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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-10 01:54 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 02:35 — 2026-11-10 02:35（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：2026-11-10 01:54最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 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 18,172 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 01:52（北京时间）
新论文 · v1arXiv:2610.34711

Intervene, Calibrate, Discover: Learning Causal Structure from Pixels

Ziyi Ding, Xiaodi Huang, Xianxin Lai, Haijier Chen, Zhang Zhang, Xiao-Ping Zhang, Jiayu Chen

原文摘要

Learning high-level causal variables from low-level observations is a central problem for artificial intelligence. With known node semantics but an unknown graph, visual readout errors can misalign model settings with environment intervention values. We address this mismatch by pairing image readouts with verified values attained through fixed round-robin interventions. With encoder and decoder frozen, a dimension-wise invertible calibration map puts visual responses and target settings in shared numerical units. After freezing this map, the agent selects interventions to resolve graph directions and fits local mechanisms to predict consequences; inverse calibration returns counterfactual states to the decoder's original coordinates. Across Domino, Pick-and-Place, Balance, Gears, CAUSAL3D, and CausalWorld, we evaluate graph discovery, intervention consequences, and counterfactual images. Controlled domino experiments show that interventions resolve orientation ambiguity left by equal additional observations. In a matched-data domino control, calibration reduces the mean error of predicted changes in other variables within the same factual context, relative to an uncalibrated model.

cs.AI · stat.AP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34709

Sparse Reconstruction by Direct Measurement-to-Field Generation in Function Space

Linzheng Wang, Jason Chen, Nicolas Tricard, Zituo Chen, Xingsen Guo, Sili Deng

原文摘要

Understanding physical systems often requires recovering their full spatial state from measurements available only at sparse locations. This reconstruction becomes challenging when physical boundaries are unknown, high-resolution training fields are unavailable, or important quantities cannot be measured directly. Sparse observations may also be consistent with multiple plausible states, leading to significant reconstruction uncertainty. Here we introduce Direct Measurement-to-Field Generation (\DMF{}), a functional rectified flow framework that learns how sparse measurements drive physical-field generation end to end. Instead of relying on grid-based rasterization or runtime guidance, \DMF{} jointly learns a sensor--global--sensor representation with the generative transport, dynamically fusing local grounding with global context to evaluate physical fields at arbitrary query coordinates. Across benchmarks involving unobserved boundaries, missing high-resolution training fields, and unmeasured physical quantities, \DMF{} outperforms alternative baselines by significantly reducing reconstruction errors and preserving the fidelity of physical properties. Furthermore, its stochastic ensemble generation reliably quantifies uncertainty while improving continuous ranked probability scores. These results extend sparse reconstruction from fixed-setting point estimation toward measurement-conditioned generation of physical fields under incomplete and changing information.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.23438

No Eyes, No Problem: What Does Touch Contribute to Blind Baoding Ball Manipulation?

Ayush Deshmukh, Nalin Agarwal, Elle Miller, Sethu Vijayakumar

原文摘要

Humans manipulate objects within their hands through touch alone with remarkable ease, but for robots, achieving sustained real-world manipulation without vision remains an open challenge. Although reinforcement learning (RL) can generate sophisticated blind manipulation policies in simulation, transferring them to a real dexterous hand remains hindered by continuously changing contacts, motion-induced tactile information drift, and the gap between simulated and physical dynamics. We study this problem through Baoding ball rotation on the Shadow Dexterous Hand Lite, using only proprioception and binary tactile feedback as observations. We achieve successful zero-shot transfer through a combination of a sensor-aligned, coupling-aware embodiment in simulation, tactile calibration, and two novel episodic domain randomisations: slew-rate action limits and STuck-AT Taxels. On the physical hand, the policy achieves sustained blind Baoding rotation, completing $\textbf{225 consecutive $\mathbf{180^\circ}$ rotations (112.5 full rotations) at $\sim0.36 \;\text{rot/s}$}$ in a single continuous trial without any vision or object-state information. Furthermore, we evaluate the contribution of tactile sensing relative to proprioception alone and identify the hand regions where tactile information is most important. This is the strongest reported hardware result for Baoding ball manipulation in both rotation count and speed, irrespective of the sensing modality used. By effectively bridging the sim-to-real gap, our framework sets a new benchmark for sustained tactile-driven dexterous manipulation on physical hardware.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2608.00583

A False Average: Pooled CoT-Monitor Accuracy Conceals a Reasoning-Dependent Fragility

