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 16:36 · 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 17:20 — 2026-11-08 17:20（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 16:36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 16:33（北京时间）
版本更新 · v2arXiv:2610.20331

Are We Overthinking One-Step Generation?

Woobin Park, Jaeyeon Kim, Yilun Du, Sitan Chen, Bohyung Han

原文摘要

Diffusion and flow matching are now dominant frameworks for generative modeling in continuous domains, but they typically require multiple network evaluations at inference. This has motivated extensive research on one-step generative modeling primarily built on diffusion and flow, though existing approaches often rely on complex training machinery. In this work, we introduce Priming Models, a simple two-stage framework for training one-step generators. Motivated by the difficulty of distributional training from scratch, Priming Models are first trained on a reconstruction objective, e.g., pixel-space denoising at a fixed noise level, before undergoing feature-space distributional post-training. Our central scientific finding is that this simple reconstruction stage is already enough to entirely alleviate the difficulty of distributional training. Empirically, across class-conditional image generation, text-to-image generation, and world modeling, Priming Models significantly advance the Pareto frontier of training compute vs. generation quality. On ImageNet at $256 \times 256$ resolution, we achieve a state-of-the-art FID of $1.19$ among one-step generators using approximately one-tenth the training compute of prior methods with comparable FID. We open-source our codebase at https://github.com/JaeyeonKim01/priming.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07091

Curvature by Design: A Support Structure for Continuum Robots

Justus Sagemüller, Harald Minde Hansen, Kristin Y. Pettersen

原文摘要

Constant- and piecewise-constant-curvature models are widely used to simplify the kinematics of continuum robots, although the assumed curvature profiles are not necessarily inherent mechanical properties of the robot and may therefore be violated during operation. Rather than assuming a prescribed curvature profile in the kinematic model and estimating deviations from it, this paper presents a multi-segment scissor-based support structure that mechanically constrains a continuum robot to exhibit prescribed constant or spatially varying curvature profiles. The design uses Taylor approximations to enable an overconstrained multi-joint linkage to predictably distribute global bending among the small-angle movements of multiple flexures. The geometric coupling is realized using compliant flexure joints, enabling the support structure to be manufactured as a single piece. The structure is integrated with a tendon-actuated continuum robot with a flexible backbone. Experiments show that the structure makes the robot resistant to deformations other than the prescribed curvature, significantly enhancing shape precision compared to classical flexible-backbone designs. This constrains the robot from making S-shapes when external loads are applied in the opposite direction of the bending. By mechanically constraining the admissible deformation, the proposed structure reduces the number of independent shape variables that must be estimated.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07089

Polynomial-Time Computation of Extensive-Form Proper Equilibria in Two-Player Zero-Sum Games

Sam Ganzfried

原文摘要

We give a deterministic polynomial-time algorithm for computing an exact extensive-form proper equilibrium in a finite two-player zero-sum extensive-form game with perfect recall and rational data. Properness is understood in the agent normal form: an action at an information set is penalized relative to a better action while all other local behavioral choices, including the player's own future actions, remain fixed. Our algorithm assigns each information set a geometric permutahedron of allowable action probabilities. A scaled doubly stochastic representation embeds these restrictions in a polynomial-size sequence-form polytope; a saddle point then satisfies the local $\varepsilon$-properness inequalities. To obtain an exact equilibrium rather than a solution at an arbitrarily small numerical perturbation, we establish sign stability of a parametric linear system, construct a persistent feasible basis, and extract the limits of behavioral ratios. The resulting probabilities are rational and have polynomial encoding length, including at information sets whose realization probabilities vanish.

cs.GT · cs.AI · cs.MA · econ.TH

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07088

Synthesizing symbolic models of human and machine reasoning at scale

Solim LeGris, Philipp Mondorf, Jinran Jin, Akshay K. Jagadish, Brenden M. Lake, Todd M. Gureckis

原文摘要

Symbolic models offer a powerful account of cognition, but their scope has historically been limited by the need for hand-engineering and computational tractability. We show how advances in artificial intelligence (AI) can scale symbolic modeling and help overcome these engineering limitations. We introduce Behavior-Conditioned Symbolic Synthesis (BCSS)---an approach for automated search of interpretable, deterministic symbolic programs that verifiably reproduce behavior---and apply it to model both human and machine behavior across hundreds of challenging reasoning problems. Analyzing these programs reveals that both people and machines tend to oversimplify, adopt rules that are partial explanations for their observations, and misinfer dependencies between problem features. These shared signatures are modulated by available resources, with reasoning effort predicting the extent to which machines simplify and explain their observations. Together, these results point to underlying mechanisms reminiscent of satisficing in both people and machines, and illustrate how BCSS offers a general approach for interpreting and comparing rule-based reasoning of humans and black-box AI systems.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07087

WAVES: Wearable Active Vibroacoustic Elasticity Sensing for Low-Cost and Non-Invasive Muscle Stiffness Monitoring

