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：2026-11-09 16:31 · 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 2026-11-08 17:25 — 2026-11-09 17:25（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 16:31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 2026-11-09 16:29（北京时间）
新论文 · v1arXiv:2610.37224

Spine: Compiling Subtask Trees into Structured Context for Long-Horizon Coding Agents

Jiahong Xiang, Kunqiu Chen, Lingming Zhang, Yuqun Zhang

原文摘要

Long-horizon coding tasks contain nested subtasks. Typically, agents record interactions sequentially into a growing history, causing context inflation and performance degradation. Compressing or trimming the history without explicit subtask boundaries can discard information needed by unfinished subtasks. Conversely, recursive subagent delegation isolates completed subtasks through child agents by assigning every subtask boundary to delegation, which conflates subtask granularity with executing agent choice, adding execution and coordination overhead. We introduce Spine, an interface and runtime that align model context with subtask nesting and completion. An agent declares explicit subtask boundaries through work scopes, allowing the same agent to execute nested subtasks inline while reserving delegation for independent parallel tasks. The runtime organizes execution in SpineTree, a persistent tree recording subtask relations, local interactions, completion states, and returned results. Before each model call, it compiles the tree into model context just in time, retaining unfinished subtasks' interactions and replacing completed subtasks' details with their results, while preserving prefix-cache reuse. We integrate Spine into Codex to build SpineCodex. With GPT-5.6 Sol, compared with native Codex, SpineCodex improves SWE-Milestone Score by 11.8% while reducing total cost by 32.4%, improves the average ProgramBench test-pass rate by 17.3%, and improves Mean@5 on eight of the ten evaluated FrontierSWE tasks. On SWE-Milestone, it also achieves a comparable Score to Recursive Subagent at 73.7% lower total cost. We also integrate Spine into Pi through a reusable software package: with Gemini 3.8 Flash and Qwen 3.8 27B, it improves SWE-Milestone Score by 9.5-17.5% and the average ProgramBench test-pass rate by 4.3-8.7% compared with native Pi.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2505.19969

Differential Privacy of Decentralized Learning: Centralized Rate Conditions and Nearly Tight Guarantees

Antti Koskela, Tejas Kulkarni

原文摘要

We analyze the differential privacy of gossip averaging on a graph with independent Gaussian noise at every node, as seen by a subset of observing nodes. We characterize the privacy loss of any sensitive node over multiple gossip steps as that of a Gaussian mechanism whose sensitivity is the solution to a binary quadratic problem with a coefficient matrix determined by the gossip matrix. We recognize this matrix as a Toeplitz matrix plus a small correction, and show that its Toeplitz symbol controls how the DP guarantees grow with the number of steps. Under a computable condition on the Toeplitz symbol, the privacy guarantee matches that of a trusted central aggregator, and we give a utility bound for strongly convex learning problems that similarly matches the centralized case. Finally, we give numerical recipes for upper and lower bounds on the DP guarantees. On realistic test cases, the two bounds agree to within a few percent.

cs.LG · cs.CR · cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37219HF 社区推荐

Vision-Language-Action or World-Action? Just Action Models

Yonghao Yu, Lang Huang, Runyi Li, Toshihiko Yamasaki

原文摘要

The vision-language-action (VLA) and world-action model (WAM) communities debate whether control policies should inherit pretrained knowledge from vision-language models or from visual generators. The debate, however, bundles three separable choices: backbone initialization, the objective applied to future observations, and whether the machinery for that future loss is kept at inference. A gap between a VLA and a WAM therefore cannot simply be attributed to any one of them. We show that decoupling these choices yields a common framework for both families, which we term Just Action Model (JAM): a pretrained visual backbone with an action expert, trained with an action loss and a foresight loss. The foresight loss trains current-observation features to predict frozen encodings of the recorded future through a prediction head discarded after training, so no visual generation is involved in either training or inference, and the backbone can be chosen freely. We first compare objectives within fixed policy architectures, then evaluate the foresight recipe across backbone families. The resulting JAM policies outperform their matched FastWAM and ImageWAM counterparts on LIBERO and LIBERO-Plus, and achieve similar or slightly higher success rates on RoboTwin. Compared with FastWAM, JAM improves the success rates from 97.0%/55.3%/91.2% to 98.2%/64.5%/91.4%, respectively. With cached foresight targets, JAM reduces estimated online training FLOPs per sample per update by 73% relative to FastWAM. Our results show that future supervision improves control without visual generation or additional inference machinery, and strong foresight performance is attainable with either generator-initialized or vision-language backbones. Project Page: https://y0uroy.github.io/JAM

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.14749

The Counting General Dominating Set Framework

Jiayi Zheng, Boning Meng

原文摘要

We introduce a new framework of counting problems called #GDS that generalizes #$(σ, ρ)$-Set, a class of domination-type problems that includes counting dominating sets and counting total dominating sets. We explore the intricate relation between #GDS and the well-known Holant framework. We adapt the technique of gadget construction of Holant to the #GDS framework; using this technique, we prove the #P-completeness of counting dominating sets for 3-regular planar bipartite simple graphs. Using interpolation for powered Holant problems and a special reduction method via symmetric bipartite graphs, we also prove the #P-completeness of counting total dominating sets for the same graph class.

