, and remains robust under substantial perturbations such as early checkpoints and extreme pruning. Moreover, controlled ablations suggest that it cannot be attributed to trivial regularization effects. While similar near-endpoint gains are visible in prior interpolation plots, they have not been explicitly documented or systematically and thoroughly analyzed. Leveraging this effect, we propose a simple, novel ensembling scheme: weight-prediction mixed ensembling that combines weight mixing with prediction-space mixing. Across our experiments, the resulting ensembling method consistently outperforms standard logit ensembling in test accuracy and yields improved calibration trade-off, highlighting complementary benefits of weight- and prediction-space mixing.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.09805

Parameter Exploration for RLVR via Variational Learning

Vatsal Venkatkrishna, Nico Carlsen Daheim, Iryna Gurevych

原文摘要

Exploration has been a focus of reinforcement learning research for a long time. Recently, there has been growing evidence that it is also an important ingredient in LLM reinforcement learning recipes that can significantly impact downstream performance. Many existing methods control exploration in the action-space, for example, using temperature scaling. However, these methods cannot reorder tokens but only influence the variance in the output distribution. This limits exploration and can lead to divergence or stalled training. Here, we investigate parameter-space exploration, where rollouts are generated by sampling different policies from a posterior that may each explore different rollouts. Sampling less or more diverse policies is then a complementary control lever over exploration. We introduce a family of methods called Perturbed Parameter Policy Optimization (3PO) which use different sampling strategies and different rollout grouping for reward estimation. Experiments on Olmo-3-1025-7B and Qwen2.5-Math-7B across mathematical reasoning and code generation tasks show that these approaches can improve the average downstream performance over standard GRPO at a near-identical FLOPs cost. Moreover, using multiple parameter samples generally produces fewer zero-advantage groups and malformed or incorrect rollouts during training than GRPO and action-space baselines. Overall, our work presents evidence that parameter-space exploration can improve reinforcement learning for LLMs.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v6arXiv:2408.02697

Why Rectified Power Unit Networks Fail and How to Improve It: An Effective Field Theory Perspective

Taeyoung Kim, Myungjoo Kang

原文摘要

The Rectified Power Unit (RePU) activation function, a differentiable generalization of the Rectified Linear Unit (ReLU), has shown promise in constructing neural networks due to its smoothness properties. However, deep RePU networks often suffer from critical issues such as vanishing or exploding values during training, rendering them unstable regardless of hyperparameter initialization. Leveraging the perspective of effective field theory, we identify the root causes of these failures and propose the Modified Rectified Power Unit (MRePU) activation function. MRePU addresses RePU's limitations while preserving its advantages, such as differentiability and universal approximation properties. Theoretical analysis demonstrates that MRePU satisfies the criticality conditions in the limit of a small kernel, and a finite-kernel analysis yields an initialization rule for deep MRePU networks. Experiments on polynomial regression, physics-informed neural networks (PINNs) and real-world vision tasks show that MRePU networks initialized by this rule remain trainable at depths at which RePU networks fail, while their accuracy relative to standard activations depends on the task.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.10828

BALD-SAM: Disagreement-based Active Prompting in Interactive Segmentation

Prithwijit Chowdhury, Mohit Prabhushankar, Ghassan AlRegib

原文摘要

The Segment Anything Model (SAM) has revolutionized interactive segmentation through spatial prompting. While existing work primarily focuses on automating prompts in various settings, real-world annotation workflows involve iterative refinement where annotators observe model outputs and strategically place prompts to resolve ambiguities. Current pipelines typically rely on the annotator's visual assessment of the predicted mask quality. We postulate that a principled approach for automated interactive prompting is to use a model-derived criterion to identify the most informative region for the next prompt. In this work, we establish active prompting: a spatial active learning approach where locations within images constitute an unlabeled pool and prompts serve as queries to prioritize information-rich regions, increasing the utility of each interaction. We further present BALD-SAM: a principled framework adapting Bayesian Active Learning by Disagreement (BALD) to spatial prompt selection by quantifying epistemic uncertainty. To do so, we freeze the entire model and apply Bayesian uncertainty modeling only to a small learned prediction head, making intractable uncertainty estimation practical for large multi-million parameter foundation models. Across 16 datasets spanning natural, medical, underwater, and seismic domains, BALD-SAM demonstrates strong cross-domain performance, ranking first or second on 14 of 16 benchmarks. We validate these gains through a comprehensive ablation suite covering 3 SAM backbones and 35 Laplace posterior configurations, amounting to 38 distinct ablation settings. Beyond strong average performance, BALD-SAM surpasses human prompting and, in several categories, even oracle prompting, while consistently outperforming one-shot baselines in final segmentation quality, particularly on thin and structurally complex objects.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.25716