Shubham Rohal, Dong Yoon Lee, Shijia Pan

原文摘要

Muscle stiffness is a physiologically meaningful biomarker associated with a wide range of musculoskeletal and neurological conditions. However, existing muscle stiffness assessment methods, such as shear wave elastography (SWE), manual palpation, and handheld mechanical probes, remain impractical for continuous, everyday monitoring due to bulky hardware, operator dependence, and limited self-use. Meanwhile, wearable muscle-sensing modalities such as Electromyography (EMG) and Mechanomyography (MMG) primarily capture muscle activation rather than passive mechanical properties of tissue at rest, leaving a critical gap in portable monitoring of resting muscle stiffness. In this work, we present WAVES, a wearable system for continuous monitoring of muscle stiffness via active vibroacoustic sensing. WAVES injects controlled vibroacoustic excitation into soft tissue and estimates muscle stiffness by measuring shear-wave propagation velocity through Time-Difference-of-Arrival (TDoA) analysis across spatially distributed wearable sensors. To achieve accurate TDoA estimation with low-cost wearable hardware, we develop a physiology- and quality-guided vibroacoustic sensing framework that effectively screens and refines TDoA for accurate stiffness estimation. We evaluate WAVES through characterization experiments using ballistic jelly and end-to-end on-body evaluation with human participants. Results demonstrate that WAVES can robustly estimate muscle stiffness across multiple users and different superficial muscles while enabling lightweight, wearable deployment for everyday use. WAVES is able to achieve a muscle stiffness estimation error of 13.1% or less across multiple users and multiple muscle groups.

cs.ET

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07084

DMuon: Scaling Matrix Optimizers in Data Parallelism with Topology-Aware Matrix Ownership and Communication

Starrick Liu, Ruizhi Chengze, Lufang Chen, Michael Zhao, Ran Yu, Xiaofan Li, dance kuzi, Yue Zhang 等 13 位作者

原文摘要

Matrix optimizers such as Muon update whole weight matrices, which conflicts with the element- or row-wise sharding of data-parallel runtimes. Once parameters are sharded as well, matrix optimizers incur extra communication or repeated computation. We present DMuon, a matrix-granular optimizer runtime for PyTorch FSDP (ZeRO-2/3) and HSDP. DMuon assigns each matrix a unique owner, which performs the Newton--Schulz (NS) iteration and optimizer update on the full matrix, and balances the load across owners by computational cost. On HSDP, ownership is global across replicas, so the cluster keeps a single copy of gradients and optimizer state, and updated parameters are published across nodes as soon as they are ready, overlapping subsequent computation. This layout makes every collective sparse and variable in length, so DMuon schedules these collectives as their data becomes ready and routes them along the cluster's two-level network. On up to 256 H100 GPUs, across three dense LLMs and two VLA models, DMuon matches or exceeds the training throughput of PyTorch FSDP2 with AdamW, reaching 1.05$\times$ that of FSDP2 with AdamW at the median on 256 GPUs. The optimized parameter gathering and gradient reduction absorb the extra communication and computation a matrix optimizer requires. Against a gather-then-replicate Muon baseline, DMuon's throughput is 2.1 times as high at the median.

cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33857

TrackTok: Object-Centric Video Tokenization with Semantically Persistent Tokens

Nhi Pham, Christopher Wewer, Bernt Schiele, Jonas Fischer, Jan Eric Lenssen

原文摘要

We introduce TrackTok, an efficient video tokenization framework that produces object-centric tokens, i.e., tokens that consistently encode the same semantic objects across time, even as it moves, deforms, or undergoes partial occlusion. Conventional patch-based or existing holistic tokenizers produce token identities often tied to fixed image locations. In contrast, our approach learns temporally persistent object-centric representations that bind visual features across frames into stable semantic units. This enables substantially more compact, continuous latent video representations, reducing the number of tokens required for downstream generative modeling with state-of-the-art flow models, while preserving the semantic structure needed for high-quality synthesis. Our tokenizer offers a favorable quality-efficiency trade-off. TrackTok achieves comparable class-conditional generative FVD on UCF-101 dataset at 8 times fewer latent tokens and better latency, and outperforms existing 1D tokenization baselines on frame prediction task on Kinetics-600 across low token budgets. These results suggest that object-aligned and temporally persistent tokenization is a promising direction for scalable video generation, where reducing latent token counts is critical for efficient modeling. Our code for this work is available at https://github.com/phamleyennhi/tracktok.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2503.13344

DeepSTEP: Simultaneous Tracking and Estimation of Pose for Animals and Humans

Shashikant Verma, Harish Katti, Soumyaratna Debnath, Yamuna Swamy, Shanmuganathan Raman

原文摘要

Maintaining a consistent identity across video frames while estimating pose is crucial for downstream tasks such as behavior analysis and action recognition, yet existing pipelines largely decouple tracking and pose estimation. Top-down methods rely on per-frame detections followed by identity association, leading to increased computational cost and error propagation, whereas bottom-up approaches often struggle to preserve identity reliably in multi-instance settings. To address these limitations, we introduce DeepSTEP (STEP), a Transformer-based framework for joint tracking and pose estimation across diverse animal species and humans. STEP unifies localization, identity maintenance, and keypoint estimation into a single model, eliminating the need for per-frame detections or post hoc matching. Our approach leverages discriminative model weight prediction to propagate target identity across frames while predicting anatomically meaningful keypoints. Discriminative model prediction typically requires predefined target states. In contrast, STEP assumes only an initial bounding box in the first frame, removing the need for explicit keypoint initialization. This is enabled by two components: Gaussian Map Soft Prediction (GMSP) and Offset Map Regression Adapter (OMRA), which allow direct keypoint prediction and simplify inference. Starting from the initial bounding box, STEP tracks the subject and estimates its pose in subsequent frames. We train and evaluate STEP on datasets spanning multiple species, demonstrating strong performance and greater efficiency than existing methods. By jointly modeling tracking and pose, STEP provides an effective and scalable solution.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.14171

CSI-JEPA: Towards Foundation Representations for Ubiquitous Wi-Fi Sensing with Minimal Supervision