Shikhar Shiromani, Leo Richter, Noah Siegel

原文摘要

Chain-of-thought (CoT) monitors are reported by their aggregate accuracy on a pool of reward hacks. We show that this number is a false average. On Terminal Wrench, about 77% of hacks are given away by the actions alone, and the monitor's pooled accuracy is dominated by them; on the remaining 23%, which an action-only monitor misses, the same monitor is fragile. We expose the fragility with a controlled attack: we rewrite only the agent's reasoning to read as good-faith engineering, leaving every command and output byte-identical. One gradient-free rewrite drops a held-out monitor's catch rate on that subset from about 95% to between 4 and 11%, while the pooled rate falls only about 25 points, near what the subset's share of the pool times its collapse predicts. The rewrite stays truthful about what happened and lies only about intent, so the trace-only monitors we test recover little, even when warned about the attack; of our defenses, only information from outside the trace helps much. The attack transfers across monitor and agent families, and the dataset's own hack labels show the same gradient with no monitor in the definition. Live agents told to hack on 27 tasks, with no monitor feedback, produce hollow hacks, but a monitor calibrated on each model's own honest solves catches nearly all of them. Applying the same rewrite to these live hacks keeps all 111 action-visible ones caught and lowers catch on the 16 whose actions score below 0.5 only from 16 to 13: the effect lands where the false average predicts, but the collapse stays a controlled result. A linear probe on a surrogate monitor's activations out-reads its verdict on the obfuscated hacks (AUC up to 0.98), but a behavioral control shows this edge does not, by itself, mean the monitor knows more than it says. Monitor accuracy should be reported on the reasoning-dependent subset, where the defense is load-bearing.

cs.CR · cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34708

Resource-Performance Trade-offs in Intra-Aisle Robotic Picking: A Discrete-Event Simulation Comparison of Shuttle Configurations With and Without an Onboard Tote Lift

Mohsen Reda Mahmoud Moursi

原文摘要

This study compares two implemented intra-aisle robotic-picking configurations through discrete-event simulation. Without an onboard tote lift, two level-captive shuttles serve the two tested levels; with the lift, one shuttle remains on its horizontal level and its onboard mechanism moves the order tote to allow picks from the adjacent upper level. Thirty configuration-task-size experiments (n = 1-15 locations; ten replications each) yield 300 replication-level cycle-time observations. Two-sided Welch tests are applied to the replication means, with Holm adjustment across the 15 comparisons. The onboard-tote-lift configuration has longer mean cycle time at all tested task sizes. At n = 15, the means are 299.477 and 333.231 s/cycle, respectively: a 33.753 s increase (11.27%). The corresponding cycle-time-derived item rates are 180.314 and 162.050 items/h (-10.13%). These rates are calculated as 3600n divided by the scenario-mean cycle time; they are not measurements of the combined concurrent capacity of two level-captive shuttles. Importantly, task locations are sampled from different eligible-level sets in the two configurations, so the result concerns the implemented configuration-and-task-generation packages, not the isolated effect of a five-second tote-lift operation under identical picked locations. The study quantifies a cycle-performance difference alongside a reduction from two dedicated shuttles to one within the tested two-level block; it does not quantify system-level maximum throughput, investment cost, or reliability.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2412.01090

STATIC: Surface-normal-guided Two-branch Alignment and Temporal Integration for Consistent Video Depth Estimation

Sunghun Yang, Minhyeok Lee, Suhwan Cho, Jungho Lee, Sangyoun Lee

原文摘要

Video depth estimation is essential for applications such as autonomous driving, AR/VR, and robotics. Recent transformer-based single-image monocular depth estimation models perform well on a single image but struggle with depth consistency across video frames. Traditional methods aim to improve temporal consistency using multi-frame temporal modules or explicit priors like optical flow and camera parameters. However, these approaches face issues such as high memory use, reduced performance with dynamic or irregular motion, and a heavy reliance on the accuracy of external motion estimators. We propose STATIC, a novel model that independently learns temporal consistency in geometrically stable and unstable regions using only two adjacent frames. By leveraging intrinsic geometric cues rather than external motion priors, STATIC generates a depth-derived geometry-aware difference mask from surface normals to identify regions with inter-frame geometric variation by measuring directional variance. For geometrically stable regions, the Masked Stable (MS) module enhances temporal consistency by focusing on structurally stable regions. For geometrically unstable regions, the Surface Normal Similarity (SNS) module models inter-frame correspondences and ensures temporal consistency by measuring feature similarities between frames. A final refinement integrates the independently learned stable and unstable features, enabling STATIC to improve consistent depth prediction across consecutive frames. Experiments on KITTI, NYUv2, and Sintel demonstrate strong depth accuracy and temporal consistency, as well as stable performance across the tested frame-rate and camera-motion conditions.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34707

S2SND-v2: Unified Online and Offline Speaker Diarization with Speaker-Adapted w2v-BERT 2.0

Jincheng Wang, Li Li, Weixin Zhu, Yannan Wang, Tao Yu, Juan Liu, Ming Li

原文摘要

This paper presents S2SND-v2, a unified online and offline speaker diarization framework built on S2SND that improves acoustic feature extraction and the use of the resulting representations. For acoustic feature extraction, we introduce a speaker-adapted w2v-BERT 2.0 front end and compare full and pruned construction routes. To better use these features, overlap-aware activity-query masking improves speaker embedding extraction under overlap, while late-speaker training aligns unknown-speaker training with online inference conditions. Combining these improvements, the pruned system achieves competitive average diarization error rates of 14.52% online and 12.03% offline across eight test sets.