cs.CC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37218

TopoField: Technical Report for ECCV 2026 SceneFun3D Challenge

Zhiwei Chen, Zhiheng Fu, Zixu Li, Mingyu Zhang, Jiale Huang, Yupeng Hu

原文摘要

Functional segmentation requires locating small interactive parts, such as knobs, buttons, and sockets, in indoor point clouds and returning confidence-ranked instance masks. A point-wise semantic predictor produces a continuous probability field, whereas the benchmark evaluates a discrete set of scored instances. This creates a substantial field-to-instance gap. We present TopoField, a deterministic decoder built on top of VOLT. TopoField first converts 13 test-time forward passes into a semantic consensus field, then decodes instance candidates from the consensus geometry, and finally ranks the candidates in a class-aware manner. The augmentation stage retains the processed-point identity of every fragment prediction, accumulates probabilities in a common point array, normalizes by coverage count, and fuses the resulting caches. The decoding stage separates high-confidence cores from broader support regions, constructs a symmetric radius-pruned point graph, and uses a multi-source graph-geodesic partition to split support regions that contain multiple seeds. On 561 ground-truth instances across 30 validation scenes, an IoU-0.5-valid candidate exists for 67.2% of instances, and top-1 coverage is 20.0%. These complementary measurements motivate joint attention to candidate construction and ranking. TopoField achieves 28.286% AP, 41.383% AP50, and 47.558% AP25. TopoField achieved second place on the ECCV 2026 SceneFun3D Challenge.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.19358

LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning

Yu Zhao, Zekun Zhang, Fan Jiang, Bo Zeng, Xintong Wang, Chonghan Liu, Shimin Shan, Yichao Du 等 9 位作者

原文摘要

Long chain-of-thought (CoT) reasoning models such as DeepSeek-R1 keep lengthening their inference chains under test-time scaling, yet standard self-attention incurs quadratic cost in context length, making long-CoT deployment costly in production. We therefore introduce LISA (Linear-Indexed Sparse Attention), a plug-and-play replacement for self-attention that requires no full pretraining. LISA combines a linear-attention branch for long-range memory with a Lightning Indexer that dynamically selects the most relevant tokens for a sparse self-attention branch. The two branches are fused through a learned gate, so the model retains broad context while focusing computation on informative tokens. We train LISA in two stages. In Stage 1, a linear-attention branch is integrated with sliding-window attention and distilled from a frozen teacher's full-attention distribution. In Stage 2, the Lightning Indexer replaces the static window and is trained with a per-head KL-divergence objective to mimic teacher attention patterns. The resulting model reduces eager-mode self-attention computation from quadratic in sequence length to linear in the number of generated tokens and the selected context budget. Experiments on DeepSeek-distilled Qwen models show that LISA cuts measured eager-mode mean sample latency by 23.9% at 16K context without degrading long-context reasoning quality. Across nine mathematical and code reasoning benchmarks, the gated LISA-1.5B model improves the equal-weight benchmark average by 4.2 percentage points relative to the full-attention baseline.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37216

Zhengrong-Spatial-Aware 1.0: Advancing 3D Multimodal Intelligence

Yu Zhang, Xiaogang Wang, Yuhang Cheng, Jingrui Li, Wenbo Chen

原文摘要

This report presents the implementation and validation of two end-to-end multimodal adaptation pipelines for 3D-aware visual question answering on a custom spatial dataset. The first pipeline fine-tunes HiSpatial-3B, which augments RGB observations with metric-scale 3D point maps; the second adapts Qwen3-VL through memory-efficient QLoRA-based supervised fine-tuning. The completed engineering stack covers dataset conversion, image-annotation alignment, monocular geometry preprocessing, instruction construction, mixed-domain training, checkpoint management, batch inference, and automated evaluation. On the target spatial benchmark, HiSpatial adaptation increases overall accuracy from 1.73% before fine-tuning to 79.89% at 3,600 steps. On a separately collected styled split, accuracy improves from 14.9% to 55.1%, indicating transfer beyond the original training set. The Qwen3-VL pipeline is likewise implemented end-to-end for both 8B- and 32B-scale models using mixed-domain QLoRA adaptation. The resulting accuracy improves from 20.74% to 45.27% for Qwen3-VL-8B and from 30.79% to 47.60% for Qwen3-VL-32B. Together, these results establish two complementary and reproducible adaptation pipelines for geometry-aware and general-purpose multimodal spatial reasoning. These results establish a reproducible engineering foundation for subsequent work on metric 3D reasoning, spatial grounding, and domain-adapted multimodal systems, while also identifying training-data composition as a central factor in preserving general multimodal capability during specialization.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37215

Retrieve to Act: Motion Primitive Graph Retrieval for Robust VLA Execution

Pham Tri Quang, Bao-Ngoc Dao, Minh Duc Nguyen, Duc-Duy Nguyen, Hung T. Ho, Linh Dang Le, Trong-Bao Ho, Thien-Loc Ha 等 18 位作者

