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
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 05:07 · 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 2026-11-08 05:16 — 2026-11-09 05:16（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：2026-11-09 05:07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 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 05:05（北京时间）
新论文 · v1arXiv:2610.38721

Idea Traces: Threading Accretive Content across Scientific Papers

Luke S. Snyder, Jeffrey Heer

原文摘要

We introduce idea traces, a novel thread-based representation of accretive content across scientific papers. Rather than capturing fixed themes from papers, idea traces surface similarities and deltas of faceted content that enable inspection of how ideas relate and evolve across the citation network. To extract traces, we contribute an LLM pipeline that deconstructs salient transitions between pairs of papers and collates the output into an idea dependency graph. We leverage idea traces in a visual system that supports idea-driven navigation starting from a seed paper, lifting the "plane" of synthesis from papers to ideas. To evaluate the usefulness and quality of generated ideas, we provide a case study that compares our approach with an LLM Q&A workflow, and interview 10 researchers who used our system and annotated 110 ideas. Experts found that our approach helped extract a useful space of connections that would have been difficult to make otherwise. Drawing on their feedback, we outline several promising directions for future research.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38720

inkGround: Benchmarking Fine-grained Visual Grounding Capabilities of Vision-Language Models for Cursive Handwriting in the Wild

Sidra Hanif

原文摘要

Human handwriting is produced as an ordered sequence of pen movements, but an offline image keeps only the final ink. Handwriting trajectory recovery aims to restore the ordered stroke points and their pen-up/pen-down transitions. Existing image-trajectory pair datasets are recorded with digitizing tablets under controlled conditions, which limits writer coverage and stylistic diversity. Moreover, there is no benchmark that measures the visual grounding capabilities of general-purpose Vision-Language Models (VLMs) for the stroke trajectory recovery task. In this work, we introduce inkGround, a benchmark for stroke trajectory recovery from full-page, camera-captured handwriting. inkGround pairs 537 page images (~18.7k words, ~163k strokes) with reference trajectories produced by a pretrained offline-to-online model, filtered by OCR agreement, and verified by human raters. Because these references are pseudo-labels that represent one plausible pen trajectory, we also evaluate VLMs on the IAM-OnDB dataset, which provides recorded pen trajectories. We cast the task as text-conditioned point grounding: given a page image and a target word, the model must locate the word and output its ordered stroke points. Outputs are scored by trajectory fidelity (DTW, Chamfer distance), readability of the rendered strokes (Accurate Rate, Correct Rate), and style similarity. We benchmark four open-source and three frontier closed-source VLMs with a shared in-context prompt. Closed-source models, notably Gemini-3.1-Pro, produce legible trajectories close to the reference, and this ranking also holds on IAM-OnDB.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38719

Learning Scientific Trajectories to Predict Future Biomedical Discoveries

Chia-Hsuan Chang, Brian Ondov, Jiang Lv, Lan Jiang, Yunmai Wang, Haerin Song, Xueqing Peng, Qiaozhu Mei 等 10 位作者

原文摘要

AI co-scientists have expanded the use of large language models for generating scientific hypotheses and guiding experimental investigation. Here we investigate whether temporal patterns in the semantic representations of complete biomedical conclusions can guide hypothesis generation. We introduce ForeSCITE, a framework that identifies thematic clusters of published conclusions, estimates a direction separating earlier from more recent findings within each cluster, and projects existing conclusion embeddings along these directions. An embedding language model trained to reconstruct conclusions decodes the projected coordinates into natural-language hypotheses. Across 407 clusters derived from approximately three million pre-cutoff conclusions, we identify temporal structure and illustrate its retention after decoding. In retrospective, time-sliced evaluations, ForeSCITE increases semantic coverage beyond the historical corpus, biomedical entity-pair novelty and post-cutoff pair re-observation relative to five prompt-based and retrieval-augmented baselines. Expert review of prioritized CAR-T hypotheses identified 37 candidates as both novel and biologically plausible, and expert justifications for five selected hypotheses illustrate their biological rationale and subsequent literature support where available. These findings support temporal guidance in semantic space as a scalable mechanism for proposing biomedical hypotheses for subsequent scientific evaluation.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.03462

When AI Joins the Team! A Model of How AI Adoption Relates To Social Patterns in Software Engineering Teams

Giusy Annunziata, Rudrajit Choudhuri, Anita Sarma, Gemma Catolino, Filomena Ferrucci

原文摘要

Context: The growing adoption of AI-assisted development tools is changing how software teams collaborate, share knowledge, and coordinate, yet its consequences for team social dynamics remain largely unexplored. Gap: It is unclear whether AI adoption is associated with an increase or reduction in community smells,socio-technical anti-patterns reflecting coordination and communication breakdowns,and through which mechanisms. Method: Grounded in Transactive Memory Systems (TMS) theory, we validate instruments for HumanAI and HumanHuman interaction along two TMS dimensions, Specialization and Coordination, and test five PLS-SEM models on survey data from 152 software professionals using AI tools. Community smell constructs were derived from the literature and validated through expert surveys and factor analysis. Results: AI adoption relates to community smells not in a single way, but through mechanisms depending on the work. In specialization work, AI is associated with higher knowledge-sharing peer interaction, which is in turn associated with fewer smells. In coordination work, AI is directly associated with higher communication quality, complementing rather than replacing human interaction. Contributions: We provide an empirically validated, TMS-grounded model showing that the AIcommunity-smell relationship is contingent on the type of collaboration, with a reusable instrument and evidence-based implications for research and practice.