cs.SD

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.28876

Forecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agents

Liqin Ye, Haorui Wang, Fardin Ahmed, Rongzhi Zhang, Yuan He, Ziyuan Lin, Yanbin Yin, Jing Peng 等 11 位作者

原文摘要

Forecasting requires large language model (LLM) agents to gather evolving evidence, revise their beliefs, and make calibrated predictions over time. Yet evaluating and improving these capabilities is challenging because real-world events unfold continuously and outcomes may take months to resolve. We introduce Forecast-Dojo, a replayable environment that reconstructs resolved prediction-market events as sequences of dated forecasting steps, enabling reproducible evaluation, longitudinal analysis, and training from agent interactions. It comprises 1,568 Polymarket events split temporally into training and evaluation sets, alongside 18.8 million dated news articles. Across 12 models, research tools consistently improve forecasting performance, and greater capture of new evidence is associated with larger improvements over time. Nevertheless, all models trail historical market forecasts, while carrying a belief notebook across dates reduces research costs without consistently improving forecast quality. We supervise fine-tuned Qwen3-30B-A3B-Thinking-2507 on collected trajectories from Qwen3-235B-A22B-Thinking-2507 to demonstrate the environment's training utility. The student's accuracy is improved from 34.8% to 42.8% on the evaluation set.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34705

Safe by Benchmark, Unsafe in Practice: Lessons from 1331 Child-Related AI Incidents

Junfeng Jiao, Kevin Chen, Shrestha Mishra, Abhejay Murali, David Atkinson, Shriti Raj, Saleh Afroogh

原文摘要

AI systems are increasingly present in children's everyday environments: education, entertainment, social networks, and toys. Their safety is typically assessed at the model level, through benchmarks, red-teaming, and content filtering. However, most AI harm taxonomies lack child-specific evidence and under-specify developmental harm and the stakeholder asymmetries unique to minors. Building on prior taxonomies, we construct a child-centered harm taxonomy mapped to sociotechnical failure modes. We curate and code 1331 publicly reported child-related AI incidents, annotating internal and external harm types and the failure mode implicated in each incident. Our analysis reveals which harms are most prevalent in public reporting, how individual-level and population-level harms relate, and which failures are most often coded alongside harm. We find that harm concentrates in representational, dignity-related, and psychological categories, and co-occurs most often with deployment-context, governance, and misuse failures rather than model defects. Harm to an individual child is also frequently linked to population-level harm, reaching children who never interacted with the system. These findings suggest that model-level evaluations, while necessary, cannot by themselves anticipate the harm pathways most often documented for children. We conclude with actionable implications emphasizing mitigations beyond model-level safeguards such as content filtering: age assurance, consent verification for depiction, safety-by-design UX constraints, incident disclosure norms, and auditing regimes targeting developmental risk. Privacy-minimized annotations, a codebook, and documentation are available at https://github.com/The-Responsible-AI-Initiative/KidAID.

cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34704

Stable Continuous-Time Consistency Distillation: An Empirical Study with a Multistep Extension

Vinay Saji Mathew, Soundar R. Kumara, Gretta D Kellogg, William KM Lai

原文摘要

Continuous-time consistency models are an attractive route to few-step generation. They remove the discretization error inherent to the timestep grid that discrete-time consistency models depend on. Until recently, however, training them was unstable. Lu & Song (2025) address this with the TrigFlow formulation and a coordinated set of architectural and training-objective changes. We conduct an independent empirical study of this framework on CIFAR-10 and ImageNet-64. No open-weight TrigFlow teachers exist at these scales, so we train them from scratch and then verify the consistency distillation (sCD) and consistency training (sCT) behavior of students initialized from these teachers. On CIFAR-10, our students reproduce the reported FID at one and two steps. On ImageNet-64, they fall short, a gap that appears related to our teacher and to architectural choices the paper leaves unspecified. We also report a parameter-count gap of about 5% between the model size stated in the paper and a faithful re-implementation, which we attribute to the scale-and-shift conditioning projections in Adaptive Double Normalization. We then propose Multistep sCD (MS-sCD), a continuous-time, segment-conditioned multistep generalization of sCD. The segment-conditioning idea is borrowed from the discrete-time multistep consistency distillation of Heek et al. (2024); we build on their preliminary continuous-time experiments within the TrigFlow/sCM framework. The rest of the algorithm follows sCD. MS-sCD replaces sCM's two-step intermediate time with a fixed segment-boundary schedule and recovers sCD at M = 1. We report FID at M = 2, 4, 8 and compare against the discrete-time MSCD baseline. Code, model weights, and training scripts are available on GitHub (Mathew et al., 2026).