原文摘要

Vision-Language-Action (VLA) policies demonstrate remarkable semantic generalization, yet remain highly vulnerable to out-of-distribution (OOD) visual shifts during execution. While existing test-time methods attempt to suppress spurious visual cues, they fundamentally overlook the rich, uncorrupted kinematic priors embedded in the policy's own training experience. We introduce Retrieve to Act (R2A), a test-time scaling framework that formulates OOD robustness purely as a geometric motion primitive retrieval problem. R2A bypasses fragile visual features by structuring successful training demonstrations into an offline spatiotemporal motion primitive graph. During inference, a query-dependent Graph Neural Network dynamically localizes the robot's ongoing execution within this graph, retrieving structurally compatible future motion primitives. These retrieved geometric priors are then seamlessly harmonized with the frozen VLA's predicted actions via a learned, dimension-wise gating mechanism, adaptively rectifying erroneous spatial trajectories while preserving the policy's local reactivity. Extensive experiments across three state-of-the-art VLA architectures, GR00T N1.7, $π_{0.5}$, and StableVLA, demonstrate that R2A consistently and significantly enhances robustness against diverse contextual perturbations. R2A achieves absolute success rate improvements of up to +12% in simulation benchmarks (LIBERO-Plus, RoboTwin2.0-Plus) and +40% in real-world deployments, without requiring any finetuning of the base policies. Project page: https://retrieve2act.github.io/r2a/

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37213

Retrospective macromolecular pool fraction mapping from conventional clinical MRI: a physics-guided self-supervised deep learning framework

Jelmer van Lune, Miha Fuderer, Oscar van der Heide, Matteo Maspero, Martin B. Schilder, Jan Willem Dankbaar, Stefano Mandija, Alessandro Sbrizzi

原文摘要

Macromolecular pool fraction (MPF) is a quantitative imaging biomarker sensitive to myelin integrity and other changes in tissue macromolecular content, but specialized acquisitions and reconstruction methods limit its use in large-scale studies. We present a physics-guided, self-supervised deep learning framework for retrospectively estimating MPF directly from conventional clinical brain MRI ($T_1$-weighted, $T_2$-weighted, and fluid-attenuated inversion recovery [FLAIR]) without paired quantitative reference scans. The framework embeds an analytical two-pool magnetization transfer signal model that related sequence-averaged radiofrequency transmit power to apparent longitudinal relaxation. To accommodate heterogeneous clinical protocols, the network conditions intermediate features on acquisition parameters via adaptive instance normalization. It was trained and evaluated on a multisite, multivendor, multiprotocol dataset of 7,705 MRI sessions (3 T). Across 1,237 test sessions, mean MPF was $0.182 \pm 0.007$ in white matter and $0.144 \pm 0.009$ in gray matter, with limited variation across vendor-by-protocol groups (between-group coefficient of variation: 2.65% and 5.63%, respectively). In 70 sessions with demyelinating-disease labels, MPF was 35.6% lower in segmented lesions than in normal-appearing white matter. MPF maps from two different clinical protocols acquired in a healthy volunteer showed a mean voxel-wise absolute percentage difference of 7.7% and a concordance correlation coefficient of $0.888$, indicating good cross-protocol consistency. These results suggest that magnetization transfer-informed self-supervised learning enables stable MPF mapping from conventional clinical MRI, providing a scalable approach to investigate demyelinating pathology in both existing imaging archives and prospectively acquired conventional clinical scans without dedicated qMT acquisitions.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37211

Uncovering Shortcut Amplification in Video RLVR through the Lens of Perceptual Uncertainty Collapse

Jiafeng Liang, Xianhao Ou, Tao Ren, Rongchuan Mu, Runxuan Liu, Dandan Tu, Ming Liu, See-Kiong Ng 等 9 位作者

原文摘要

Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective post-training paradigm for enhancing the video reasoning capability of Large Multimodal Models (LMMs). Despite its empirical effectiveness, we show that outcome-level optimization can introduce an undesirable shortcut amplification effect, whereby models increasingly favor text-prior answers even when they are not supported by the visual evidence. To characterize this behavior, we investigate the training dynamics of video RLVR through the lens of perceptual uncertainty, analyzing how predictive uncertainty evolves under video-conditioned and text-only contexts. Our analysis identifies a perceptual uncertainty collapse phenomenon, in which RL training continuously sharpens the model's answer distribution while the uncertainty reduction attributable to visual evidence progressively diminishes. A further gradient-direction analysis reveals that such confidence enhancement becomes increasingly less aligned with visually grounded uncertainty reduction and is instead dominated by text-prior compression. Motivated by these findings, we propose Bifocal Self-distillation Policy Optimization (BSPO), a self-distillation framework that regulates policy updates with two complementary distributional signals. Specifically, BSPO derives empirical reasoning principles from intra-group correct and incorrect rollouts to identify reasoning-sensitive tokens, and introduces shortcut-aware visual perturbation to penalize predictions that remain invariant when task-relevant visual evidence is weakened. By adaptively reweighting the original RL advantage, BSPO preserves the task-solving benefits of RLVR while promoting updates that are both reasoning-sensitive and visually grounded. Extensive experiments validate the effectiveness of BSPO in improving video reasoning performance and strengthening visual faithfulness.

cs.CV · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.27895

The Shape of the DPO Hyperparameter Landscape: What to Measure, How It Moves with Scale, and When Not to Transfer It

Hannan Mahadik, David Salinas, Jacek Golebiowski, Aaron Klein

原文摘要

Direct preference optimisation (DPO) is widely used for language model post-training, but its performance depends strongly on the choice of its hyperparameters, such as the learning rate and the reference-policy regularisation parameter $β$. To better understand the DPO hyperparameter landscape, we conduct extensive experiments using a dense hyperparameter grid across different model scales from the same family. This allows us to analyse how the optimal DPO hyperparameters evolve with model size and the number of update steps, with intermediate checkpoints providing an inexpensive signal to accelerate the hyperparameter optimisation process. Furthermore, by evaluating our models on both static and dynamic benchmarks, we identify which benchmarks provide the strongest signal for hyperparameter selection. Finally, we investigate how different state-of-the-art hyperparameter optimisation strategies perform in this setting. Our experiments show that the optimal learning rate varies with model size and that hyperparameters are not transferable across training datasets. We also find that validation loss is a poor proxy for hyperparameter optimisation, as hyperparameters that minimize validation loss only weakly correlate with optimal hyperparameters for downstream benchmarks. Therefore, DPO hyperparameters need to be tuned specifically for the target model, dataset, and evaluation objective. We also show that short candidate training runs can substantially reduce the cost of this selection. We release all our training configurations and evaluation results to support reproducible analysis of selection quality and training cost.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.32983