Quantitative Tiling Stability From Quadratic Discrepancy In Hamming Spaces

Valery, Grishin, Aryeh Lev Zabokritskiy

原文摘要

Quadratic ball discrepancy measures how uniformly a code meets Hamming balls over all centers and radii. Perfect codes minimize this quantity among codes of the same cardinality. We prove a quantitative refinement: at the parameters of every perfect code other than a one-word code or the full space, the discrepancy excess over the minimum is at least an explicit positive multiple of the discrepancy at the packing radius. The latter equals the tiling defect divided by the square of the code cardinality. This defect is the total squared deviation of the covering multiplicity from one. The comparison applies to all codes of that cardinality. For one-error perfect codes, the coefficient is at least one, and no larger constant holds for all such codes; explicit coefficients depending on the parameters can be much larger. The tiling defect also measures the failure of uniform ball noise to smooth a code distribution. Consequently, the same discrepancy excess gives explicit bounds on holes, overlaps, and divergence from the uniform distribution.

cs.IT · math.CO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08180

Quantum Advantage with Sign-Free Proofs: An Oracle Separation between $\mathsf{StoqMA}$ and $\mathsf{MA}$

Yassine Hamoudi, Yvan Le Borgne, Shrinidhi Teganahally Sridhara

原文摘要

Several landmark oracle results (FOCS 2000, FOCS 2025, STOC 2026) establish strict separations along the chain $\mathsf{MA} \subseteq \mathsf{QCMA} \subseteq \mathsf{QMA}$, showing that quantum verification and quantum witnesses can each provide additional power over classical proof systems. These separations, however, use substantial coherent quantum computation, often through the quantum Fourier transform. We prove that a minimal quantum resource already suffices to outperform every classical verifier. Namely, we show the separation $$\mathsf{MA} \subsetneq \mathsf{StoqMA}$$ relative to a classical oracle. The class $\mathsf{StoqMA}$, introduced by Bravyi, Bessen, and Terhal (arXiv 2006), restricts the verifier to classical reversible computation, followed by a single Hadamard-basis measurement. Its power is closely tied to the complexity of stoquastic Hamiltonians, a sign-problem-free and seemingly more tractable class of quantum Hamiltonians. Our separating problem is to determine whether a sparse high-girth graph, given via an adjacency-list oracle, has a large or small Perron--Frobenius eigenvalue. This amounts to a ground-energy estimation task for a related stoquastic Hamiltonian. Our construction builds on a line of work on graph exploration problems with exponential quantum speedups, from welded trees (STOC 2003) to recent constructions (STOC 2021, arXiv 2026).

quant-ph · cs.CC · cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08179

Knowing When to Teach: Learning from Teachable Prefixes in Multilingual Reasoning Distillation

Jaewon Cho, Minseo Yoon, Jinyoung Park, Jinwoo Seo, Jaewon Chu, Alice Oh, Hyunwoo J. Kim

原文摘要

On-Policy Self-Distillation (OPSD) improves reasoning by training a student on its own reasoning, using the same model conditioned on reference solutions as a teacher. Applying OPSD to multilingual reasoning requires the teacher to provide useful feedback across languages, even when the student makes mistakes in intermediate steps. We observe a phenomenon we call Teacher Drift: as these mistakes accumulate, the teacher may follow the student's incorrect steps instead of correcting them. Our analysis shows that this shift tends to occur earlier in lower-resource languages. To account for these differences across languages, we propose Teachable On-Policy Self-Distillation (TOPSD), which determines where and whether teacher supervision should be applied to each reasoning trajectory. TOPSD uses teacher-student likelihood to estimate where drift begins and select a prefix for supervision. It then verifies whether the teacher can recover the correct answer from that prefix, applying distillation only to prefixes that pass verification. Experiments on multilingual mathematical reasoning across ten languages and three model scales show that TOPSD consistently outperforms conventional OPSD, particularly in low- and medium-resource languages.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08177

BabyTheorist: A Benchmark for Learning to Theorize the World from Observation Alone