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34703

Intrinsic Information Rates of Summaries in Simulation-Based Inference

Vansh Bansal, Pradip Sharma Poudel, James G. Scott

原文摘要

Simulation-based inference often encodes observations $Y$ into a fixed-dimensional summary $S$, with the posterior conditioning only on $S$. While exact preservation often requires infinite information, any such summary imposes a finite information budget on inference which is rarely an explicit choice or measurement. In this paper, we make the budget explicit by modeling the summary as a lossy channel from $Y$ to $S$, and ask two questions: how large must the budget be, and how best is it spent? First, we show for parametric models that this budget, measured by the mutual information $I(Y;S)$, grows unboundedly as the posterior concentrates, even when fixed-dimensional sufficient statistics exist. More generally, the required budget is set by the distribution of the random posterior, and we bound it from above by quantizing posteriors and from below by converses that weight each posterior state by its probability. Second, we show that a finite budget is best spent stochastically. Under a common-support condition on the simulator, covering the continuous observation spaces typical of simulators, a deterministic summary necessarily loses something: a stochastic summary achieves \emph{strictly} lower distortion than every deterministic summary and every time-shared mixture of deterministic summaries at every positive budget too small for exact preservation. Motivated by these results, we insert a binary bottleneck into neural posterior estimators, measure each trained summary's rate, and compare summaries at matched rate. Across four simulator benchmarks and several encoder families, stochastic bottlenecks achieve favorable rate--loss tradeoffs, and architecture rankings change at different information budgets.

stat.ML · cs.LG · stat.CO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34702

Faster Polyhedral Intersections in 3D

Joseph Donato, Daniel Shevitz, Rao Garimella

原文摘要

The operation of intersecting two polyhedra, which can be reduced to clipping one polyhedron with a series of planes formed from another polyhedron, is central to intersection based mesh interpolation and material interface reconstruction. R3D is a robust library for such operation which implements the algorithm of Sugihara. In this paper, we present J3D, a new implementation of the clipping algorithm of Sugihara that provides substantial performance improvements over R3D.

cs.CE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34701

Movable-Element Multi-Functional RIS-Assisted Hybrid RSMA-NOMA: A Constrained Hybrid Reinforcement Learning Approach

Li-Hsiang Shen, Chi-Te Kuo

原文摘要

In this work, we propose a movable-element (ME) multi-functional reconfigurable intelligent surface (MF-RIS) architecture, termed MM-RIS, which integrates element mobility with adaptive signal reflection, transmission, amplification, and energy harvesting (EH) to enhance communication flexibility and energy self-sustainability. A hybrid rate-splitting multiple access (RSMA) and non-orthogonal multiple access (NOMA) transmission scheme is further designed to improve spectral efficiency. We formulate an energy efficiency (EE) maximization problem by jointly optimizing transmit beamforming, power and rate allocation, MM-RIS configurations, panel deployment, and ME positions. To address the resulting non-convex mixed continuous-discrete optimization problem, we propose constrained hybrid deep reinforcement learning with federated transformer and parametrized sharing (CRAFTS). CRAFTS integrates multi-agent proximal policy optimization (MAPPO) and multi-agent deep Q-networks (MADQN) through bi-directional parametrized sharing to handle continuous and discrete actions, respectively. Moreover, a transformer-based architecture and federated learning (FL) are incorporated to enhance state representation and distributed knowledge sharing, whilst a Lagrangian-based adaptive penalty mechanism facilitates the constraint satisfaction. Simulation results have demonstrated that the proposed MM-RIS architecture and CRAFTS framework substantially improve EE and constraint satisfaction compared to the benchmarks in the open literature. Moreover, the results validate the benefits of spatially reconfigurable MM-RIS, hybrid RSMA-NOMA transmissions, and intelligent collaborative learning, highlighting the potential of the proposed framework for energy-efficient and adaptive next-generation wireless networks.

cs.AI · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34700

DPE-Rec: Diversity-Preserving and Efficient Diffusion Language Model Recommendation for Bundle Construction

Pingchuan Ma, Bohan Jiang, Chengshuai Zhao, Dawei Li, Zhen Tan, Huan Liu

原文摘要

Generative bundle construction completes a partially observed bundle by generating its missing items from a large product catalog. Compared to autoregressive LLMs, diffusion LLM emerges as a natural fit for this unordered generation task. Their bidirectional attention provides an inductive bias better aligned with unordered bundle construction. Iterative denoising can reveal multiple tokens per step, potentially reducing inference latency. However, directly applying DLMs to this task presents two key challenges: 1 Despite its flexible reveal order, confidence-guided decoding tends to postpone semantic-fork decisions until refinement tokens constrain their choices, reducing bundle diversity. 2 Revealing more tokens per step can compromise recommendation quality, stifling the potential for faster inference. We introduce DPE-Rec, a diffusion framework for diversity preservation and efficient recommendation. DPE-Rec preserves diversity by introducing semantic-fork-aware GRPO, which prioritizes semantic-fork decisions via autoregressive rollouts. It improves efficiency through pseudo-trajectory distillation, which concentrates learning from the vast random corruption space onto the compact trajectory-induced subspace visited by high-quality decoding, unlocking reliable multi-token decoding. Together, these components enable diverse and accurate bundle construction with substantially fewer denoise steps. Experiments on multiple bundle construction benchmarks show that DPE-Rec improves recommendation performance by 63% on average, and its fast variant achieves 25.6$times$ faster inference on average than existing generative recommendation arts, with minimal loss in recommendation quality.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34697