cs.SE · cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38709

Latent Decision Flow Rewards for Clinical Guideline Reasoning

Gaurav Bhatt, Marinka Zitnik

原文摘要

Clinical practice guidelines encode evidence-based recommendations as conditional decision flows, which makes them a natural source of process supervision for training reasoning models. Two properties of clinical reasoning make this supervision difficult to use. A decision flow consistent with a guideline does not by itself determine the correct answer for a given patient, which we call the path--answer gap, and several valid decision flows can support the same clinical decision, which we call path multiplicity. Current training approaches address parts of this problem. Answer rewards supervise the final decision, and process rewards computed against a reference flow supervise one valid decision flow per case. Supervised fine-tuning on annotated flows teaches guideline-consistent reasoning but constrains the model to one trajectory per case and can reduce answer accuracy. We introduce GUIDER, a method that jointly optimizes a decision flow controller and a reasoning policy. The controller learns to generate plausible decision flows from guideline-derived supervision, and the policy learns to generate a decision flow and a final answer for each patient case. GUIDER computes the process reward for the policy over several controller-generated flows, which accounts for path multiplicity, and gates this reward on answer correctness, which addresses the path--answer gap. Joint training allows the process supervision to evolve with the policy. On MedGUIDE, GUIDER with Qwen3-14B achieves 82.5 weighted accuracy and 73.5 guideline adherence, 3.3 and 3.1 points above the strongest clinical reinforcement learning baseline. With Qwen3-14B and Gemma4-12B backbones, GUIDER also improves over CRPO, MRPO, and FaithMed on the out-of-domain benchmarks AMEGA-LLM, RealMedQA, and CancerGUIDE.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38708

Curvature-Guided Sparsification for Graphs with Community Structure

Avin Kolahdooz, Jose Jairo Garcia, Sarah Percival

原文摘要

Graph sparsification in large-scale networks often requires balancing structural accuracy and computational efficiency. Curvature-based methods, particularly Ollivier-Ricci curvature (ORC), have shown strong performance in identifying inter-community bridges, but their computational cost limits scalability. In this work, we propose a two-stage curvature-guided pipeline for graph sparsification with the goal of preserving community structure. We first use the Lower Ricci Curvature, a combinatorial lower bound of the ORC, to perform efficient edge filtering, substantially reducing graph size before applying the computationally intensive optimal-transport-based ORC curvature and Ricci flow. Results from empirical studies on synthetic and real-world datasets demonstrate that the combined LRC-ORC pipeline can achieve community-recovery accuracy comparable to ORC-only sparsification in terms of Adjusted Rand Index (ARI) and Normalized Mutual Information (NMI), while reducing runtime on most evaluated benchmarks. Our findings suggest that integrating combinatorial and geometric curvature notions provides a computationally efficient and structurally principled framework for graph sparsification in complex networks.

cs.SI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38706

cuPDQPx: A GPU-Accelerated Restarted Halpern PDHG for Large-Scale Convex Quadratic Programming

Haihao Lu, Zedong Peng, Jinwen Yang

原文摘要

We present cuPDQPx, a GPU-accelerated, factorization-free first-order solver for large-scale convex quadratic programming (QP). Building on the restarted reflected Halpern primal-dual framework of cuPDLPx, we introduce an auxiliary-variable splitting that yields explicit updates without linearizing the quadratic objective or solving inner quadratic subproblems. A preconditioned proximal point interpretation yields both sublinear and linear fixed-point residual convergence guarantees. For practical efficiency, cuPDQPx integrates diagonal preconditioning, step-size selection, adaptive restart, and adaptive primal and quadratic weight updates. cuPDQPx is implemented in C and CUDA with optimized sparse matrix-vector products, kernel fusion, and CUDA Graphs. Numerical experiments on the Maros-Mészáros collection, a convex subset of QPLIB, and synthetic large-scale QPs demonstrate that cuPDQPx has strong numerical performance at both $10^{-4}$ and $10^{-8}$ tolerances.

math.OC · cs.MS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.07083

Graph-Based Recognition of Simulated Train-Driver States From Facial and Upper-Body Keypoints

Olivia Nocentini, Marta Lagomarsino, Gokhan Solak, Younggeol Cho, Qiyi Tong, Sara Zeynalpour, Marta Lorenzini, Alessandro Ledda 等 9 位作者