New Lenses on Learning Design: Course Types and Indicators from Large-Scale Moodle Data

Ekaterina Soroka, Niels Seidel, Marcus Specht, Kamila Misiejuk

原文摘要

Although learning design (LD) plays a central role in shaping online courses, large-scale empirical evidence on how courses are actually structured remains scarce, and existing analytics work has characterised courses through student engagement with specific learning activities rather than through indicators of the design itself. This study addresses both gaps through an analysis of learning management system (LMS) data from 606 courses at a distance university. Using LMS data, we first applied dimensionality reduction and clustering to a structural variable set, from which three distinct LD types emerged empirically: Compact, Expansive, and Interactive and statistically characterised how their design elements differ across disciplines, activity load, and interfaces. Building on this typology, we derived three LD indicators, activity-mode balance, structural clarity, and analytics readiness, each combining multiple LMS-derived variables into higher-order constructs that target a different aspect of LD. All three indicators differentiated significantly across the LD types and added pedagogically meaningful dimensions for interpretation. These contributions advance the operationalisation of LD in technology-enhanced learning research by demonstrating that higher-order LD indicators can be derived directly from routinely collected LMS data, and offer empirical insight into how LD manifests at scale within a large distance university.

cs.CY · cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37206

SimplexLoRA: Dynamic Rank Updating via Alternating Minimization with Simplex Projection

Igor Shalygin, Grigorii Davydenko, Andrey Veprikov, Aleksey Antonov, Nikolay Bushkov, Stanislav Moiseev, Aleksandr Beznosikov

原文摘要

The success of large language models in real-world applications relies on parameter-efficient fine-tuning methods such as Low-Rank Adaptation (LoRA), which inserts compact, trainable adapters into selected layers. In this paper, we propose SimplexLoRA, a LoRA variant that adaptively adjusts adapter ranks during fine-tuning based on their learned importance. Unlike standard LoRA, which employs a fixed rank across all layers, SimplexLoRA optimizes per-adapter importance weights on the $n$-scaled simplex during a short warm-up and then freezes them, dynamically allocating capacity where it is most beneficial without increasing the overall parameter budget or inference cost. We evaluate SimplexLoRA across 12 language understanding, summarization, and reasoning tasks using DeBERTaV3, BART-large, Llama 3.1 8B, and Qwen3-8B. Our results show that SimplexLoRA consistently matches or outperforms standard LoRA and recent adaptive baselines, with the largest gains at low ranks. Our code is available at https://github.com/brain-lab-research/SimplexLoRA.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37203

Remember Where You Walk: Learning Spatial Memory for End-to-End Legged Robot Exploration

Leon Magnus, Nico Bohlinger, Jan Peters, Oleg Arenz

原文摘要

Humanoids and other legged robots operating in complex environments must remember information that leaves their field of view and only becomes relevant much later. Reinforcement learning policies address this using memory networks such as LSTMs that are trained end-to-end with the policy to memorize such task-relevant aspects. Yet, such architectures often fail to preserve sufficient information over long horizons. In this work, we propose a network architecture based on Hadamard memory that specifically targets robot navigation. Our Local Spatial Matrix Memory (LSMM) enables RL agents to store generic task-relevant information at specific, position-based memory cells, enabling flexible and spatially grounded memorization. We evaluate LSMM on the task of autonomous maze exploration, where it matches the maze coverage of strong recurrent and finite-history baselines while being the only architecture that remembers the maze layout, reducing the reconstruction error threefold.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37202

3D-SceneQ: Empowering 3D LLM With Query-Guided Adaptive Pruning and Multi-Modal Feature Enhancement

Yongqi Shan, Lu Zhang, Jiazuo Yu, Yunzhi Zhuge, Huchuan Lu

原文摘要

Current 3D scene understanding pipelines typically concatenate vast numbers of 3D object tokens with text tokens and feed the resulting sequence to a Large Language Model (LLM). However, existing 3D-LLMs for scene understanding encounter two major limitations: (i) excessive inclusion of task-irrelevant object data, introducing noise that reduces reasoning accuracy and increases hallucinations; and (ii) reliance solely on point cloud data, which inherently lacks the rich semantic information available in complementary 2D modalities, such as color, material properties, texture, and high-level contextual relationships. To address these challenges, we introduce 3D-SceneQ, a 3D LLM that unifies adaptive token pruning with multimodal semantic enrichment, markedly advancing scene understanding, reasoning, and grounding. Specifically, we propose a Query-Guided Adaptive Pruning (QGAP) module that adaptively selects task-relevant objects based on the intended meaning of user instructions, leveraging a learnable latent query to retain critical information while effectively suppressing irrelevant noise. In addition, we introduce a Multi-modal Object-level Feature Enhancement (MOFE) module, which integrates 2D feature embeddings from pre-trained models into 3D representation to enrich object-level semantic information. Evaluations show that 3D-SceneQ outperforms current state-of-the-art methods across multiple benchmarks (e.g., +5.7 CIDEr on Scan2Cap and +17.0 EM@1 on SQA3D), demonstrating its remarkable capabilities in various 3D language reasoning tasks.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37734

