跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+86新增论文
+61其中 AI 相关
+14已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 10:40各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 11:06 — 2026-11-16 11:06(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:2026-11-16 01:34最近发现新增版本:2026-11-16 10:40库内论文最新更新时间:2026-11-13 16:48

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。

23,434 已收录论文19,641 AI 相关6,765 有修订112 HF 社区发现

浏览论文库

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 23,434 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

版本更新 · v2arXiv:2609.32499

Learning an Anchored Prompt Space for Continual Adaptation of Large Language Models

Rongguang Ye, Zhan Zhuang, Yichen Wu, Ming Tang, Kede Ma

原文摘要

Continually adapting large language models requires acquiring new knowledge while preserving previously learned capabilities. Although jointly adapting model parameters and task-specific soft prompts is promising, it has two key limitations: previously learned prompts may lose effectiveness as the model evolves, and relationships among prompts that could support cross-task transfer are not explicitly learned. We propose Learning an Anchored Prompt Space (LAPS), which preserves historical prompt effectiveness and learns relationships among task-specific soft prompts to facilitate positive transfer. Historical prompts are first aligned with the updated model through self-distillation. LAPS then constructs an anchored prompt space whose vertices correspond to learned task-specific soft prompts and whose intermediate geometry is shaped by learnable Bézier control prompts. Once this space is learned, LAPS identifies the best-performing prompt for each task on its validation set, allowing the selected prompt to draw on knowledge acquired from related tasks. Experiments on the TRACE benchmark across three Qwen3 model scales show that LAPS consistently outperforms existing distillation-based, prompt-based, and joint prompt-parameter adaptation methods, improving overall task performance while reducing forgetting.

cs.CL · cs.AI

版本更新 · v7arXiv:2508.20866

AVIATOR: Towards AI-Agentic Vulnerability Injection Workflow for High-Fidelity, Large-Scale Code Security Dataset

Amine Lbath, Massih-Reza Amini, Aurelien Delaitre, Vadim Okun

原文摘要

The increasing complexity of software systems and the sophistication of cyber-attacks have underscored the need for reliable automated software vulnerability detection. Data-driven approaches using deep learning models show promise but critically depend on the availability of large, accurately labeled datasets. Yet existing datasets either suffer from noisy labels, limited vulnerability coverage, or fail to reflect vulnerabilities as they occur in real-world software. This also limits large-scale benchmarking of such solutions. Automated vulnerability injection provides a way to address these limitations, but existing techniques remain limited in coverage, contextual fidelity, or injection success. In this paper, we present AVIATOR, the first AI-agentic vulnerability injection framework. AVIATOR decomposes vulnerability injection into a coordinated workflow of specialized AI agents, tool-based analysis, and iterative self-correction, explicitly mirroring expert reasoning. It integrates RAG and lightweight LoRA-based fine-tuning to produce realistic, category-specific vulnerabilities without relying on handcrafted patterns. Across three benchmarks, AVIATOR achieves high injection fidelity (91-95%) surpassing existing injection techniques in both accuracy and vulnerability coverage. When used for data augmentation to train deep learning-based vulnerability detection (DLVD) models, AVIATOR provides the strongest downstream gains in vulnerability detection. Across models and base datasets, AVIATOR improves average F1 scores by +22% over no augmentation, +25% over VGX, holding the prior best injection success rate, and +3% over VulScribeR, the prior state-of-the-art LLM-based injection model, with +7% higher recall and no precision loss. Its augmented data exhibits the lowest distributional distortion and scales efficiently with <2% syntax rejection at 4.3x lower cost than VulScribeR.

cs.CR · cs.AI

新论文 · v1arXiv:2610.37181

LitUbik: open-source software for human-led systematic reviews with traceable AI assistance

Adolphe J. Bequet, Sebastien Laurent, Baptiste Bouvier

原文摘要

LitUbik is an open-source, self-hosted tool for conducting systematic reviews, from the registered protocol to the PRISMA 2020 diagram. LitUbik covers calibrated search equations, automated searching, deduplication, blinded multi-reviewer screening, full-text retrieval, snowballing, appraisal, extraction and reporting, on one server or across disconnected instances. At each stage, optional AI assistance from commercial or local language models offers proposals that a named reviewer accepts or rejects. Every AI call is logged, so the AI-use disclosure is written from a record. A systematic review of 31 papers on review tools, conducted in LitUbik, compares it with existing tools and illustrates its use. LitUbik is distributed under AGPLv3.

cs.DL

新论文 · v1arXiv:2610.37179

Irreducibility Testing of Sparse Polynomials over Integers is NP-hard and Probabilistic Polynomial Time

Yichuan Cao, Xiao-Shan Gao, Qiao-Long Huang, Jiawei Nie

原文摘要

In this paper, we prove that irreducibility testing for sparse polynomials in $\mathbb{Z}[X]$ is coNP-hard under deterministic polynomial-time many-one reductions. That is, there exists no polynomial-time irreducibility test algorithm unless $\mathrm P=\mathrm{NP}$. We also provide an upper bound for this problem by demonstrating that the same irreducibility testing problem lies in $\mathsf{PP}\subseteq\mathsf{PSPACE}$; in other words, it can be solved in probabilistic polynomial time and, moreover, within polynomial space. The fact that $\mathsf{SparseIrred}_{\mathbb{Z}}\in\mathsf{PP}$ relies on the quasi-Riemann hypothesis result of Cureton--Thorner and on the uniform effective prime-ideal bound by Frei--Sofos--Widmer just posted recently.