原文摘要

Driver fatigue poses a significant challenge to railway safety, with traditional systems like the dead-man switch offering limited and basic alertness checks. This study presents a vision-based monitoring system that relies solely on a single front-facing RGB camera and a graph neural network to classify simulated train-driver states into alert, not-alert, and an emergency class comprising acted emergency-like behaviours. To optimize input representations for the model, an ablation study was performed, comparing three feature configurations: skeletal-only, facial-only, and a combination of both. Experimental results show that combining facial and skeletal features yields the highest accuracy (81%) for the three-class model under the light condition, outperforming models that use only facial or skeletal features. Furthermore, the combination of facial and skeletal features achieves 99% accuracy in the alert/not alert classification in light condition. Additionally, we introduced a controlled RGB video dataset containing alert, not alert, and acted emergency-like behaviours recorded under three illumination conditions. These contributions represent a step toward passive and non-contact train-driver state recognition based on facial and upper-body dynamics.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.18635

Deterministic Streaming Lower Bounds for Approximate Maximum Clique and Maximum Independent Set

Adithya Diddapur

原文摘要

We study the canonical \textsf{Maximum Clique} and \textsf{Maximum Independent Set} problems in the one-pass edge-arrival graph streaming setting. Here, the edges of some input graph $G = (V,E)$ are presented one at a time (possibly including deletions), before an algorithm needs to produce either a large clique or independent set at the end of the stream, with the focus being on space complexity. We are interested in finding $β$-approximate solutions, for any $β\geq 1$. Previous work gave an algorithm using $\tilde{O}\left(n^2/β^2\right)$ bits of space, together with a corresponding $\tildeΩ\left(n^2/β^2\right)$ two-party communication lower bound [Halldórsson et al., ICALP'12], seeming to resolve the problem. However, their algorithm crucially relies on randomness, and the best known deterministic algorithm remains a folklore derandomisation using $O\left(n^2/β\right)$ bits of space, leaving a (deterministic) gap of size $\tilde{O}(β)$. We make progress towards this gap with a strong lower bound for a restricted range of $β$: whenever $β\leq \sqrt{n}/36\log n$, any deterministic algorithm for either problem must use $Ω\left(\frac{n^2}{β\cdot\log n}\right)$ bits of space. Our proof is via a two-party one-way communication lower bound, and highlights the power of randomness when approaching either of these problems.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2601.01236

The asymptotic size of finite irreducible semigroups of rational matrices

Stefan Kiefer, Andrew Ryzhikov

原文摘要

In this paper we investigate the maximum size of finite semigroups of rational $n \times n$ matrices, with the goal of shedding more light on their structure. Such semigroups provide a rich generalisation of transition monoids of unambiguous (and, in particular, deterministic) finite automata. While in general such semigroups can be arbitrarily large in terms of $n$, a classical result of Schützenberger from 1962 implies an upper bound of $2^{O(n^2 \log n)}$ for irreducible semigroups. A semigroup of rational matrices is called irreducible if the only subspaces of $\mathbb{Q}^n$ that are invariant for all matrices in the semigroup are $\mathbb{Q}^n$ and the subspace consisting only of the zero vector. Irreducible matrix semigroups can be viewed as the building blocks of general matrix semigroups, and as such play an important role in mathematics and computer science. From the point of view of automata theory, they can be seen as a generalisation of strongly connected weighted automata. Using a very different technique from that of Schützenberger, we improve the upper bound on the cardinality to $3^{n^2}$. This is the main result of the paper. The bound is in some sense tight, as we show that there exists, for every $n$, a finite irreducible semigroup with $3^{\lfloor n^2/4 \rfloor}$ rational matrices. Our main result also leads to an improvement of a bound, due to Almeida and Steinberg, on the mortality threshold of finite semigroups of rational matrices. The mortality threshold is a number $\ell$ such that if the zero matrix is in the semigroup, then the zero matrix can be written as a product of at most $\ell$ matrices from any subset that generates the semigroup.

cs.FL · math.GR · math.RA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.30888

Breaking the Infinite Barrier in the $\frac{1}{3}$--$\frac{2}{3}$ Conjecture

Max Aires, Swee Hong Chan, Igor Pak, Greta Panova

原文摘要

The balance constant is a poset parameter measuring how well random linear extensions can be split according to their relative order on two elements. We give an $\varepsilon$-improvement for the balance constant over the bound by Brightwell, Felsner and Trotter (1995), for some small $\varepsilon>0$. This is the first general result towards the $\frac{1}{3}$--$\frac{2}{3}$ conjecture in over 30 years.

math.CO · cs.DM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38697

SatOps-Decision: Low-Latency Discriminative Decisions for Onboard Satellite Communication Operations

Lifan Mei, Yuxuan Li, Jiaxian Tu, Shenghe Xu

原文摘要

We propose SatOps-Decision, a method for low-latency decisions in satellite communication operations. To the best of our knowledge, it is the first application of Jev-style general-purpose discriminative decision models to satellite operations, and the accompanying benchmark is the first dedicated to this approach. The learned scorer, a locally adapted Laya encoder with its native decision head, selects among supplied operational answers in a single forward pass. The benchmark combines authored operational contracts, controlled state changes and independently checked labels in an auditable construction. Evaluation prioritizes complete-request latency and raw decision accuracy; all main accuracy comparisons use the same 1,024 held-out questions, separate from training and development. SatOps-Decision's local scorer has a median latency of 90.3 ms per decision, versus 493.9 ms for Qwen3.5-0.8B generation and 388.4 ms for OneJev1.6-0.8B: $5.47\times$ and $4.30\times$ speedups based on median request times in the measured FP32/MPS implementations. Its mean raw accuracy is 85.3%, versus 42.5% for frozen Laya, 40.7% for Qwen generation and 58.6% for OneJev. As cloud accuracy references, original Jev 1.14/1.13 reach 87.4/81.9%.