When Skills Tell Agents Not to Ask: A Large-Scale Study of Oversight Directives in Agent Skills

Timofey Sanko, Yuan Tian

原文摘要

Agent skills, reusable instruction packages centred on a SKILL.md file, extend AI agents on demand, and a single line in a widely copied skill reaches every agent that loads it. Some lines are oversight-loosening directives: they tell the agent to proceed without approval, to bypass checks with --no-verify, or to keep working without checking in. Although such directives can remove a checkpoint from every agent that loads them, no prior work has examined them. We present the first large-scale study of oversight-loosening directives, analyzing 1.53 million English skills from GitSkills. We split skills into units (sentences, bullets, table cells, and code lines), develop a codebook that labels oversight directives by polarity, mechanism, and scope, label 2,097 units by hand, and train a detector to scale the analysis. Our results show that about one in seventeen skills (about 88,000 skills) contains a loosening directive. These directives most often loosen oversight through permission flags, and most of them (70.1%) apply unconditionally rather than only in specific contexts such as CI. Compared with skills that have the same amount of oversight language, skills that run shell code, install packages, or use sudo have 1.7-1.8 times the odds of containing a loosening directive, an association that holds across all our robustness checks, and they do not compensate with more tightening. Loosening spreads through a few upstream skills rather than through edits by their adopters: 2.4% of the skill families that carry loosening account for half of all copies of loosening-carrying skills, and 1.1% of distinct loosening units for half of all loosening occurrences. Open-source skill scanners catch at most 46% of loosening directives, with a precision below 0.4, while the LLM behind them, prompted with our codebook instead, catches 61% at a precision of 0.71.

cs.CR · cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37201

Does Your Generalist Skill Optimizer Really Incentivize Agentic Tasks? Rethinking Skill Optimization via Bipartite Attribution

Jiawei Zhou, Bo Peng, Yuxuan Huang, Ming Zhang, Youbang Sun, Xiang Wang, Chaochao Lu

原文摘要

Skill optimizers adapt an agent to long-horizon tasks, such as repairing a terminal environment, by rewriting its skill, a natural-language procedure in its context, and keeping the edits that raise success on a small dev set. On such tasks success is noisy, so a gain on a small dev set does not show that an edit helps, and a success score does not show what the edit costs. We introduce BiPA, which replays an optimizer's acceptance rule on candidates identical to its seed to measure what selection alone reports, and records each episode as a bipartite graph of turns and the text they read to trace extra input tokens to the behavior behind them. Across three optimizers, three agentic benchmarks and two models, the learned skills succeed about as often as their hand-written seed, 0.1 points higher on average. Their dev gains vanish on test: keeping the best of several candidates on at most 30 tasks reports gains this large even when none changed. They read about 16% more input tokens: the optimizers almost always add rules, half to re-check work and some to act one call at a time, and the agent follows them as extra turns, each re-sending the whole conversation. Four principles follow: accept an edit only if its gain exceeds what selection alone reports; charge it for the turns it adds, not for its length; let the editor delete and merge rules; show it what earlier rules cost. Code is available at https://github.com/valleysprings/BiPA.git.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37200

PipeLink: Contract-Guided Linking of GPU Kernel Components

Jize Guo, Xupeng Miao

原文摘要

The fastest machine-learning kernels are compositions of components, such as loaders, matrix-multiply mainloops, epilogues and communication stages, that run concurrently on one GPU streaming multiprocessor and share its on-chip memory, barriers, warps and registers. Because these components hard-code where they sit in this shared space, they cannot be compiled, shipped or replaced on their own: combining components from different sources means forking them by hand or keeping them in separate kernels. We present PipeLink, a contract-guided linker for GPU kernel components. Each component is compiled separately into an LTO object that carries a contract stating what it requires and what it promises; PipeLink checks the contracts against each other, relocates every component by solving one joint placement of the SM's resources, and generates the transfers between them, and the vendor LTO backend folds the result into constants. Across 51 configurations on Hopper and Blackwell GPUs, linked kernels run within 0.2% of the same sources compiled as one unit. Linking makes new compositions practical: a CuTe attention operator inside a ThunderKittens decode megakernel speeds up decoding by 2.16$\times$, a four-owner MoE training megakernel matches the original monolith, one unchanged attention core yields sparse and context-parallel variants that outperform FlexAttention, vLLM and Transformer Engine, and a GEMM + SwiGLU composition whose consumer serves three GPU architectures runs 1.2$\times$ faster on Blackwell than cuBLAS with a compiled activation.

cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37199

A Bi-level Co-design Framework for Lunar Monoped with 2D Jump and Landing Control

Sanjay Ramkumar, Suraj Kumar

原文摘要

Legged robots for lunar exploration must be designed for low gravity, where reduced contact forces and long flight phases make leg morphology and controller choice interdependent. We study this for a planar monoped in lunar gravity ($1.625$ m/s$^2$) using a bi-level co-design framework: a differential evolution outer loop searches over link lengths, and each candidate is evaluated on a vertical jump by either a quadratic program based task-space controller (QP-TSC) or a direct-collocation based trajectory optimization. The two controllers yield different optimal link lengths, and trajectory optimization outperforms the QP-TSC across most of the design space, with 17% lower Cost of Transport (COT) at their respective optima. We then extend to a 2D jump, where trajectory optimization with centroidal angular momentum regulation produces stable in-place and forward jumps, and an LQR controller absorbs impact and stabilizes the robot after touchdown. This is demonstrated on a baseline morphology with both links 0.3 m long.