Xuanhao Luo, Zhizhen Li, Yuchen Liu

原文摘要

Channel state information (CSI) provides a widely available sensing modality for human and environment perception, but existing CSI sensing models usually rely on task-specific supervised training and require substantial labeled data for each task, device, user, or environment. This limits their scalability in practical deployments where unlabeled CSI is abundant but labeled data is costly to collect. In this paper, we present CSI-JEPA, a self-supervised predictive representation learning framework for label-efficient and transferable Wi-Fi sensing. CSI-JEPA learns reusable temporal-spectral representations from unlabeled CSI samples by predicting latent features of masked channel regions from visible context. To better match the physical structure of CSI, it jointly tokenizes CSI along the time and subcarrier dimensions and introduces a channel variation-aware masking strategy that prioritizes regions with stronger local channel dynamics. After pretraining, the encoder is frozen and adapted to downstream sensing tasks using lightweight task-specific adapters. We evaluate CSI-JEPA on seven real-world Wi-Fi sensing tasks spanning diverse objectives and deployment settings. The results show that CSI-JEPA improves downstream sensing performance over competitive baselines, achieving up to 10.64 percentage points (pp) mean accuracy gain over the supervised Transformer and matched-budget label savings of up to 95.0%. Across unseen tasks, environments, hardware platforms, and CSI organizations, frozen CSI-JEPA improves downstream adaptation by up to 22.92 pp over non-pretrained baselines, demonstrating strong representation transferability.

cs.LG · cs.NI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.03261

Exact Agreement Expansion up to the Top via Non-polarity

Tali Kaufman, Huy Tuan Pham

原文摘要

Agreement expansion asks whether local assignments to faces of a poset that usually agree on a sampled common face must agree with a single global function on most faces. Agreement expansion is exact (approximate) if local assignments need to exactly (approximately) agree with the global function. We suggest a new proof technique for agreement expansion that enables agreement expansion in settings which were previously beyond reach, such as: exact agreement expansion for Grassmannian posets (before only simplicial complexes support exact agreement expansion); agreement expansion based on assignments to top faces of the a complex (before agreement expansion is generally proven only for assignments to low dimensional faces); agreement expansion from one-sided spectral expansion (before, two sided spectral assumption was needed in general settings). Specifically, for down-closed simplicial and Grassmannian complexes, we prove an exact agreement theorem between any two layers assuming one-sided spectral expansion in links of singletons. As an application, we show that full bases of every rank-$k$ matroid admit exact agreement with soundness $O(k^2/[h(k-h)])$ when tested through $h$-element independent sets. We also obtain exact agreement on Grassmannian posets under one-sided spectral expansion, with stronger soundness under a local distance guarantee. Our key proof ideas center around non-polarity of the distributions of local assignments, probed via a random exposure of elements.

cs.CC · cs.DM · math.CO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07081

Wide View Synthesis from Overlapping Perspective Cameras in Autonomous Driving

Kaixuan Zhang, Zhipeng Xiong, Minxian Li, Mingwu Ren, Xiatian Zhu

原文摘要

Multi-perspective-camera systems are widely adopted since they provide broad visual coverage for autonomous driving, motivating the synthesis of a unified wide view from spatially separated observations. In this work, we formulate wide view synthesis (WVS), which aims to synthesize a geometrically consistent wide view at a specified virtual viewpoint from multiple perspective cameras. Unlike conventional image stitching, WVS requires reasoning about 3D geometry and visibility to handle depth-dependent parallax and occlusions arising from spatially separated camera centers. While vanilla 3D Gaussian Splatting (3DGS) enables high-fidelity view synthesis, its reliance on per-scene optimization limits its applicability to driving scenes. Furthermore, WVS introduces additional challenges, *e.g.*, peripheral stretching under perspective projection and photometric inconsistencies across cameras. To address these challenges, we propose **Wide-View Gaussian Splatting (WV-GS)**, a feed-forward Gaussian-splatting framework that synthesizes wide views without per-scene optimization. Specifically, we introduce Piecewise Perspective Rendering (PPR) to mitigate peripheral stretching through local perspective projections sharing a common camera center, and Spatial Affine Photometric Modeling (SAPM) to account for camera-dependent photometric variations during training. We further introduce **WideDrive**, a synthetic benchmark providing dense ground-truth wide views and adapt a LiDAR-projected sparse-reference protocol to real-world datasets. Extensive experiments on multiple datasets demonstrate the effectiveness of WV-GS for WVS. Dataset and code will be publicly released.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07078

Optimistic Hedge in General-Sum Games: Fundamental Limits and Regret Bounds via Temporal Approximation

Yuval Dagan, Nadav Eisen, Liad Erez, Tomer Koren

原文摘要

Optimistic Hedge, a multiplicative weight update with one step of extrapolation, is one of the most natural regret-minimizing dynamics for games, and characterizing its regret has been a longstanding open question. Daskalakis, Fishelson and Golowich proved that if all $m$ players in a finite general-sum game follow Optimistic Hedge with a fixed learning rate, each player's regret is polylogarithmic in the horizon $T$. Subsequently, Ha showed that an appropriate choice of learning rate makes each player's regret bounded independently of $T$. This bound, however, is non-constructive and its dependence on the number of actions $n$ is not explicit, leaving open whether Optimistic Hedge can achieve a constant regret bound which is polynomial in the size of the game. We show that the answer hinges on the number of players. In two-player games, there is a learning rate for which Optimistic Hedge guarantees $O(n\log n)$ regret independent of the horizon. In three-player games, however, no such bound is possible: for any learning rate up to an absolute constant and for sufficiently large horizon $T$, there is a game with $n$ actions per player in which some player's regret is $2^{Ω(n)}$, and more generally, for every $m\ge3$ we construct $m$-player games in which some player's regret is $2^{Ω(mn)}$; for learning rates above $2^{-Ω(mn)}$, that player's regret even grows linearly in $T$. Our upper bound is based on a temporal approximation framework for the analysis of Optimistic Hedge. Starting from the variance-based RVU bound of Daskalakis et al., we approximate the losses over time-localized windows by well-behaved functions, whose total variation is a small fraction of their cumulative variance. In $m$-player games, the same framework gives a significantly simplified proof of the recent $O(\sqrt{m}\log n\log T)$ regret bound due to Ha.