cs.LG · cs.AI · cs.NI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.15528

Inter-Satellite Link Optimization for Low-Latency Global Networking

Arman Mollakhani, Jerayu Tiamraj, Shu-Jie Cao, Dongning Guo

原文摘要

Large-scale low-Earth-orbit satellite constellations offer a promising platform for global low-latency networking, in part because signals propagate faster in free space than in fiber and copper. In such systems, end-to-end latency is largely determined by the inter-satellite link (ISL) topology. In particular, the network diameter--the longest shortest path, in hops, between any pair of satellites--serves as a key performance metric for time-sensitive applications. Designing diameter-optimal topologies is challenging due to node degree constraints, orbital dynamics, and the combinatorial nature of link selection. This paper proposes a two-stage optimization framework for ISL topology design. First, a continuous relaxation of the link-selection problem is formulated as a convex program that maximizes the algebraic connectivity of the graph Laplacian, serving as a tractable surrogate for diameter minimization. Second, the resulting fractional solution is mapped to a feasible topology via maximum-weight b-matching, a problem solvable in polynomial time. Simulations on Walker-Delta constellations show that the proposed method consistently achieves smaller network diameters than a local-search baseline and standard patterned topologies. For a 1,584-satellite constellation in which each satellite has four ISLs of up to 2,500 km, the diameter is as small as 12 hops, and the maximum propagation delay between any two satellites is about 90 ms. With up- and downlinks adding up to 8 ms, the user-to-user propagation delay is at most about 98 ms, comparable to the delay over a great-circle fiber route between antipodal points on Earth.

cs.NI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.17155

Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization

Yicheng Lang, Changsheng Wang, Yihua Zhang, Mingyi Hong, Zheng Zhang, Wotao Yin, Sijia Liu

原文摘要

Zeroth-order (ZO) optimization provides a gradient-free alternative to first-order (FO) methods by estimating gradients via finite differences of function evaluations, and has recently emerged as a memory-efficient paradigm for fine-tuning large-scale models by avoiding backpropagation. However, ZO optimization has a fundamental tension between accuracy and query efficiency. In this work, we show that ZO optimization can be substantially improved by unifying two complementary principles: (i) a projection-based subspace view that reduces gradient estimation variance by exploiting the intrinsic low-rank structure of model updates, and (ii) Muon-style spectral optimization that applies gradient orthogonalization to extract informative spectral structure from noisy ZO gradients. These findings form a unified framework of subspace gradient orthogonalization, which we instantiate in a new method, ZO-Muon, admitting a natural interpretation as a low-rank Muon optimizer in the ZO setting. Extensive experiments on large language models (LLMs) and vision transformers (ViTs) demonstrate that ZO-Muon significantly accelerates convergence and achieves a win-win improvement in accuracy and query/runtime efficiency. Notably, compared to the popular MeZO baseline, ZO-Muon requires only 24.7% of the queries to reach the same SST-2 performance for LLM fine-tuning, and improves accuracy by 25.1% on ViT-L fine-tuning on CIFAR-100.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2410.09512

Indirect Optimal Control for Constructing Libraries of Periodic Trajectories: Application to Bipedal Walking

Maximilian Raff, Kathrin Flaßkamp, C. David Remy

原文摘要

Trajectory optimization is a fundamental tool for generating efficient, dynamically consistent periodic motions, commonly referred to as gaits, in legged locomotion. This paper explores the indirect method of periodic trajectory optimization, emphasizing its application in creating optimal gaits for legged systems and contrasting it with the more common direct method. While the direct method offers implementation flexibility, it is limited by its need for an input space parameterization. In contrast, the indirect method achieves higher accuracy by computing the control input from states and costates along the optimal trajectory. In this work, we tackle the convergence challenges associated with indirect shooting methods by utilizing numerical continuation methods. This is particularly useful for the systematic development of gait libraries. Our contributions include: (1) the formalization of a general periodic trajectory optimization problem that extends existing first-order necessary conditions to a broader range of cost functions and operating conditions; (2) a methodology for efficiently generating optimal gait libraries using single shooting and numerical continuation; (3) a novel approach for reconstructing Lagrange multipliers and costates from passive gaits; (4) a comparative analysis of the indirect and direct shooting methods using a compass-gait walker as a case study, demonstrating the higher accuracy of the indirect method; and (5) demonstrating applicability to the more complex legged robot RABBIT, with ten dynamic states and four inputs. These results establish a systematic indirect optimal control framework for synthesizing families of optimal periodic trajectories in legged locomotion.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38694