cs.RO · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37197

Conditional Values: The Contingent Foundations of Attitudes toward Artificial Intelligence

Sam Flanders, Melati Nungsari

原文摘要

How do broader values shape whether people judge artificial intelligence (AI) as good or bad for humanity? This article analyzes provisional World Values Survey Wave 8 data from 40,960 respondents in 24 country samples using pooled and national prediction models, outcome-independent respondent profiles, and groups of countries. The analysis reveals a cross-country anchor: general optimism about science and technology is the strongest pooled predictor of favorable AI evaluation and recurs among the leading predictors in every national sample. Expert authority, education and information access, selected forms of trust, openness, and demographic position provide nationally distinctive patterns. Eleven value profiles formed without AI attitudes span 49.1% to 62.2% favorable evaluation. Most evaluative variation occurs within these profiles, making them useful contexts for identifying how the same values distinguish favorable from unfavorable evaluators in different social configurations. Institutional legitimacy, structural advantage, information connectedness, personal choice, redistribution, and openness differentiate evaluations in particular profiles. The same axis can relate differently to AI evaluation across profiles: secular reasoning has a significant positive association among secular moderate pluralists but a suggestive negative association among institution-trusting civic joiners. Together, the findings show that public receptivity to AI as technological change has a common predictive anchor but develops within plural configurations of resources, institutions, authority, openness, and social position. This distinction helps anticipate where generalized technological optimism is likely to travel and where AI deployment and governance will encounter context-specific sources of legitimacy or concern.

cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37196

How Much Can Best-of-N Help a World Action Model? Measuring Selectable Headroom and Realizing It in Closed Loop

Haojia Gao, Yue Cao, Yumin Liu, Haohua Que, Mingkai Liu, Guanqiu Guo, Zhuo Zou, Bokui Chen 等 9 位作者

原文摘要

World action models (WAMs) predict the visual consequences of the actions they generate, which makes test-time selection a natural way to improve a fixed policy: imagine the futures of candidate actions and execute the best one. The benefit of selection is bounded by the selectable headroom, how much better the best candidate truly is, but the standard estimate, which executes each candidate once and keeps the best outcome, conflates candidate quality with the randomness of everything that follows. We introduce a denoised counterfactual protocol, based on bitwise-reproducible branching, repeated continuations, held-out oracles, and common random numbers, that measures the headroom a selector can realize, and use its measurements to build a fail-gated selector. Across four WAMs, two benchmarks, over 100,000 branched rollouts, and pre-registered tests, we find that (i) the standard estimate overstates the selectable headroom of native samples: bounds from 17 continuations per candidate place its selectable share between 24% and 66% for three WAMs; (ii) structured action perturbations create up to 16 points of selectable headroom; and (iii) in both WAMs with action-conditioned imagination, imagined futures carry candidate-outcome information with no detectable loss relative to real futures, information that the value head of Cosmos Policy leaves unused. Deviating from the policy chunk only when a readout of the WAM predicts failure, the selector raises closed-loop task success from 76.9% to 81.6% on held-out episodes of training tasks, with the largest gain where the policy fails most often, and from 62.6% to 69.8% on unseen tasks.

cs.RO · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37195

Action-Value Calibration via Continuation Sharing for Long-Horizon Agentic Reinforcement Learning

Yingjian Chen, Lang Zhou, Zixin Zhao, Pingfan Li, Weishi Zheng, Zhilin Zhao

原文摘要

Reinforcement learning for long-horizon agents relies on feedback from sequences of interactions, making credit assignment to individual actions difficult. Existing methods such as GiGPO compare actions at shared states to compute relative advantages, but estimate each action's value from a single sampled continuation. The resulting local credit remains sensitive to decisions made later in the trajectory. To address this problem, we propose ConCal (Continuation Calibration), a recursive continuation-value estimator that incorporates continuation evidence already present in a rollout batch. ConCal matches visits from the same task by their incoming state-action-state transitions, combines shared continuation evidence with each visit's own transition estimate, and propagates calibrated values backward to refine earlier action-value estimates. This reduces dependence on individual sampled continuations and mitigates local credit distortions without additional rollouts. Held-out return diagnostics show lower error in within-group value differences and higher agreement with reference action orderings than estimates based on individual continuations. With Qwen2.5-1.5B-Instruct, ConCal improves success rates over GiGPO by 3.39 and 5.86 percentage points on ALFWorld and WebShop, respectively. Our code is available at https://github.com/Yingjian-Chen/ConCal.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37733

Selective Transfer Learning for Groundwater Level Anomaly Forecasting: Accuracy-Risk Trade-offs