cs.LG · cs.GT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.29157

Hardness of Counting Orderings: Taking Gadget Amplification to the Limit

Marcelo Arenas, María Alejandra Schild, Bernardo Subercaseaux

原文摘要

We introduce a new elementary technique for proving $\#P$-hardness results under Turing reductions, and showcase its applicability by settling the counting complexity of several fundamental problems about counting orderings in graphs, posets, and geometric configurations. The technique addresses a natural difficulty in counting reductions: when designing gadgets that attempt to enforce a semantic property, the introduction of the gadgets themselves can affect the function to count in complicated ways. In a nutshell, we introduce an amplification parameter $q$ for the gadgets (e.g., replacing a subset of the vertices of a graph by $q$ copies) and show that the limiting behavior when $q$ tends to infinity, or even to negative values, filters out the unwanted effects of the gadgets, which allows us to recover the desired counts. These limits can be computed symbolically via interpolation, after showing that the probability of a random ordering satisfying the problem's constraints is a rational function in $q$. Concretely, with this methodology, we show $\#P$-completeness for counting the following objects: (a) successive vertex orderings, even on bipartite graphs, (b) $st$-numberings of graphs, (c) shellings, even for bipartite graphs, (d) perfect elimination orderings, even for split graphs, (e) linear extensions of N-free posets of height $3$, (f) linear extensions of posets of height $2$, and (g) peeling sequences of point sets. Result (e) settles a conjecture of Felsner and Manneville (2015), and although result (f) was first proved by Dittmer and Pak (2018), we include an alternative proof, using our technique, that does not rely on the result of Brightwell and Winkler (1991) about hardness of counting for general posets. Result (g) answers a question of Eppstein.

cs.CC · math.CO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07073

When Verification Is Not Agreement: Cross-Agent LLM-to-Dafny Formalization

Priyanath Maji

原文摘要

A verified Dafny postcondition certifies that a formula holds, but it does not guarantee that the result was reached through genuine independent reasoning. We introduce a cross-agent formalization protocol where a Specifier model translates clinical trial criteria into a Dafny predicate, and an Implementer model writes an operational method checked against it. A same-model control establishes that even with no capability gap, independent re-extraction from identical text agrees only 59.3% of the time. Evaluating four model configurations on 96 clinical trial documents, we find that agreement is highly sensitive to how model capability is allocated across the two roles: the GPT-4.1-nano/GPT-4.1-mini configuration achieves 53.0% agreement when the stronger model is the Implementer, but only 14.3% when the roles are reversed. The strongest tested configuration, GPT-5.6-luna/GPT-5.4-mini, improves agreement to 34.4% but remains below the same-model baseline and is dominated by direct contradiction (42.7%). We also detect a critical verification artifact in which a weaker Implementer satisfies the postcondition by invoking the Specifier's predicate directly; after structural auditing, corrected agreement falls from 14.3% to 13.2%. Our results show that verification success alone is insufficient evidence of independent cross-agent agreement, and that model capability does not guarantee agreement when formalizing the same source independently.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07072

Automated Feedback to Peer Tutors Increases Their Talk Moves and Learner Reasoning but Not the Balance of Talk

Dorottya Demszky, Yann Hicke, Joy Yun, Mariah Olson, Max Karpawich, Anees Iqbal, Matt Wu, Jimmy Huang 等 10 位作者

原文摘要

Automated feedback on classroom discourse improves instruction in professional and online teaching contexts, and recent work suggests that delivering similar feedback to learners may strengthen these effects by sharing responsibility for participation. Whether this holds in small-group volunteer tutoring has not been tested. We present results from a randomized controlled trial across two four-week SAT mathematics bootcamps on the Schoolhouse.world platform, involving 1,030 volunteer tutors, 7,443 learners and 6,508 recorded sessions. Tutors were randomly assigned to receive no feedback, automated feedback on their own discourse, or that feedback together with participation feedback delivered to their learners under one of two motivational framings. Feedback to tutors increased eliciting of learner ideas, uptake of learner contributions, and learner reasoning by 8-15%, and the pattern replicated across both bootcamps. However, tutor talk time, which averaged 91.5% in the control group, did not change in any condition, and learner-facing feedback did not further change discourse. Interviews with 17 tutors indicate that they adopted the moves the feedback recommended but were limited by learners who did not respond. Interviews with 13 learners suggest why the learner-facing feedback had little effect: it reported a group-level rather than a learner-level statistic, some learners preferred to listen, and learner-to-learner interaction was rare in these sessions. Automated feedback can change how tutors invite learner thinking, but shifting how much learners talk likely requires changes beyond feedback.

cs.CL · cs.ET · cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.34763

The Physical Cost of Context: Quality-Constrained Resource Accounting for Coding Agents