Geometry Matters in Packed 3D Attention

Amil Khan, Anantajit Subrahmanya, B. S. Manjunath

原文摘要

Packing a 3D volume into a token sequence is not merely long-sequence modeling. Once the volume is packed, sequence order no longer encodes the geometry of the sample---so a positional mechanism indexed by sequence position can learn the memory layout rather than the object. This is a general failure mode for attention over packed geometric data. We introduce PACK3D, a local-global attention operator that separates memory layout from attention geometry. PACK3D keeps local neighborhood attention exact, compresses only distant context into contiguous 3D block summaries, and indexes every query-key interaction with axial RoPE on true token-grid coordinates rather than packed positions. Because the rotation is applied before a block is summarized, the query-to-summary logit remains a weighted sum of query-relative 3D displacements; compressed global context therefore stays spatially interpretable after packing, instead of collapsing to anonymous pooled content. We measure the failure mode directly. On a controlled synthetic task---train on one packing, change only the memory order of the tokens, hold the physical labeling rule fixed---learned positional embeddings and packed-sequence RoPE solve the training layout perfectly yet collapse under Morton, block-contiguous, and random repacking, while axial grid-coordinate RoPE stays exact throughout. The same coordinate system carries to real data: on Allen WTC-11 hiPSC microscopy, PACK3D improves over a parameter-matched 3D U-Net on the 15-structure joint task and over a matched learned-position local-global baseline, with controls isolating the coordinate system, not encoder capacity, as the source of the gain. A fused Triton implementation matches windowed-attention latency at 65k tokens while supplying the long-range context windowing cannot---so the operator is not only correct but trainable at scale.

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2608.02673

dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model

Hankun Wang, Bohan Li, Shi Lian, Xiaoyu Gu, Jing Peng, Da Zheng, Yiwei Guo, Colin Zhang 等 10 位作者

原文摘要

Speech editing for content creation requires precise control over both what an edit should do and where it should apply. Free-form natural language provides a flexible interface for expressing edit requests, but its ambiguity may leave the intended operation, parameters, or target region underspecified. We study a semi-formal transcript-grounded edit instruction that specifies operation categories and parameters and binds them to transcript spans or boundaries. This semantic timeline avoids explicit timestamp alignment and provides an externally inspectable contract for compositional edits. We instantiate the interface in dots$.$tts$.$edit, a speech editing model built on a continuous autoregressive speech generation architecture. Four representative speech-creation controls cover lexical content, affective expression, pitch and speaking-rate delivery, and temporal phrasing through text, emotion, prosody, and pause editing. Task-specific data pipelines construct operation- and scope-controlled pairs while retaining source-derived context outside each target region. We further introduce doteBench, a bilingual benchmark that measures precise instruction following, local preservation, and audio quality across the four controls and their composition. Experiments show leading overall instruction following and local preservation across its five editing categories, while audio quality remains comparable to existing open-source systems. Across three Seed-TTS-Eval shards, the model shows negligible differences from the base model in zero-shot TTS recognition error rate and speaker similarity.

cs.SD · cs.AI · cs.CL · eess.AS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38686

On the Generalization Gap of Streaming Federated Learning with Markovian Data

Masoud Kavian, Milad Sefidgaran, Youssef Attia El Hili, Malik Tiomoko, Abdellatif Zaidi

原文摘要

Streaming federated learning (SFL) allows clients to train a shared model from continuously arriving data without retaining large local datasets. Such streams often exhibit temporal dependence, yet its effect on generalization remains poorly understood. In this paper we study the expected generalization gap of the aggregated model when client data follow Markov processes, using information-theoretic and rate-distortion techniques. Our framework accommodates heterogeneous Markovian dynamics across clients and distinguishes temporal dependence from information acquired during local learning. We establish bounds under cross-entropy loss, specializing them to Linear Next-Token Prediction (LNTP) and Self-Attention Next-Token Prediction (SANTP). These results quantify the effects of client count, communication rounds, sample size, data dimension, mixing time, and context length. In particular, they reveal a communication--generalization tradeoff: although frequent aggregation may help optimization, it can weaken generalization guarantees. They also suggest a potential advantage of distributed over centralized streaming learning under a fixed total data budget. Temporal dependence enters through the square root of the mixing time. By analyzing the history-state process, we obtain refined bounds with improved context-length dependence under suitable mixing conditions. Experiments on GPT-style language-model pretraining with TinyStories and real-world time-series forecasting illustrate how collaboration and communication frequency influence generalization under temporal dependence

cs.LG · cs.IT · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38687

Deogen: Automatic Benchmark Generation for Reasoning over Policies

Sam Kouteili, William Liang, Keeran Murray, Adriana Zhou, Ramesh Viswanathan, Scott Shapiro, Ruzica Piskac