Yaxuan Wu, Ali Mohammed Mansoor Alsahag, Seyed Sahand Mohammadi Ziabari

原文摘要

This work studies context-aware selective transfer learning for multi-well groundwater anomaly forecasting in the Netherlands. Source-domain pretraining can raise average accuracy but is not uniformly reliable: it degrades performance on a substantial fraction of heterogeneous wells. Context-Aware Selective Learning (CASL) uses calibration-trained, constrained contextual blending of frozen no-transfer and fixed-transfer parents. Global Convex Blend uses the same parents with one calibration-fitted weight per seed. The corrected task requires nine consecutive observed monthly inputs and an exact three-calendar-month target, without interpolation. Evaluation covers 457 wells and 13,718 test windows under five predefined seeds, with the four-cell maxsim0.60 source pool frozen using Always-TL validation RMSE alone. Fixed transfer harms 18.38-51.86% of wells. CASL has 0.424-1.084% lower RMSE than No TL, partially rescuing 97.53-99.50% and fully rescuing 23.46-43.78% of fixed-harmed wells. Partial rescue can arise structurally from convex blending and does not establish contextual superiority. Global Convex Blend protects more wells in four seeds, while CASL has slightly lower pooled RMSE in four. Neither dominates: the results support an accuracy-risk trade-off on the fixed split, not rolling deployment validity.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.28930

Amplified Pruning and Path Selectors for Deterministic Radio Gossiping

Qin Xin

原文摘要

We study deterministic gossiping in unknown strongly connected directed radio networks with $n$ vertices, $m$ arcs, and distinct identifiers in $[N]$, where $N=n^{\mathcal O(1)}$. Messages are unrestricted and collision detection is unavailable. Our neighborhood-clearing procedure reuses an elected receiver to secure its entire closed in-neighborhood in $\mathcal O(n\log^2n\log\log n)$ rounds. Charging each distinct closed neighborhood once yields $\mathcal O(m\log^2n\log\log n)$ rounds under an explicit degree-concentration condition, for every polynomial identifier range. A complementary adaptive-pruning procedure combines quadratic contraction with completion sensitive to the number of unsecured sources. If $a\ge1$ sources remain at completion entry, permutation selectors reduce the balanced completion budget by a factor of $\log^{2/3}(a+1)$ relative to interleaved path selectors. A geometric execution attains $\widetilde{\mathcal O}(k^2+nτ+\min\{u^2,(nu)^{2/3}\})$ for a path cover of scale $k$, weight $τ$, and $u$ exceptions. For directed graphs with common in- and out-degree $Δ$, the portfolio achieves $\widetilde{\mathcal O}(\min\{n\sqrtΔ,n^2/Δ\})$. Every graph also admits $\widetilde{\mathcal O}(\min\{n^{4/3},N+(mn)^{3/5}\})$ rounds. Only $n,N$ are inputs; degrees, covers, and structural constants are used solely in the analysis. The unrestricted polynomial-identifier density extension remains open.

cs.DS · cs.CC · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.06928

When Do Pretrained Audio Representations Help Music Recommendation? A Study Across Ranking and Generative Interfaces

Qingrui Li, Haowei Lou, Chengkai Huang, Quan Z. Sheng, Lina Yao

原文摘要

Pretrained audio encoders are increasingly used to provide content representations for music recommendation, but their downstream value can change substantially with the recommendation interface through which they are used. We study this effect across six pretrained audio encoders and three representative settings: content-based retrieval, sequential recommendation, and Semantic-ID-based generative recommendation. Using matched random-feature and ID-only controls, we distinguish absolute recommendation performance from gains over content-free inputs. Across two music datasets and a full-catalog evaluation, music-pretrained and audio-text-aligned encoders are generally stronger when their pretrained geometry is used directly or converted into Semantic IDs, while these differences become much smaller after interaction-based adaptation in SASRec. We further examine how audio representations should be discretized for generative recommendation by varying residual-quantization width, depth, and retained layers. At epoch 10, depth one performs best at every tested width, while larger codebooks generally help at depth three; the best single-layer subset also outperforms the full three-layer identifier in every evaluated comparison. For CLAP-Music, the third-layer identifier ranks higher under both original and shuffled assignments, whereas the full three-layer identifier gains more from the original assignment. Better reconstruction likewise does not ensure better ranking. Overall, our results show that the utility of pretrained audio representations is interface-dependent and that Semantic-ID quality should be assessed by downstream ranking rather than representation fidelity alone.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37192

Tight Bounds for Randomized Generalized $k$-Server on Uniform Metrics

Junho Hwang

原文摘要

In the generalized $k$-server problem, each of $k$ servers moves in its own metric space, and a request $(r_1,\dots,r_k)$ is served once some server $i$ stands at the point $r_i$ of its space. We determine the randomized competitive ratio against an oblivious adversary when every space is a uniform metric. With unit distances the ratio is $Θ(k\log k)$: we give a $(k+1)\ln(2k)$-competitive algorithm and show that for large $k$ every algorithm has ratio at least $\frac{1}{20}k\ln k$, improving the bounds $O(k^2\log k)$ and $Ω(k)$ of Bienkowski, Jeż, and Schmidt. When server $i$ pays $w_i$ per move, the ratio is $\exp(Θ(k))$: we give a $20^k$-competitive algorithm, which also applies to weighted $k$-server on uniform metrics. This improves the $\exp(O(k^2))$ bound of Bijoy, Mondal, and Chiplunkar and matches the $Ω(2^k)$ lower bound of Ayyadevara and Chiplunkar up to the base of the exponent. Both algorithms follow normalized weights exactly, through couplings whose expected movement is controlled by the decrease of the logarithm of the total weight. The lower bound hides a random permutation among the solutions of random permutation constraints, which split into small, well-separated components, and then forbids one position to one server at a time.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37190