Zhongming Yu, Yitong Ma, Hengjia Yu, Boqin Yuan, Xiangye Lin, Hejia Zhang, Jishen Zhao

原文摘要

Coding agents resend a growing context on every model call, and context policies are usually judged by the prompt tokens they save. Executed work also depends on call count and prefix reuse: a caching runtime prefills only the tokens after the longest cached prefix. A shorter prompt can therefore cost more if it rewrites cached history. Our quality-gated protocol splits executed prefill into logical prompt minus reused prefix and measures KV residency, time, and energy. On 450 localization cases derived from SWE-rebench V2, preloading ten retrieved blocks (Eager) and adding anchored history compaction (Compact) both pass a five-point non-inferiority gate. In a separate 900-cell study, Eager cuts model calls by 35.7% and the GPU-energy proxy by 33.2% against on-demand search (Grep); Compact saves nothing further. Enabling prefix caching leaves Eager's prompt volume similar (+8.3%; its 95% CI spans zero) but cuts its uncached prefill by 67.7%. Deleting history can turn a token saving into extra work. With mini-SWE-agent on 100 SWE-bench Verified instances, keeping only the last five observations (Mask-5) cuts Eager's prompt volume by 33.3% but loses 135.9k reusable tokens per task. Uncached prefill rises by 608.5%, the energy proxy by 125.6%, and the policy misses the quality gate. Policies thus save physical work by shortening the trajectory and can multiply it by editing reusable history.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07071

Shaping & Monitoring Models through their Internal Representations

Thomas Fel, Matthew Kowal, Matt Feiszli, Satchel Grant, Andrew Lee, Chris Earls, Fatih Dinc, Vasudev Shyam 等 26 位作者

原文摘要

We propose Mechanistic Shaping, a unified framework for shaping models through their internal representations. Mechanistic Shaping is applied during training so that models follow specifications (rules) about which concepts they express, measured via their outputs or internal representations (e.g., no harmful content), and also which concepts they rely on, i.e., what they use to make their decisions (e.g., not a candidate's gender when screening a résumé). Across multiple domains (vision, medical imaging, language), scales (up to 32B parameters), and training paradigms (classification, SFT, DPO, GRPO), we find that Mechanistic Shaping substantially reduces targeted behaviors while preserving task performance. Since training against a representation can also modify it, we ask whether shaped concepts remain monitorable, a question that depends on the class of monitors considered. We therefore introduce a hierarchy of such classes, which separates a concept that escapes one probe from a concept that is truly gone. We characterize three geometric mechanisms of circumvention: the concept can drift away from the monitor, be erased from the layer, or persist in higher-order statistics as a nonlinear encoding, which we explain through a product-code construction. Although other mechanisms may arise in different settings or at larger scales, these three account for all of our observations, and each can be detected by a matching monitor. In practice, we find that shaped concepts largely remain monitorable: refitted linear probes recover the concept in most settings, and the original probe remains reliable whenever gradients do not flow through it. Taken together, these results point to the potential of using interpretability as a tool for training, and call for a correspondingly rigorous science of interpretability-based training.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2510.02906

FinMultiHopQA: A KG-Grounded Multi-Hop Financial QA Benchmark for Evidence-Driven Reasoning

Abhinav Arun, Reetu Raj Harsh, Bhaskarjit Sarmah, Stefano Pasquali

原文摘要

Multi-hop financial question answering often requires composing evidence distributed across filing sections, fiscal years, and peer companies. Prior financial QA benchmarks address parts of this problem individually, but none jointly support controlled multi-hop taxonomies, document topologies, motif-level reproducibility, and provenance-linked auditability at scale. We introduce FinMultiHopQA, a benchmark of 15,600 qualitative and quantitative questions, grounded in FinReflectKG, a temporally indexed financial knowledge graph derived from SEC 10-K filings with 17.5M+ triples. The pipeline instantiates statistically salient 2-3 hop typed KG motifs across intra-document, inter-year, and cross-company regimes. Beyond closing this gap, the same construction lets us hold each question's underlying evidence constant while varying only its presentation - embedding it in noisy surrounding context or changing its order - giving a controlled instrument to study a secondary question at scale: using six such presentations, we test whether reasoning LLMs' performance depends on evidence structure. Results confirm this: despite their reasoning capacity, judged correctness remains consistently lower under less-structured presentations of the same evidence - most sharply for quantitative cross-company reasoning and 3-hop branch motifs - indicating that reasoning alone does not fully offset how evidence is structured; KG-linked presentation also uses fewer input tokens by design. We release the benchmark, provenance annotations, model outputs, evaluation records, and supporting technical documentation.

q-fin.CP · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07069

Finite-Time Convergence and Regret Guarantees for Neural Reinforcement Learning in POMDPs

Jingjuan Huang, Zhiyao Zhang, Alvaro Velasquez, Nathaniel D. Bastian, Jia Liu

原文摘要

Reinforcement learning (RL) in Partially Observable Markov Decision Processes (POMDPs) is computationally challenging due to the curse of long-range dependence on history. Fortunately, recent studies have shown that a range of POMDPs that satisfy the filter stability assumption can be well approximated by a superstate Markov Decision Process (MDP) based on a truncated history in a finite-memory window, with a value gap that decays with the window length. However, existing finite-time convergence analyses on such superstate MDP surrogates are either limited to over-simplified linear function approximation or rely on an i.i.d. sampling oracle that is violated by POMDP trajectories, both of which severely limit the applicability of these theoretical results in practice. This motivates us to bridge the gap by investigating RL in POMDPs with nonlinear neural value function approximation. Our main contributions are threefold: i) We first establish a new finite-state MDP point-wise approximation error bound, which lays the foundation for our RL algorithm design and analysis in POMDPs; ii) By applying Temporal-Difference (TD) learning to POMDP-generated superstate transitions and targeting the Bellman fixed point of the superstate MDP, we prove a finite-time critic error bound with nonlinear neural value function approximation; and iii) By combining the neural critic function approximation error bound with the policy mirror descent framework, we obtain a finite-time sublinear regret against the optimal POMDP value. To the best of our knowledge, such a finite-time sublinear regret based on neural function approximation is the first in the literature for finite-memory POMDPs. Our numerical experiments also verify our theoretical results.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07068