原文摘要

Language models are increasingly being deployed in regulated settings, where a model must apply given rules to the facts of a situation to determine a verdict. Benchmarking this capability, known as deontic reasoning, remains a costly and manual process, with existing datasets largely hand-crafted. In this paper, we present DeoGen, a scalable, automatic, and parametrizable benchmark generator for deontic reasoning. By autoformalizing policy rules to first-order logic, we can construct decision trees that capture possible outcome trajectories. Each path down a tree becomes a benchmark entry, with each tree producing combinatorially many entries relative to tree depth. Paths ending at a leaf entail a verdict, while non-leaf paths measure a model's ability to abstain when presented with insufficient information. Evaluations show frontier models return the correct verdict 89-92% of the time. Notably, performance degrades (22-40% correct) on entries without sufficient information to claim a verdict, even with explicit instructions to abstain in such cases. In all, DeoGen presents an automatic, scalable, and parametric method for generating deontic reasoning benchmarks.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38683

Quantum-Inspired Pairwise Ranking Aggregation via Active LLM Feedback

Quan Mai, Susan Gauch, Gibson Nkhata

原文摘要

Ranking aggregation from multiple retrievers is a powerful yet under-explored technique in modern retrieval and RAG systems. We introduce LLM-IRA, the first extension of the quantum-inspired interactive ranking aggregation framework to document reranking. By leveraging large language models (LLMs) solely for pairwise judgments on high-disagreement document pairs, our method learns fusion weights in a principled, interactive way. The final ranking is a simple, ultra-fast pointwise linear fusion of scores, no full pairwise matrix or expensive listwise prompting is required. Experiments on the BEIR benchmark and TREC Deep Learning tracks with an open-weight instruction-tuned judge (Llama-3.1-8B-Instruct) show that LLM-IRA matches or numerically exceeds strong static fusion baselines on 5 of 6 evaluated benchmarks. We report two weight-update variants: momentum blending and a full accumulated-history refit, which together reach statistical significance (Wilcoxon signed-rank, p<0.05) over the best unsupervised aggregator on 4 of 6 benchmarks (DL19 under momentum; DL20, DBpedia, and NFCorpus under accumulated refit, which is the stronger of the two configurations overall). On the benchmarks we profiled (DL19, DL20), it already clears the best unsupervised baseline within as few as 5 LLM calls per query, well before exhausting its typical ~25--30 call budget. LLM-IRA also achieves cost-effectiveness comparable to state-of-the-art zero-shot LLM rerankers at an order of magnitude fewer LLM calls, and requires no training data or model fine-tuning.

cs.IR · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38682

Write Once, Instrument Anywhere: Portable, Sandboxed Tooling with WebAssembly Components

Elizabeth Gilbert, Chris Fallin, Heather Miller, Ben L. Titzer

原文摘要

Monitoring and debugging deployed software is crucial for scalability, performance, and robustness. Cross-cutting concerns are pervasive across software ecosystems, yet engineers must address them with a fragmented toolbox. While high-level frameworks exist to offer application-level types and semantics, they often lock a solution into specific languages, runtimes, or hardware architectures. Portability often forces engineers to choose lower-level instrumentation mechanisms. For example, in-language frameworks can trace a request across processes, but multi-language contexts require instrumentation at the boundary, for example using eBPF. While these frameworks provide powerful capabilities, they often result in 1) a tradeoff between application-level types or low-level bytes and packets, 2) non-composable domain-specific tools, 3) feature fragmentation across frameworks, and 4) tools that often run with unrestricted access to the program and its environment. We address these problems with Splicer, a WebAssembly component interposition framework that 1) provides semantically rich application-level types, 2) enables pluggable tooling with powerful capabilities, 3) reduces ecosystem fragmentation through porting across languages and hardware, and 4) confines each tool to a sandbox with explicitly granted permissions. We evaluate Splicer on a suite of benchmarks demonstrating the pluggability of non-trivial tooling written in multiple source languages and their performance.

cs.SE · cs.PL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38681HF 社区推荐

Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models

Yecheng Wu, Song Han, Han Cai

原文摘要

Self-distillation offers a way to improve reasoning models when a suitable external teacher is unavailable. However, common approaches rely on privileged information to construct a stronger self-teacher, limiting their use when only unlabeled prompts are available. In this paper, we introduce Weakening-Induced On-Policy Self-Distillation (WISD), which instead constructs a weaker counterpart of the original model and uses the contrast between the two as a training signal without requiring privileged information. We explore two ways to construct the weaker model: low-bit quantization and magnitude pruning. We evaluate WISD across diverse architectures and scales on mathematical and coding reasoning tasks. Across these benchmarks, quantization and pruning improve average accuracy over the original models by 4.0 and 5.5 percentage points, respectively, achieving state-of-the-art performance even without privileged information. Notably, pruning raises Qwen3.5-4B's accuracy from 57.7% to 70.5% on HMMT 2025 and from 39.1% to 56.7% on LiveCodeBench v6. Quantization raises Qwen3.6-35B-A3B's accuracy from 68.5% to 74.6% and from 61.8% to 69.5% on the same benchmarks, respectively. These results establish WISD as a novel and effective self-distillation framework for large reasoning models.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38678HF 社区推荐

AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding

Lu Wang, Zhuoran Jin, Longxiang Wang, Junhong Chen, Yupu Hao, Yao Xu, Daojian Zeng, Yubo Chen 等 11 位作者