Semantic Transferability of Generative Rate-Distortion-Perception Systems

Jinwan Jeon, Seoyeon Hwang, Sung Hoon Lim

原文摘要

Generative lossy compression combines a rate-limited representation with a stochastic decoder that preserves source-dependent information while generating unresolved detail. We ask what remains reusable when a rate-distortion-perception (RDP) system selected for one operating point is transferred to a prescribed conditional-generation task. We distinguish the single-letter RDP factorization from its block-code implementation and compare Full Redesign with three increasingly restrictive transfer strategies. Renderer-Only Transfer retains only the renderer and redesigns semantic steering. Representation-Induced Transfer additionally retains the semantic latent law induced by the original representation. Full-Model Transfer retains a compatible RDP code, marginalizing over the task conditional law to form its semantic encoder. For finite alphabets, we characterize Renderer-Only Transfer's exact compression-common-randomness rate region, renderer-hull controllability condition, and compression-rate penalty relative to Full Redesign. Under unlimited common randomness, this penalty is the minimum residual semantic information $I(S;U|X)$ forced by the inherited renderer. Representation-Induced Transfer is exact if and only if the semantic condition depends on the source only through the recurrent-class label $C$ of the end-to-end RDP test channel. Every compatible RDP code reused under Full-Model Transfer preserves $C$ and supports every task satisfying $X-C-S$. Any additionally transferable within-class semantic dependence must satisfy $I(S;X|C)\le R_0-H(C)$, where $R_0$ is the inherited compression rate. The bound is exact when $R_0=H(C)$. A scalar Gaussian specialization yields a renderer-noise controllability threshold, a closed-form transfer penalty, and examples of identical Gaussian RDP test channels with different Renderer-Only Transfer capabilities.

cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.09972

A deterministic polynomial-time algorithm for the Bilu--Linial signing problem on bipartite graphs

Zhiqiang Xu

原文摘要

We give a deterministic polynomial-time algorithm for the Bilu--Linial signing problem on bipartite graphs. For every finite simple bipartite graph of maximum degree at most an integer $Δ\ge3$, the algorithm assigns signs to its edges so that the signed adjacency matrix has operator norm strictly less than $2\sqrt{Δ-1}$. Our algorithm builds on the randomized recursive repair framework of Jadbabaie, Saberi, and Sra~\cite{JSS26}, with deterministic rules for sign selection and vertex deletion.

cs.DS · cs.CC · math.CO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.03825

Dynamic Short Convolutions Improve Transformers

Oliver Sieberling, Bharat Runwal, Rameswar Panda, Yoon Kim

原文摘要

Transformers have become the dominant architecture for large language models, largely due to the scalability and flexibility of attention, feed-forward layers, residual connections, and normalization. This paper introduces dynamic short convolutions as an additional neural network primitive for improving Transformers. Unlike static short convolutions, dynamic convolutions use input-dependent filters, which preserves the locality bias of convolution while increasing expressivity. Motivating experiments show that applying dynamic short convolutions to key, query, and value representations improves performance on challenging associative recall tasks compared with static convolutional variants. Across language-modeling experiments ranging from 150M to 2B parameters, dynamic convolutions consistently outperform standard Transformers and Transformers augmented with static short convolutions. Fitting scaling laws indicates a 1.33$\times$ compute advantage over compute-matched Transformers when dynamic convolutions are applied to the key, query, and value vectors, and a 1.60$\times$ advantage when adding dynamic convolutions after every linear layer. Dynamic convolutions also offer improvements on linear RNNs (Mamba-2/Gated DeltaNet) and mixture-of-experts architectures. We make these gains practical with custom Triton kernels that enable efficient training with a manageable end-to-end slowdown. These results suggest that dynamic short convolutions are a scalable, hardware-efficient, and expressive primitive for advancing Transformer-based language models.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34694

Gangqinpu: A Multi-Genre, Multi-Task Piano Dataset with Aligned Audio, MIDI, and Musical Scores

Wei Zeng, Anvay Mathur, Ye Wang

原文摘要

Aligned audio, performance MIDI, and musical scores provide valuable supervision for music analysis and performance modeling, yet datasets that jointly align all three modalities remain scarce and limited in scale and genre diversity. We introduce Gangqinpu, a multi-genre piano dataset containing 18,786 score-performance pairs and 1,007.1 hours of source audio, with automatic note-level alignments and derived beat/downbeat annotations. It spans diverse genres, including pop, classical, jazz, folk/traditional, rock, and blues. Our automated pipeline transcribes piano audio, aligns the resulting MIDI with musical scores, assigns genre labels, and filters out non-expressive performances with a score-informed binary classifier. We further construct joint splits with ASAP using conservative score-similarity grouping to reduce data leakage. We evaluate Gangqinpu on performance MIDI-to-score transcription, expressive performance rendering, and beat tracking. Downstream experiments demonstrate the value of Gangqinpu as complementary training data, with cross-dataset gains in beat tracking and primarily in-domain benefits for transcription and expressive performance rendering. The code and dataset are publicly available at https://github.com/wei-zeng98/gangqinpu.