ReDrone5G: Field Trial Evaluation of Remote UAV Media and Control over Public and Private 5G Networks

Kashif Mehmood, Tu Dac Ho, Katina Kralevska, Hacı Mehmet Güzey

原文摘要

Drone-assisted live media production stresses cellular networks by combining high-rate uplink video, continuous telemetry, and latency-sensitive command/control on a mobile aerial platform. This paper presents ReDrone5G, an end-to-end field-trial platform evaluated across two practical fifth-generation (5G) deployment paths: a commercial public non-standalone (NSA) network in Sivas, Turkiye, and a private OpenAirInterface (OAI)-based standalone (SA) testbed in Trondheim, Norway. The same drone, media, telemetry/control, and monitoring stack is used in both trials, which are treated as complementary, non- equivalent field deployments rather than a controlled A/B comparison. Results show that the commercial deployment sustains remote drone media operation, while the evaluated private deployment exhibits lower control RTT and video latency and higher video throughput. The private setup also exposes signal-to-noise ratio (SNR), reference signal received power (RSRP), modulation and coding scheme (MCS), physical resource block (PRB), and block error rate (BLER), providing cross-layer radio/network context. ReDrone5G shows that public 5G is useful for feasibility validation, while private 5G enables repeatable experimentation, tuning, and future service assurance for drone-media workflows.

cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07066

Cooperative Multi-Agent Reinforcement Learning via Epigraph-Form Guided Exploration

Sungil Son, Hoseong Jung, Dahyun Oh, H. Jin Kim

原文摘要

Discovering cooperative behavior in multi-agent reinforcement learning (MARL) is challenging due to the combinatorial complexity of joint state-action spaces, which hinders the emergence of coordinated behaviors from trial-and-error alone. Intrinsic rewards are often used to aid discovery, but naively combining them with team objectives can distort the learning signal, compromising task performance. In this paper, we propose EFXPLORER, a constrained exploration framework that maximizes exploration objectives subject to a constraint that preserves established task performance. We solve the resulting problem using an epigraph reformulation that introduces adaptive exploration budgets. This approach separates intrinsic rewards from task objectives and regulates exploration through task feasibility. To further encourage diverse and temporally extended exploration, we incorporate a successor distance-based intrinsic reward that captures long-horizon dependencies. Empirically, our method outperforms strong baselines and induces novel cooperative strategies across SMAX, VMAS, and MPE benchmark suites.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.01367

DUEL: Exact Likelihood Reshapes Masked Diffusion Scaling Laws and Beyond

Gilad Turok, Yair Schiff, Chris De Sa, Volodymyr Kuleshov

原文摘要

Masked diffusion models (MDMs) are trained to predict tokens in every order but generate in one. As such, MDM likelihood is an intractable sum over all orders. The evidence lower bound (ELBO) is used as a proxy for likelihood, but it is a loose bound and assumes positions are unmasked uniformly at random. Frontier MDMs, however, select positions with deterministic rules such as confidence. To resolve this mismatch we introduce DUEL, a framework that unifies common deterministic MDM samplers. DUEL computes the likelihood exactly, under the sampler that is actually used during generation. DUEL is a simple plug-and-play algorithm applicable to any pretrained MDM with no retraining. To compute the likelihood of a text sequence, simply replay generation, reveal the true tokens instead of sampled ones, and sum their log-probabilities. Evaluating with DUEL instead of the ELBO changes what we conclude about MDMs. The perplexity gap between MDMs and autoregressive (AR) models shrinks by up to 32% in-domain and 82% zero-shot. In scaling laws, the reported 16x MDM-AR compute gap falls to 9x under DUEL, showing over 1/3 of it is an evaluation artifact. Scoring multiple-choice answers with likelihood via DUEL instead of the ELBO improves LLaDA-8B accuracy on all six tasks, by up to 9.7 points. DUEL also selects samplers correctly: it matches a gold-standard LLM judge on every decided comparison, which generative perplexity and MAUVE fail to do. DUEL reveals that MDMs are more competitive with AR models than the ELBO suggests.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07065

Stochastic Dynamics of Generative AI: From Autoregressive Models to Interacting LLM Networks and Neural SDEs

Vikram Krishnamurthy, Yiming Zhang, Luke Snow

原文摘要

This paper develops a stochastic dynamical-systems perspective on three classes of generative AI models. First, we formulate large language models (LLMs) as high-dimensional nonlinear autoregressive models with attention-based dependencies. This formulation connects pretraining by conditional maximum likelihood to sequential token generation and provides a probabilistic interpretation of LLM operation. Second, we consider networks of interacting LLMs and characterize their collective behavior through mean-field ordinary differential equations. These dynamics provide a framework for understanding emergent preferential attachment and persistent structural biases, including type-dependent glass-ceiling effects. Third, we consider neural stochastic differential equations (SDEs) as continuous-time generative models for stochastic trajectories, including those observed at irregular time intervals. We discuss their training with particular emphasis on Wiener-space cubature methods based on rough-path analysis as an efficient alternative to Monte Carlo estimation. Together, the three settings address probabilistic prediction, information exchange and emergent behavior in interacting networks, and path-space generative modeling.