原文摘要

Recent advances in multimodal large language models have increased interest in interaction paradigms for video understanding. The evolution from offline to streaming and proactive interaction has gradually shifted models from passive responders toward more proactive agents that can decide when to answer. However, existing proactive paradigms typically assume that the information required to answer a query is complete, leaving models to only wait or answer. In the real world, however, information is often incomplete due to uncertainty from either the video or the user. In proactive paradigms, such uncertainty can cause the model to wait forever or generate highly hallucinatory responses. We therefore argue that proactive interaction should be redefined with a third action: ask, allowing models to actively ask for missing information. To study when and what models should ask before answering, we introduce AskStream, the first multi-turn benchmark spanning video and user uncertainty for streaming video understanding, with four task categories and eight subtasks. It contains 438 videos with 2,714 manually annotated frame-level time windows across three types: wait, ask, and answer. Across both multiple-choice and open-ended settings, even the strongest model attains only 52.18% on our proposed Ask-F1 metric, highlighting substantial limitations in proactive information seeking under uncertainty.

cs.CV · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.17989

Whom Do AI Agents Serve? Role-Induced Sponsorship Bias in Decision Models and Generative LLMs

Davood Wadi, Yu Ma

原文摘要

Consumers increasingly delegate product search to AI shopping agents powered either by generative large language models (LLMs) that deliberate in natural language or by non-generative decision models that output calibrated choice probabilities in a single forward pass. Because retail platforms monetize through sponsored placements that shoppers typically discount, we examine whether an AI agent's evaluation of paid listings depends on who delegates the agent across both model families. Across three studies with no instructions to favor advertisers, naming a booking platform (vs. a traveler) as the agent's principal significantly attenuates the penalty applied to sponsored listings. Study 1 establishes this sponsorship bias across generative LLMs, prompt wordings, and reasoning efforts, showing that platform delegation weakens pre-choice skepticism and that naming the consumer as the beneficiary eliminates the bias. Study 2 establishes the bias across six commercial and open-weight decision models on calibrated choice probabilities and shows that consumer-aligned fine-tuning of an open-weight decision model (Kev 9B) across non-hotel retail categories eliminates the bias zero-shot on hotel choices. Study 3 decomposes the disclosure label across both model families, showing that attributing the placement to the platform triggers the sponsorship bias, whereas stricter disclosure wording ("Sponsored" vs. "Promoted") lowers paid-listing evaluation without eliminating this bias.

econ.GN · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38667

ExplainCC: Explaining Correlated Clusters by Node Labels

Nadeesha Shyami Kumari Herath Mudiyanselage, Florian Adriaens, Nikolaj Tatti

原文摘要

An increasingly important requirement for clustering algorithms is that decisions and outcomes need to be clearly understandable for human users. We address this requirement for the Correlation Clustering (CC) problem, in case the objects to be clustered are accompanied by labels. In CC one seeks to partition a set of objects into clusters based on pairwise similarity and dissimilarity information. Our proposed model only considers clusters that can be explained by a label tree, which is essentially a decision tree that partitions the objects according to labels. The goal is to find an explainable partition of the data that minimizes the CC objective function. We formalize this problem from a theoretical viewpoint, and prove several hardness of approximation results, also when constraining the size of the tree. Our proposed greedy method finds locally optimal splits, and works recursively in a top-down approach. To efficiently compute the best split, we carefully maintain certain counters. An experimental evaluation demonstrates its effectiveness. The proposed algorithm processes graphs with over million edges in a few minutes, can find the ground truth in synthetic data, and is able to produce interpretable clusters in real world networks.

cs.LG · cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38664

Upper Bounds for CSP Non-redundancy via Locally Decodable Codes

Joshua Brakensiek, David Conlon, Venkatesan Guruswami, Xiaoyu He, Jiaxi Nie, Maya Sankar, Hung-Hsun Hans Yu

原文摘要

In the study of constraint satisfaction problems (CSPs), the non-redundancy of a relation measures the maximum number of clauses in a CSP instance which can be logically independent. In the last few years, CSP non-redundancy has found a number of applications including in query complexity, sparsification, kernelization and streaming. In this paper, we present a novel technique for upper-bounding the non-redundancy of some relations using locally decodable codes (LDCs) and locally correctable codes (LCCs). More precisely, known limitations on the structure of 2-query LDCs and LCCs can be translated into limitations on the size of certain non-redundant CSP instances. This technique builds on a technique used by Brakensiek and Guruswami [STOC 2025] to bound non-redundancy via techniques from matching vector codes. Using LDCs and LCCs, we give improved upper bounds on non-redundancy of the BCK predicate pioneered by Bessiere, Carbonnel, and Katsirelos [AAAI 2020] as well as its well-studied Boolean variant. We also give the first example of a Boolean predicate whose non-redundancy is provably not of the form $n^{k\pm o(1)}$ for some positive integer $k$.

cs.DM · cs.CC · cs.IT · math.CO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.32782