cs.SD · cs.AI · eess.AS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.28963

AutoWorld: Learning Multi-Agent Traffic Simulation with Self-Supervised World Models

Mozhgan Pourkeshavarz, Tianran Liu, Nicholas Rhinehart

原文摘要

Simulation with realistic traffic agents is essential for validating autonomous driving systems. Existing data-driven simulators learn agent behavior from higher-level abstractions such as 3D bounding boxes and polylines, inferred by upstream perception pipelines. These lossy abstractions discard sensory context that directly shapes agent behavior, limiting the distributional realism that simulation aims to reproduce. To address this limitation, we propose AutoWorld, a traffic simulation framework that grounds agent behavior in raw sensor observations through a self-supervised world model trained on LiDAR occupancy data. Given world model samples, AutoWorld constructs a coarse-to-fine predictive scene context as input to a multi-agent motion generation model. Furthermore, we designed a motion-aware latent supervision objective that enriches AutoWorld's latent representation of scene dynamics. To better exploit this latent space during inference, AutoWorld employs a cascaded Determinantal Point Process framework to guide diversity-aware sampling across both the world model and motion model. Experiments on nuPlan and Waymo demonstrate that AutoWorld improves generation realism, with larger gains in partially observed scenarios where trajectory abstractions are most limited, reducing collision rates by 36%. AutoWorld also remains physically plausible under planner-controlled ego behavior and supports controllable, diverse safety-critical scenario generation.

cs.RO · cs.AI · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.03210

Differentiable FEM versus PINN for pavement layer inverse analysis: enforcing physics as hard or soft constraints

Yongjin Choi, Hyeonbin Moon, Seunghwa Ryu

原文摘要

Automatic-differentiation-based inverse analysis methods, including physics-informed neural networks (PINNs) and differentiable programming, have recently shown great promise due to their ability to compute accurate gradients and convergence efficiency. However, their applicability to falling weight deflectometer (FWD) backcalculation remains unexplored. This study critically evaluates PINN-based inverse analysis for a multilayer pavement system and investigates differentiable finite element method (DiffFEM) as an alternative based on a synthetic benchmark. The standard PINN does not recover layer moduli because of the sharp domain discontinuities inherent to layered pavement systems. Although we use an extended PINN with domain decomposition (XPINN), which shows better performance on discontinuous domains, its performance remains highly sensitive to loss weighting and network architecture, and degrades under measurement noise. By contrast, DiffFEM consistently achieves more accurate, stable, and computationally efficient inversion results. These results show and quantify the expected advantage of DiffFEM, which enforces the governing physics as a hard constraint in the solver, over PINN-based approaches, where the governing physics is imposed as a soft constraint through the loss function. More broadly, the findings suggest that the choice between PINN- and DiffFEM-based inverse analysis needs careful consideration, with DiffFEM offering practical advantages when an efficient and robust differentiable forward solver is available.

cs.CE · cs.LG · math.NA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.22957

Query-adaptive Recurrent Tokenization

Bavesh Balaji, Pranav Gopinath, Pouya Sadeghi, Sirisha Rambhatla

原文摘要

Visual information worth extracting from an image and the token budget it warrants depend on the text query. Yet modern vision and vision-language models largely encode images independently of the query and allocate a fixed visual token budget to every input. We introduce the Query-Adaptive Recurrent Tokenizer (QART), a backbone-agnostic module that makes visual representations both query-steerable and budget-adaptive. QART steers the visual representation toward query-relevant evidence while adapting its token budget to the amount of information required. Its key principle is simple. Additional tokens are allocated until the visual features relevant to the query are represented with sufficient fidelity. Starting from frozen encoder features, QART recurrently constructs a compact representation and uses reconstruction quality over the query-relevant visual support to control token allocation. On Visual7W and VQAv2, QART achieves 81.96% and 76.37% accuracy using only about 29 visual tokens, reducing token counts by 20-25x relative to dense VLM inputs. It further reaches 92.0% P@1 on CORE and 36.3% PR-AUC on PODS, outperforming SteerViT on PODS by 8.4%. Together, these results show that visual representations need not be fixed in either content or capacity and can instead adapt to what each query requires.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2605.02487

Visibility-Aware Mobile Grasping in Dynamic Environments

Tianrun Hu, Anxing Xiao, David Hsu, Hanbo Zhang

原文摘要

We consider mobile grasping in unknown and dynamic environments, where a robot must approach and grasp a target object using a camera with a limited field of view. This setting introduces two visibility constraints. Incomplete environmental observations can create collision risks along the whole-body trajectory, while occlusions can hinder object pose refinement during grasping. Previous systems often assume known or static environments and decouple perception from motion, leaving safety unresolved around unobserved obstacles. We present a unified system that enforces both visibility constraints at runtime through three core components. A velocity-aware gaze policy directs perception toward fast-moving regions of the planned swept volume, a hierarchical subgoal policy samples grasp and intermediate configurations that maintain target visibility, and a real-time whole-body planner replans over a receding horizon as the map updates. Across 400 randomized simulation scenarios and real-world trials on a Fetch mobile manipulator, our system achieves success rates of 70.4% in unknown static environments and 57.9% in dynamic environments, outperforming the decoupled navigation- and-manipulation strategy by 16.3 and 9.3 percentage points, respectively, while significantly reducing collisions.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34690