cs.LG · eess.SP · eess.SY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02490

How Contextual Information in Physical Environments Shapes Decisions with AI

Omar Elgohary, Amanda Elvarsdottir, Vannessa Lee, Zhu-Tian Chen

原文摘要

AI assistants in augmented reality may advise users about parts of the physical world they cannot directly observe. We ask whether contextual information from the situation helps users make better decisions with fallible AI. In an AR visual- search study (N = 32), we varied target prevalence and scene visibility while participants judged whether a key was present, with or without AI assistance. Lowering target prevalence and revealing part of the desk together improved observed AI-assisted accuracy, but our analysis did not demonstrate that this gain came from participants making better use of context. Context also changed which answers seemed plausible: when keys were rare, participants became more skeptical of Present suggestions, but this shift applied to both correct and incorrect suggestions rather than improving selective acceptance of correct advice. Revealing part of the desk also increased decision time, with little evidence of better AI use. Overall, contextual information can shape AI- assisted decisions and increase decision effort without necessarily helping users judge when the AI is correct.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07063

SD-LoRA: Training-Time Structural Distillation into LoRA for Few-Shot Vision-Language Adaptation

Mohammed Rahman Sherif Khan Mohammad, Ardhendu Behera, Sandip Pradhan, Swagat Kumar, Yonghuai Liu

原文摘要

Few-shot adaptation of vision-language models must balance two competing goals: learning fine-grained visual distinctions from very limited supervision and preserving the efficiency that makes frozen CLIP-like models attractive for deployment. Existing lightweight adaptation methods, including prompt tuning, LoRA, and cache-based adapters, typically supervise global image embeddings and therefore underuse token-level structure. Conversely, structure-aware methods exploit local evidence but often introduce additional inference-time computation. We propose SD-LoRA, a structural distillation framework that uses token-level graph reasoning only during training and transfers its effects into a lightweight LoRA-adapted CLIP model. During training, a heterogeneous graph teacher models patch-patch, global-local, and visual-text relations over high-resolution ViT tokens. Rather than retaining this graph at test time, SD-LoRA transfers its structural bias into the shared CLIP-LoRA backbone through implicit distillation and Prototype Predictive Alignment, which aligns graph-conditioned representations with support-derived class prototypes. At inference, the graph teacher is discarded; prediction requires only a single CLIP-LoRA forward pass and a cache-based classifier. Across 11 few-shot benchmarks, SD-LoRA improves over a strong CLIP-LoRA baseline by 2.4/1.8/3.0/2.4/2.0 percentage points in the 1/2/4/8/16-shot settings, respectively, without additional graph computation at test time. Results on base-to-novel generalization, cross-dataset transfer, out-of-distribution robustness, and calibration further show that training-time structural supervision improves both accuracy and transfer reliability. Code is available at https://github.com/MR-Sherif/SD-LoRA.git.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07061

Segment What It Can Draw: Querying a Text-to-Image Generator with Its Own Images for Skin Lesion Segmentation

Hongyu Cao, Guangfu Guo, Jinghan Zhang, Dakshak Keerthi Chandra, Ying Zhang, Kunpeng Liu

原文摘要

Skin lesion segmentation without annotated masks requires the target to be specified through other cues. Existing approaches rely on dermoscopy-specific rules, annotation-derived model priors, or user-selected regions. A general text-to-image diffusion transformer offers a text interface to the target, but its concept-word attention is unreliable on dermoscopy images: in the model's attention-output space, the word-derived skin-to-lesion direction is poorly aligned with the direction separating real skin from real lesions. We show that the direction derived from generated healthy-skin and lesion images is substantially better aligned. Based on this finding, we propose GENIQ, a training-free method that constructs initial skin and lesion prototypes from generated images and refines them using the most skin-like and lesion-like patches from unlabelled dermoscopy images. It scores test patches along the refined direction and applies a gated threshold to suppress contextual spill-over around small lesions. Without inference-time annotations or additional models, GENIQ achieves Dice scores of 0.85-0.88 on three dermoscopy test sets. It outperforms zero-shot and word-based attention methods on all three sets, and a hand-designed dermoscopy pipeline in Dice and IoU on two.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.06596

Reportable Shortcuts with RLBWTs

Travis Gagie

原文摘要

Backward search over a run-length compressed Burrows-Wheeler transform (RLBWT) takes one step per pattern character, even when long stretches of the pattern match material that recurs throughout a highly repetitive collection. We describe shortcuts: for a precomputed set of pairs $(α,β)$ of strings, a backward search that has just matched $β$ and finds $α$ immediately to its left in the pattern can cross $α$ in one step. Since a shortcut is taken only after its pair has been recognized in the pattern, the search returns a report of the shortcuts it took along with the usual BWT interval. Our motivation is pangenome graphs, where such pairs mark the places where a pattern passes through a vertex, so the report gives the path a match takes through the graph. We work out the case of a single linear reference $R$, with $β$ ranging over the length-$\ell$ windows of $R$ starting at multiples of $\ell$, and $α$ over the $2^t \ell$ characters preceding such a window. We show that the search counts correctly, that under stated conditions it crosses a stretch of the pattern matching $m$ consecutive windows of $R$ with $O(\log m + m / 2^τ)$ shortcuts, where $2^τ\ell$ is the longest shortcut, and that the shortcuts can be built efficiently from the RLBWT. On the Pizza&Chili cere collection of 37 genomes, shortcuts make backward search 2.3 to 4.2 times faster on exact patterns of length 200 to 1000, and 1.7 to 2.0 times faster with 1% of the characters substituted, for 86% more space. On 11 gigabases of genomes of seven bacterial species, they make it 1.6 to 1.9 times faster on exact patterns for 32% more space. On whole chromosome 19 haplotypes against 16 to 64 others from the Human Pangenome Reference Consortium, shortcuts in both directions make Boyer-Moore-Li search for maximal exact matches of length at least 1000 about 8 times faster.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.34499