Acoustic Signature Optimisation for Bioinspired Flapping-Wing Micro Aerial Vehicles

Yi Lun Duh, Krispin C. V. Broers, Sophie F. Armanini

原文摘要

Flapping-wing micro air vehicles are prized for quiet flight, yet the few existing measurements show engineered wings to be 15-30 dB louder than the animals they imitate. This paper investigates two passive geometric approaches to reduce the acoustic signature of a flapping membrane wing, and applies these to an exemplary wing. A significant sound source in flapping wings is the impulsive click radiated at stroke reversal, when a slack membrane snaps between two curvatures. Our first noise-reduction approach optimises the wing's venation layout, based on an analytical model of the reversal click as a dynamic snap-through of the membrane. The optimised venation pattern was manufactured and resulted in a reduction of up to 8 dB during the reversal snap in experiments. During testing, the venation was found to be sensitive to orientation rather than thickness. Secondly, an additive trailing-edge fringe inspired by hummingbird feathers was shown to further reduce the broadband swoosh by 3-4 dB at no lift cost, matching a cut serration wing without removing lifting area.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37188

Negative Results for Reciprocity-Based Over-the-Air Split Learning Under Channel Aging: Stability, Alignment, and Geometry

Tianhao Guo, Xianzhong Li, Hao Luo

原文摘要

In reciprocity-based over-the-air split learning, channel aging rotates and attenuates the derivative signal returned to the transmitter. Seven case studies combine numerical forecasts, mechanism checks, and competing predictions. Near the correlation zero, an archived SGD comparison finds truncated inversion 0.000813 lower in cross-entropy than polar correction, with a paired 95% interval for the difference from -0.001853 to 0.000060, and a retained-mode quadratic proxy slightly favors truncation. Selecting the return port with the largest received power falls short of the predicted five-point alignment advantage over random selection at both tested spacings, gaining at most 0.97 points, while the local inverse relation between amplitude and phase gradient is supported. Seven specified interference-induced accuracy-collapse predictions are rejected, and independent zero-mean interference preserves the conditional mean under a fixed linear chain. Per-subcarrier correction and spherical-wavefront compensation do not deliver their predicted accuracy gains. Focusing leaves both methods near chance in a single-mode model and adds no observed gain in a model with a line-of-sight component plus scattering. A successful port assignment under nonsymmetric motion refutes an exact-symmetry requirement. The competing positioning-error prediction is supported. Gaussian rail jitter with a standard deviation of 0.383 wavelengths yields high terminal test accuracy, whereas a fixed bias of the same magnitude yields near-chance accuracy. These cases distinguish valid local physical relations from unsupported training forecasts through task support, noise injection, and update moments.

eess.SP · cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37186

VGIQA: Fine-Grained Image Quality Assessment with Visual Grounding Rewards

Weichang Wang, Liyu Chen, Shuyue Guan, Jie Hu, Fei Gao, Wei Li, Nannan Wang

原文摘要

Image quality assessment (IQA) aims to evaluate the perceptual visual quality of images. Recently, the rapid development of Multi-modal Large Language Models (MLLMs) has significantly advanced the IQA field. By integrating chain-of-thought (CoT) reasoning and reinforcement learning (RL), these models can generate more accurate and interpretable results while relying on less training data. However, existing MLLM-based methods are predominantly constrained to holistic, image-level evaluations and lack the capability to produce fine-grained, localized assessments, which substantially limits their practical applicability. To address this limitation, we propose VGIQA, a novel IQA model endowed with both local and global quality assessment capabilities. VGIQA is trained via a two-stage paradigm comprising a cold-start phase followed by reinforcement learning. Driven by carefully designed local quality assessment reward functions, our model exhibits exceptional image quality understanding on VGSR-2K, a new dataset we propose specifically for local quality evaluation, significantly outperforming existing open-source MLLMs such as Qwen2.5-VL-72B-Instruct and Qwen3-VL-32B-Instruct. Furthermore, the local quality evaluation task can effectively enhance the model's performance on the degradation perception task.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.30188

CalArena: A Large-Scale Post-Hoc Calibration Benchmark

Eugène Berta, David Holzmüller, Francis Bach, Michael I. Jordan

原文摘要

Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated. Post-hoc calibration provides a simple and widely used solution, but the large number of proposed methods, combined with small-scale and inconsistent evaluations, makes it difficult to determine which approaches are truly effective in practice. We introduce a large-scale, standardized benchmark for post-hoc calibration, covering nearly 2000 experiments across tabular and computer vision tasks, including binary, multiclass, and large-scale classification settings. Our benchmark aggregates predictions from a diverse set of classical models, modern deep learning architectures, and foundation models, and provides unified, reproducible implementations of dozens of calibration methods within a common evaluation framework. We argue that Post-Hoc Improvement (PHI) in proper scoring rules offers a principled alternative to traditional calibration error estimators for comparing post-hoc methods, capturing both calibration quality and potential degradation to the model's predictive performance. Using this framework, we conduct the most comprehensive empirical study of post-hoc calibration to date. Our results reveal consistent patterns across domains: smooth calibration functions outperform binning-based approaches, dedicated multiclass methods are essential in high-dimensional settings, and generic machine learning models are not competitive without calibration-specific design. To facilitate future research, we release all data, code, and evaluation tools, providing a plug-and-play benchmark for developing and comparing calibration methods.

cs.LG · cs.AI · stat.ML

查看论文
arXiv ↗PDF ↗