IsoAct: Geometry-Aware Post-hoc Debiasing via Isometric Actions

Sumin Park, Taero Kim, Minhyeong Cho, Subeen Park, Jong Hwan Lee, Kyungwoo Song

原文摘要

Learning representations that are robust to nuisance factors is essential for reliable deployment, but remains challenging when the representations lie on non-Euclidean manifolds. Existing debiasing methods typically assume Euclidean representations or apply linear interventions, which can distort the geometry of structured latent spaces. We propose IsoAct, a post-hoc framework that accounts for geometry in both nuisance identification and representation editing. It identifies nuisance-predictive directions using Fisher discriminant analysis (FDA) in tangent coordinates and applies corrections through manifold-native actions that preserve manifold membership. Controlled and real-world experiments on hyperspherical, hyperbolic, and $\mathrm{SE}(3)$ representations evaluate nuisance reduction, utility preservation, and manifold validity jointly. IsoAct reduces nuisance recoverability while retaining competitive utility. Its clearest joint result is on KLIFS, combining reduced kinase-group recoverability, strong structural prediction, and valid rigid poses.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34689

RSKD: Grounding Semantic Consistency in Driving VLMs via Distillation

Chuchu Xie, Yang Zhong, Kangan Qian, Hao Ye, Kun Jiang, Diange Yang

原文摘要

Knowledge distillation can transfer large multimodal models to compact models for autonomous driving, but uniform token-level matching can dilute planning-relevant semantics and amplify teacher errors. We propose RSKD, a semantic-consistency-guided distillation framework that routes supervision according to both the task importance of an answer phrase and its semantic consistency with the teacher prediction. Task-critical semantic phrases are localized in the ground-truth answer, and a phrase-level consistency score controls the balance between Jensen--Shannon divergence (JSD) distillation and ground-truth supervision. Teacher information is emphasized only where it is semantically consistent, while semantically inconsistent phrases receive stronger ground-truth supervision. We evaluate RSKD on DrivingVQA, LingoQA, and MapLMv2. RSKD improves over the compared student-based baselines on DrivingVQA and LingoQA and remains competitive on MapLMv2.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34688

From Speech Tokens to Stolen Voices: Attacker-Chosen-Text Speaker Impersonation via Representation Inversion

Ye Lu, Shen Wang, Runze Liu, Zhitao Ou, Haonan Huang, Yihan Yan, Fanghui Sun, Zhaoyang Zhang

原文摘要

Speech interaction systems have gradually evolved from traditional cascaded systems that use text as intermediate information to end-to-end speech language models that directly process speech representations. In some applications, the speech frontend runs on the user's device and sends speech representations to a remote server for inference, while the original audio remains local. However, these representations may still contain speaker identity information. If an attacker obtains them, it may use this information to imitate the user's voice, threatening their voice privacy. To investigate this risk, we propose \stia, a Speech Token Inversion Attack that generates speech with attacker-specified text in a victim's voice using a single short leaked representation, without access to the original audio or its transcript. Specifically, \stia converts discrete, continuous, or mixed speech representations into conditioning sequences and trains a conditional flow-matching speech generation model using pairs of different utterances from the same speaker in public speech datasets. The model combines speaker characteristics contained in the leaked representation with the specified text to generate speech in the victim's voice. Experiments show that, with a Moshi representation leak corresponding to 3 seconds of speech, \stia achieves an average CAM++ speaker cosine similarity of 0.78 and a target-text word error rate of 3.80\%. These results show that speech frontend representations reveal reusable speaker identity information and highlight the need to consider privacy risks when designing speech frontend representation methods.

cs.SD · cs.AI · cs.CR · cs.CV · cs.MM

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.02423

Investigating and Alleviating Harm Amplification in LLM Interactions

Ruohao Guo, Wei Xu, Alan Ritter

原文摘要

Large language models (LLMs) can serve as helpful assistants, yet they can equally function as harm amplifiers that enable malicious users to achieve harmful outcomes beyond their capabilities through extended interactions. This risk manifests along two axes, i.e., democratizing domain expertise that allows novices to produce specialized harmful content, and scaling harmful operations at volumes that manual effort cannot match. Existing works, however, often overlook how LLMs compound harm across multi-turn conversations. We introduce HarmAmp, a new benchmark for multi-turn harm amplification scenarios spanning twelve risk categories. Each scenario is grounded in real-world threats and satisfies rigorous criteria, i.e., substantive amplification, operational specificity, and multi-turn necessity. We further propose TrajSafe, a proactive monitor that anticipates harmful trajectories and intervenes through actions such as probing users' genuine intents and steering the models towards safer completion. Our extensive experiments demonstrate that TrajSafe significantly reduces the harmfulness incurred in multi-turn interactions while preserving a low over-refusal rate and the target model's general capabilities. Our work offers a promising paradigm to alleviate the nuanced safety risks in LLM interactions.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34687