Can Statistics Tell Whether an Undeciphered Text Is Language? Calibrated Tests on the Voynich Manuscript

Xin Zhang, Victor S. Sheng

原文摘要

Statistics are often the only evidence of whether a text in an unread script records a language, but meaningless text shares many of them. A test means little until it is run on texts whose answer is known. We build such tests and apply them to the Voynich manuscript, whose text may be meaningless copying or a language hidden by a cipher. We write both accounts as programs, fit them with the same search budget and check them on held-out statistics. The copying process of Timm and Schinner predicts these statistics better than any cipher with one key, but ciphers with two keys, or that encode only the word classes of a real text, do equally well. A trace of language that needs no decipherment says more. In 28 texts in 16 natural languages the same word pairs keep sharing a line, and the manuscript shows this at half the strength of the weakest. Word codes fall to this level only with heavy miscopying or a plaintext whose word pairs recur weakly, such as abbreviated Latin. Solvers that read enciphered controls find nothing readable in the manuscript under letter ciphers, word codes or codes with one word per letter or syllable. One cipher remains, a nomenclator with two keys, which writes frequent words whole and spells the rest, and whose scribe miscopies more than half of the words. Our tests exclude it in all languages but Arabic and Hebrew. Planted messages show that a short message could still hide.

cs.CL · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07059

A hierarchy of physics-embedded neural operators for structural dynamic surrogate modelingA hierarchy of physics-embedded neural operators for structural dynamic surrogate modeling

Amir Ansrollahi, Mehmet Sefa Orak

原文摘要

Structural-response surrogates must capture moving resonances, phase changes, and unequal-amplitude transfer channels during optimization or health-state changes. Physics-embedded learning seeks FEA-level accuracy at lower cost by embedding physics in inputs, forward passes, losses, and backpropagation. We propose Modal Rational (MR), mapping structural features to modal quantities for analytical frequency-response reconstruction. The Physics-Guided Modal Operator Network (PGMON) adds bounded frequency, damping, and residual-flexibility corrections. Modal Operator with Structural GELU and Anchored-SIREN Correction (MOSAIC) denotes the bounded spectral-discrepancy framework used here; MOSAIC-MR and MOSAIC-PGMON add such discrepancies. They support finite-dimensional maps and physical decoders for future neural operators; evidence is fixed-topology, not a completed operator comparison. Two 20,000-design populations are studied: an 80 m steel truss tower with variable member areas and attached masses, and a tapered shell beam with ten variable station masses. Archived tests cover ten designs and seven acceleration histories per structure; they are benchmarks, not seismic-design assessments. With 5% reference modal damping, MR, PGMON, and MOSAIC give mean displacement-history errors of 0.73-0.76% for the tower and 0.029-0.116% for the beam, against declared band-limited modal references. Supplied modal frequencies are distinguished from design-only use; unequal parameter counts and training settings are explicit. Error analysis separates learned modal discrepancies, truncation, and excitation weighting, explaining acceleration and difficult-tower limits and risks of blind use. Results support physically structured prediction but limit claims about generalization, computational savings, and added corrections. Next is developing and validating neural operators around these architectures.

cs.CE · math-ph · physics.comp-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07055

Expanding the Quality-Coverage Frontier with Competitive Flow Matching

Wenxuan Peng, Richard Zhang, Haitian Zheng, Jaskirat Singh, Tsai-Shien Chen, Eli Shechtman, Bharath Hariharan, Hadar Averbuch-Elor 等 9 位作者

原文摘要

Flow matching (FM) generators often face a quality-coverage tradeoff. Inference-time techniques such as classifier-free guidance raise quality, but at the cost of coverage. We hypothesize this limitation stems from a basic property of the objective: an intermediate noisy image could correspond to many clean images, yet the model can only predict a single velocity, at best averaging over the multiple possibilities. To mitigate this, we introduce competition among predictions during training. We achieve this by augmenting the predictor with a randomly drawn low-dimensional conditioning code $z$. For each training example, we sample $K$ values of $z$ to produce $K$ candidate velocities that compete to explain the target, and apply the loss only to the best-matching candidate. This winner-take-all objective allows different modes to shape different predictions, rather than being averaged into a single compromise. Furthermore, this term naturally enables a new form of guidance, auxiliary conditioning scaling, which complements traditional guidance methods. Together, these two guidance mechanisms show that our method substantially improves the quality-coverage frontier. We validate on ImageNet-256, using two different testbeds, SiT and RAEv2. Given less than 3% of the original SiT pretraining compute for post-training, at the 67% Recall point, our method reduces $\mathrm{FD}_{r,6}$ from 19.22 to 5.91. On RAEv2, at the 70% Recall point, it reduces $\mathrm{FD}_{r,6}$ from 16.83 to 3.18.

cs.CV

查看论文
arXiv ↗PDF ↗