Learning response-aware patient dynamics for respiratory support

Xiaolei Lu, Shamim Nemati

原文摘要

Respiratory support can shape the short-term physiological trajectory of critically ill patients, but patients receiving the same intervention may follow different physiological trajectories. Clinical patient dynamics models typically predict future states from recent physiology and recorded interventions, while physiological change is mainly represented through the predicted future state. We propose a response-aware patient dynamics model that explicitly represents physiological change during autoregressive state updating. The model decomposes predicted physiological change into state-dependent baseline dynamics and respiratory-support-associated deviations, with room air providing a reference for the decomposition. We provide a formal analysis of this reference-anchored formulation. A response pathway encodes the predicted physiological change and uses it to update the latent patient state across the forecast horizon. Across ICU cohorts from two independent institutions, the proposed model achieves comparable overall trajectory prediction to patient dynamics baselines, with more consistent improvements when physiological states are changing.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38661

Quantize by Doing: Task-Guided Mixed-Precision Quantization of Vision-Language-Action Models

Jiuyi Xu, Xiao Hu, Meida Chen, Song Wang, Yang Ye, Yangming Shi

原文摘要

Post-training quantization (PTQ) reduces the memory footprint of vision-language-action (VLA) models, but lowering bit widths while maintaining task performance remains challenging. Existing work has used sensitivity estimates from calibration data to assign bit widths to different model components. However, using task success directly to guide mixed-precision allocation is underexplored because closed-loop evaluations are costly and the effect of quantizing one component depends on the precision of other components. To this end, we propose \textbf{QbD-VLA}, a task-guided mixed-precision quantization method that uses task success from short closed-loop evaluations to assign weight and activation bit widths while accounting for interactions between model components. Experiments covering four VLA models and all four LIBERO suites show strong task performance at average precisions of approximately 4 bits for weights and fewer than 6 bits for activations. On SIMPLER, the gain over uniform quantization is small. On a Franka Research 3 robot arm, simulation-selected allocations show no detected success-rate loss on X-VLA but fail on $π_{0.5}$. These findings support using task success to guide mixed-precision VLA quantization, while highlighting the need for real-world evaluation before deployment. Code is available at \href{https://github.com/jiuyixu25/QbD-VLA}{\texttt{github.com/jiuyixu25/QbD-VLA}}.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.10323

Semantic Multi-Agent Intrusion Detection for IoT:Zero-Day and Adversarial Threats with Risk-Aware Reasoning

Saeid Jamshidi

原文摘要

The rapid proliferation of Internet of Things (IoT) devices has enabled unprecedented automation and connectivity, but it has also substantially increased the attack surface, exposing networks to sophisticated cyber threats, including zero-day and adversarial intrusions. Traditional Intrusion Detection Systems (IDS) struggle to generalize to unseen attacks, often require substantial computational resources, and lack interpretability, particularly in resource-constrained and heterogeneous IoT networks. Recent advances, including Deep Learning (DL), open-set detection, and Large Language Model (LLM)-based semantic reasoning, address some of these challenges but typically focus on zero-day and adversarial threats and rarely combine semantic reasoning with multi-agent systems. To overcome these limitations, we propose a semantic multi-agent ID that integrates four specialized agents (e.g., Scout, Mutator, Auditor, and Arbiter) that leverage semantic embeddings and multi-stage probabilistic decision fusion. The Scout induces structured hypotheses from semantic embeddings; the Mutator generates adversarially constrained variants; the Auditor evaluates consistency and filters unreliable outputs; and the Arbiter produces interpretable, risk-aware alerts. Extensive experiments across multiple real-world IoT datasets demonstrate that the proposed system achieves 95.9% overall detection accuracy, reduces false-positive rates to 6.8%, improves zero-day detection to 87.9%, and maintains computational efficiency suitable for edge deployment.

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.37584

REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation

Yuxi Huang, Silin Zhou, Chenhao Wang, Zihan Li, Gangming Guo, Pei Ke, Shen Gao, Shuo Shang

原文摘要

Personalized recommendation depends on learning semantic and collaborative relations among items from online content and user interactions. Generative recommendation (GR) offers a promising paradigm by autoregressively generating discrete semantic IDs (SIDs) of items. However, randomly initialized SID token embeddings and GR models trained from scratch do not directly inherit the semantic relations inherent in items, while inter-item collaborative relations are learned largely implicitly through token-level attention and next-token supervision. To address this limitation, we propose REGER, a unified framework that explicitly incorporates inter-item relations into semantic pretraining, history encoding, and SID generation. We pretrain the GR model through generative semantic retrieval, enabling it to inherit inter-item semantic similarity by learning to generate semantic neighbors' SIDs. We combine global attention with local attention aligned with SID boundaries to capture historical context and directed transitions between adjacent items. We further develop a theoretical framework for hierarchical preference decomposition over the SID prefix tree, proving an exact factorization of collaborative preference distributions and a weighted decomposition of item-level KL divergence into prefix-conditional KL divergences. Building on this analysis, we distill a discriminative teacher's full conditional distributions over all legal next tokens at ground-truth prefixes along the target SID path, jointly optimizing this objective with cross-entropy. Extensive experiments on real-world datasets demonstrate consistent improvements over existing GR baselines and support the effectiveness of the proposed preference distillation.

cs.IR · cs.AI

查看论文
arXiv ↗PDF ↗