Doojin Baek, Junyeob Baek, Mingyu Jo, Hosung Lee, Taegu Kang, Gyubin Lee, Sungjin Ahn

原文摘要

How would we know whether a machine truly understands the world? We argue that one key capability is \textit{observational theory learning}: acquiring reusable theories from pure observations and applying them to new situations. Current visual reasoning benchmarks focus primarily on the latter, presenting each task as a few-shot puzzle grouped by a common rule. We introduce BabyTheorist, a benchmark for controlled training and evaluation of observational theory learning. BabyTheorist generates continual streams of before-after visual observations from hidden compositional programs; during training, learners see only the resulting transitions, with no program labels, task identities, or support sets. To support theory learning and evaluation, BabyTheorist controls the program language, a curriculum over program complexity, recurring frequent subprograms, and a continual train-test protocol with level skipping. Seven representative baselines plateau well below ceiling, with the gap widening as the curriculum advances---evidence that BabyTheorist isolates a capability current program-learning approaches do not yet address.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08175

PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers?

Yue Zhang, Jilei Sun, Liqiang Jing, Yijie Wei, Ruohan Yang

原文摘要

Automating printed circuit board (PCB) routing requires coordinating board-level connectivity decisions with geometric execution under strict design rules. Although recent agents can interact with native routing tools, reliable routing on complex boards remains challenging. We present PCBRouteAgent, a multimodal PCB routing agent inspired by how human engineers coordinate global strategy with local execution. A Global Routing Planner combines board images and structured electrical and geometric information to specify connection topology, routing order, corridors, and layer transitions. A Detailed Routing Executor realizes these guides through KiCad's native routing engine and performs bounded local recovery. Unresolved failures are returned as structured feedback, enabling targeted guide revisions while preserving accepted routes. We evaluate PCBRouteAgent on 247 synthetic and real-world boards from four PCBWorld-Bench test splits. It achieves clean-pass rates of 100%, 94.9%, 100%, and 40% on D2, D3-A, D3-B, and D3-C, respectively. On the three real-world subsets, PCBRouteAgent outperforms the best evaluated baseline in clean-pass rate by 13.9, 36, and 10 percentage points, respectively.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08174

NOMA Assisted Coordinated Beam Hopping for VLEO Satellite Communication Systems

Jiayang Kang, Xinwei Yue, Xuyang Zhang, Tian Li, Peng Yang, Chunyu Pan, Shaoli Kang

原文摘要

This paper investigates a non-orthogonal multiple access assisted coordinated beam hopping (NOMA-CBH) scheme in multidimensional very low Earth orbit (VLEO) satellite communication systems, where multiple satellites employ CBH and coordinated beams jointly serve ground users and a dedicated ground station (GS). To characterize the VLEO-specific propagation environment, we develop a channel model that incorporates atmospheric attenuation, Doppler effects, and pointing perturbations. Building upon this architecture and channel model, a low-complexity decoupled (LCD) algorithm is designed to optimize beam scheduling and power allocation. We further derive closed-form outage probability expressions for the ground users and the GS, perform asymptotic analysis to characterize their diversity orders, and evaluate the delay-limited throughput. Simulation results demonstrate that: i) The NOMA-CBH with LCD algorithm achieves an enhanced system sum rate relative to orthogonal multiple access with coordinated beam hopping (OMA-CBH); ii) Across the considered heterogeneous traffic-demand operating points, the NOMA-CBH scheme achieves higher aggregate delivered traffic than the benchmark schemes; and iii) The outage performance of NOMA-CBH is better than that of OMA-CBH.

cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.15838

TinySense+: Entropy-Aware CSI Compression for Scalable and Adaptive Wi-Fi Sensing