Machine Learning Applications in the Solar Interior and Atmosphere

Vishal Upendran, Carlos J. Díaz Baso

原文摘要

The solar interior and atmosphere constitute a strongly coupled, multiscale dynamical system defined by continuous temporal evolution. Predicting the state of this system requires modeling physical interactions that span disparate spatial and temporal scales, constrained by heterogeneous and sparse data. This chapter formalizes the Sun within the mathematical framework of dynamical systems theory, defining a global state vector ($\vec{S}$) governed by thermodynamical, kinetic, and magnetic properties. Because solar observations represent projected, multi-modal, and partially observable measurements ($\vec{O}[\vec{S}]$) of this hidden state, pure physics-based deduction is fundamentally constrained. We present a unifying thesis: the primary role of machine learning in heliophysics is to act as a structured family of mathematical operators---specifically Inference ($\mathcal{I}$), Emulation ($\mathcal{E}$), Propagation ($\mathcal{P}$), and Control ($\mathcal{C}$)---that reconstruct, simulate, and couple this global state vector across disparate physical layers. By framing the vast, multi-disciplinary literature within this unified state-space taxonomy, we demonstrate how data-driven techniques bridge observational gaps to resolve hidden multiscale couplings and dramatically accelerate the simulation of non-linear processes, establishing a rigorous pathway to predict the global evolution of the Sun.

astro-ph.SR · astro-ph.IM · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34685

Good Rankings, Poor Choices? Rethinking Language-Only Vision-Language Model Selection

Hyuk Kwon, Jaebyeong Jeon, Hyeonseo Jang, Kibok Lee

原文摘要

Language-Only Vision-Language Model Selection (LOVM) aims to identify the Vision-Language Model (VLM) with the highest zero-shot accuracy on a target task using only textual information. We revisit the existing LOVM evaluation protocol and argue that ranking metrics, such as top-5 recall and Kendall's rank correlation, do not directly assess the performance of the selected model. We therefore adopt simple regret (SR), defined as the performance gap between the best and selected models, and introduce Outlier-Robust Normalized Regret (ORNR) to account for the varying performance ranges across tasks while reducing sensitivity to outliers. Building on this revised evaluation protocol, we propose Target-Conditioned Expected Source Regret (TC-ESR), a training-free method that selects the model with the lowest similarity-weighted mean regret across source tasks. Across 22 target tasks and 43 VLMs, TC-ESR achieves the lowest mean SR and ORNR among all compared methods. Separately, we identify two sources of target performance leakage in the prior ranking-based evaluation protocol and provide corrections that remove both.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34684

Knowing When the Evidence Is Enough: Requirement-Directed Search with Horn-Closure Certificates

Xinyu Zhang, Weiwei Sun

原文摘要

After each Web search, a search-augmented model must decide whether its evidence suffices: answer, search again, or abstain. Prevailing systems leave this to holistic model judgement, which can accept a context naming every entity yet lacking one required fact. We instead make sufficiency structural: a per-query requirement hypergraph states which facts jointly yield another fact. This raises two challenges: deriving requirements from the question alone, and linking each requirement to passages about the right entity. Certify therefore decomposes the question, searches per requirement, and accepts links only after entity checks. Horn closure over the links yields a certificate, the minimal sufficient passages and their derivation, or an abstention naming open requirements. Given correct retrieval, requirements and links, the decision is sound, and complete up to the entity check. Pooled over three corpora with unanswerable twins, Certify decides significantly more accurately than search agents, graph retrieval and sufficiency judges in default configurations. On the same evidence, it matches a proprietary model's sufficiency label without an additional model call. Over 21M Wikipedia passages, entity checks add 4 to 13 points of decision accuracy where gold evidence exists. Finally, answers from its certificate are 80% correct, against 57% from all retrieved passages.

cs.IR · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34683

Topic-Level Fairness in Retrieval-Augmented Generation

Jaeyoung Park, Hantian Zhang, Kexin Rong, Steven Euijong Whang

原文摘要

Group fairness in retrieval-augmented generation (RAG) systems is typically evaluated using metrics aggregated across queries. However, such metrics can conceal topic-level disparities: a system may favor women on questions about human rights and men on questions about actors and filmmakers, appearing nearly neutral overall even though neither topic is fair. We therefore study topic-level fairness, which requires group fairness to hold within each topic rather than only in aggregate. To reduce the topic-level disparity, we adapt the reranker separately for each topic with a Bradley-Terry objective under direct supervision from the generated output: preference pairs built from the generator's own output carry the direction that topic requires. With preference pairs built from RoMQA alone, the adaptation reduces the mean absolute per-topic disparity by 51% on RoMQA and by 40% on TREC Fair Ranking while retaining accuracy. No baseline reaches the reduction, even when modified to treat each topic separately rather than apply one correction to every topic. Neither does our method with one reranker for all topics, which follows the direction that most topics require.

cs.AI

查看论文
arXiv ↗PDF ↗