Phuc H. Nguyen, Toan Gian, Cuong D. Do, Symeon Chatzinotas, Van-Dinh Nguyen

原文摘要

Wi-Fi human pose estimation requires high-rate channel state information (CSI), making communication a bottleneck when sensing is offloaded from resource-constrained devices. Effective compression must therefore preserve pose information while accommodating different communication budgets. We present TinySense+, an efficient compression framework for scalable Wi-Fi-based human sensing with entropy-aware transmission and test-time rate adjustment. The framework uses a vector-quantized generative adversarial network to encode CSI into discrete latent indices shared between an edge device and a server. A causal Transformer predicts conditional index probabilities for arithmetic coding, while a differentiable rate-distortion objective balances expected code length, CSI reconstruction, and pose accuracy. Prefix-conditioned latent completion reuses the entropy model to infer an omitted suffix, allowing the transmitted prefix length to change without retraining the encoder. We evaluate the framework on MM-Fi and WiPose datasets and prototype it on Raspberry Pi and Jetson Nano devices connected to an RTX 8000 server. On MM-Fi, entropy coding reduces the baseline cost from 8.00 to 4.82 bits per index without changing pose accuracy. Rate-aware training further reduces this cost to 3.21 bits per index and improves PCK20 from 41.21% to 44.01%. Results also show that transmitting half of the latent sequence retains a PCK20 of 40.36%. The evaluated operating range reaches a compression ratio of 5840 with PCK20 = 37.92%. These results show that optimizing latent predictability alongside sensing fidelity provides a useful communication-accuracy trade-off for edge-server Wi-Fi sensing.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08173

Regret Bounds for Profit Maximization in Bilateral Trade: Learning the Best Posted-Price Mechanism

Johannes Brüstle, Simone Di Gregorio, Federico Fusco, Stefano Leonardi

原文摘要

Bilateral trade models the task of intermediating between two strategic agents, a seller and a buyer, willing to trade a good for which they hold private valuations. We study this problem from the perspective of a profit-maximizing broker in a regret minimization framework. At each time step, a new seller and buyer arrive and the broker proposes a trading price to each agent. The trade happens if both agents accept, and the profit of the broker is the difference between the price received from the buyer and the one paid to the seller. At the end of each interaction, the learner only observes whether the trade occurred, and its goal is to achieve sublinear regret relative to the best fixed pair of prices in hindsight. We start by investigating the adversarial version of the problem, where buyer and seller valuations are generated by an adversary. In this setting, we construct a polynomial-time learning algorithm with a $\tilde O(T^{\frac 23})$ regret rate, which is nearly tight even if the valuations are drawn i.i.d. from independent distributions, thus matching the rate for one-sided pricing. Our adversarial algorithm combines a localized estimation procedure with an information-based minimax construction. We then consider valuations drawn i.i.d. from independent distributions satisfying the monotone-hazard-rate (MHR) property and provide a learning algorithm with nearly tight $\tilde{O}(\sqrt{T})$ regret. The algorithm combines localized estimation with a stochastic convex bandit routine applied to the negative logarithm of expected profit. Finally, we complement this result by showing a separation between MHR and regular distributions, proving that the minimax regret rate in the latter setting is $\tilde Θ(T^{\frac 35})$. This last result contrasts with the $\tilde{O}(\sqrt{T})$ regret bound that can be obtained for one-sided pricing with regular distributions.

cs.GT · cs.DS · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08172

Uniform Three-Fold Product Expansion of Algebraic-Geometry Codes over a Fixed Field

Cassie Ding, Min-Hsiu Hsieh

原文摘要

A collection of classical codes $C_1,\dots,C_m$ has product expansion if every low-weight word in the sum of their extensions to the product space can be written as a sum of words supported on few lines, each line being a codeword of the corresponding $C_i$. For $m=2$ product expansion is equivalent to robust testability of the tensor code, while for $m\ge 3$ it is strictly stronger; it is the hypothesis on the local codes behind recent constructions of good quantum LDPC codes, good quantum locally testable codes, and quantum codes with transversal non-Clifford gates. No explicit family over a fixed field was previously known to achieve constant rate, linear distance for both the code and its dual, and 3-fold product expansion at growing length. We prove that for the one-point evaluation codes $C_i$ of length $N_i=728\cdot27^{\,i-1}$ and pole order $\lfloor N_i/5\rfloor$ on the Garcia--Stichtenoth tower over $\mathbb{F}_{729}$, the triple $(C_i,C_i,C_i)$ has product expansion with a constant independent of $i$. The dual codes $C_i^\perp$ then form an explicit fixed-field family of rate tending to $109/130$ and relative distance at least $8/65$. The proof is geometric: we view the words of the sum code as arrays on the product of three copies of the $i$-th curve of the tower, where the parity checks are sections of a line bundle. An exact generation theorem describes the sum-code words supported on the grid footprint of a suitable divisor. A support-localisation argument then shows that every low-weight array lies on such a divisor, after deleting a small number of coordinates. We also give a sufficient criterion for three-fold product expansion in terms of degree and genus ratios, yielding explicit families over every non-prime finite field of order at least $512$. The principal conclusions have been formally verified in Lean 4.

cs.IT · math.AG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08170

The Promise of Strategic Agentic Scambaiting

Abhishek Satyam, Hossein Siadati, Haadi Jafarian, Sima Jafarikhah, Juntao Chen

原文摘要

Scammers have increasingly adopted AI-driven capabilities, evolving from automated message generation to fully agentic conversational systems that scale operations and maximize the exploitation of fraudulent resources before detection and takedown. In parallel, agentic scambaiting has emerged as a defensive approach in which autonomous agents impersonate potential victims and engage scammers in sustained interactions to extract actionable threat intelligence, such as mule bank accounts and cryptocurrency wallet addresses, that can be reported to disrupt fraudulent infrastructures. Together, these developments transform online fraud into an adversarial socio-technical ecosystem in which autonomous scamming and scambaiting agents engage in deceptive interactions while competing over the discovery, preservation, and exploitation of one another's resources. A fundamental and largely unexplored question is how defensive scambaiting can remain effective in an agent-to-agent environment, and under what conditions either side gains a strategic advantage. In this paper, we present a formal model of agent-to-agent fraud interactions that captures the strategic decision spaces available to both attackers and defenders. Using this framework, we analyze the dynamics of engagement, resource consumption, belief adaptation, and disruption outcomes. We find that scammer profitability turns negative once baiting-agent prevalence exceeds certain thresholds, and that when both sides improve at the same pace, defender investment in mimicry quality outpaces equivalent gains in scammer detection capability, so the arms race favors the defender under our baseline parameters. Our model and findings provide insights into the stability, scalability, and long-term effectiveness of autonomous defensive agents in an evolving AI-mediated fraud landscape.

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.19427

Direction-Dependent Path Loss Modeling in Olive Orchards for Precision Agriculture

Mohammad Rowhani Sistani, Katarzyna Kosek-Szott, Pierluigi Gallo

原文摘要

Wireless links deployed in orchards often exhibit significant variability in the strength of the received signal that is not adequately captured by classical distance-based propagation models. In row-structured olive groves, signal attenuation differs markedly between along-row and cross-row propagation directions, leading to discrepancies when using omnidirectional propagation assumptions such as those adopted in the Free Space Path Loss (FSPL) model or ITU-R vegetation loss formulations. This paper proposes a topology-based propagation model that explicitly accounts for orchard layout and the relative positions of radio devices within the plantation structure. Experimental validation was conducted using LoRa technology operating at 868 MHz, and the results were compared with established models from the literature and with the proposed two-dimensional model. The proposed approach achieves a closer fit to measured RSSI data than conventional models, providing a more reliable basis for link budgeting and network planning in structured agricultural environments.

cs.NI · eess.SY

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2307.08336

RAYEN: Imposition of Hard Convex Constraints on Neural Networks

Jesus Tordesillas, Victor Klemm, Jonathan P. How, Marco Hutter

原文摘要

Despite the numerous applications of convex constraints in Robotics, enforcing them within learning-based frameworks remains an open challenge. Existing techniques either fail to guarantee satisfaction at all times, or incur prohibitive computational costs. This paper presents RAYEN, a framework for imposing hard convex constraints on the output or latent variables of a neural network. RAYEN guarantees constraint satisfaction during both training and testing, for any input and any network weights. Unlike prior approaches, RAYEN avoids computationally expensive orthogonal projections, soft constraints, conservative approximations of the feasible set, and slow iterative corrections. RAYEN supports any combination of linear, convex quadratic, second-order cone (SOC), and linear matrix inequality (LMI) constraints, with negligible overhead compared to unconstrained networks. For instance, it imposes 1K quadratic constraints on a 1K-dimensional variable with only 8 ms of overhead compared to a network that does not enforce these constraints. An LMI constraint with 300x300 dense matrices on a 10K-dimensional variable can be guaranteed with only 12 ms additional overhead. When used in neural networks that approximate the solution of constrained trajectory optimization problems, RAYEN runs 20 to 7468 times faster than state-of-the-art algorithms, while guaranteeing constraint satisfaction at all times and achieving a near-optimal cost. Finally, we demonstrate RAYEN's ability to enforce actuator constraints on a learned locomotion policy by validating constraint satisfaction in both simulation and real-world experiments on a quadruped robot. The code is available at https://github.com/leggedrobotics/rayen

cs.LG · cs.RO

查看论文
arXiv ↗PDF ↗