cs.CC

版本更新 · v2arXiv:2609.30027

Synthetic Hospital: An Open, Verifiable, Physician-Validated Longitudinal EHR Benchmark

Christine Park, Valerie Chen, Tim Dettmers

原文摘要

Frontier language models are rarely used in clinical workflows because the realistic, longitudinal benchmarks needed to develop them are scarce. Real electronic health record (EHR) data cannot be openly shared due to privacy, ethics or data use issues and it does not contain verifiable ground truth since the chart records only reflect what clinicians documented. We introduce Synthetic Hospital, an open, fully synthetic, fact-grounded longitudinal EHR benchmark that resolves the open sharing and verifiable ground truth barriers. Built entirely from public medical-education material with no protected health information, it comprises 1,268 longitudinal patients and 5,602 encounters, where every diagnosis, finding, and temporal relation is grounded in standard ontologies (ICD-10-CM, SNOMED CT, LOINC) and with a complete provenance chain back to its source medical education material. Synthetic Hospital is served through a simulated hospital record system that mirrors real EHR infrastructure (standard interoperability APIs, role-based access and function-calling interface). In a blinded review, physicians distinguished its records from real patient charts at near-chance rates (53%). Across 10 frontier and open models, none approaches ceiling: the best model reconstructs a patient's longitudinal problem list with a severity-weighted F1 of 0.73, level with the mean of seven physicians on a matched subset but well below the best of them (0.89), and misses roughly half of clinically relevant findings when summarizing a chart. Overall, these results highlight that Synthetic Hospital is a difficult and realistic test of clinical AI performance.

cs.AI · cs.DB

新论文 · v1arXiv:2610.37178

INTR++: INterpretable TRansformer with better Accuracy, Interpretability, and Adaptability

Dipanjyoti Paul, Arpita Chowdhury, Maneet Chatterjee, Daichi Kitaguchi, Tanya Berger-Wolf, Tetsuya Sakurai, Wei-Lun Chao

原文摘要

Interpretable Transformers often perform well in domain specific settings but lose effectiveness beyond that. Achieving ViT-like broad applicability requires models with consistent performance across domains. Recent works on Interpretable Transformers, INTR and Prompt-CAM, were developed keeping domain adaptability in mind. Prompt-CAM leverages learnable prompts to promote adaptability. However, these prompts are fixed in nature and therefore struggle to adapt to domains with substantial variation in input image characteristics, resulting in reduced interpretability. To address this limitation, we propose INTR++, which extends Prompt-CAM by incorporating a lightweight Prompt Adapter Module (PAM). PAM enables prompts to be adaptive by enriching them with domain-specific knowledge, thereby ensuring consistent interpretability across diverse domains including those with varying image characteristics such as medical imaging, micro-scopic imaging, and remote sensing imagery. INTR++ retains the standard architecture and end-to-end learning of Interpretable Transformer based models, while adding only a small number of additional parameters compared to Prompt-CAM. We demonstrate that INTR++ delivers consistent improvements in all aspects across domains like animals, plants, medical imaging, microscopic imaging, remote sensing imagery and object-centric data.

cs.CV

新论文 · v1arXiv:2610.37175HF 社区推荐

MLE-World: Predicting Machine Learning Experiment Outcomes with a Learned World Model

Brian Ko, Han Wang, Hejia Geng, Li Erran Li, Sherry Yang

原文摘要

AI research agents can propose, execute, and improve programs that solve machine learning tasks. However, executing each candidate program requires training and evaluating ML models, limiting how many candidates an agent can explore at each step. We introduce MLE-World, a world model finetuned from Qwen3.5-4B that predicts a program's terminal output (error traces, training logs, and validation scores) from its code and data description without executing it, together with a confidence score estimating the prediction's correctness. Because a prediction costs one inference call rather than a training run, MLE-World makes test time scaling (TTS) affordable for these agents. We build five TTS policies, guided by MLE-World, that compare several candidates per step by their predicted outputs: Sequential revision, Best-of-N, Pairwise judging, Fusion, and a UCB style rule that also adds an exploration bonus from this confidence score. Since predictions can be wrong, we run a candidate for real only when its confidence score is low. On 17 MLE-bench Lite tasks, MLE-World matches the real terminal output on 77.9% of held out programs, versus 41.1% for much larger prompted models. MLE-World guided TTS achieves up to 22.1% higher observed mean performance than the agent without a world model, with less real execution. Project webpage: https://mle-world.github.io/.

cs.LG · cs.AI

版本更新 · v2arXiv:2605.16600

The Geometry of Learning: Read-Write Asymmetry Across Training

Valeria Ruscio, Keiran Thompson

原文摘要

Pretraining and alignment update the same transformer weights, and we ask in which directions each stage changes them. The residual stream gives every matrix a shared coordinate system, in which a weight change can be compared with the principal subspace of the activations the matrix reads and with the prediction subspace of the unembedding. In this frame, alignment updates to the query and key matrices are enriched in the principal input subspace, while its updates to the output matrices are close to random relative to the prediction subspace, and the same signature appears in late pretraining and under every objective we apply to one checkpoint, so it is a property of the training stage rather than of the objective. The gradient of a linear map is a sum of outer products $δ_t a_t^\top$, and the residual stream enters this product through the activation $a_t$ for matrices that read from it and through the upstream gradient $δ_t$ for matrices that write into it. Read gradients therefore inherit the spectrum of the activations, which is the same under every objective, while write gradients inherit the geometry of the upstream gradients, which point into the prediction subspace only early in pretraining, when the output matrices acquire their prediction geometry. The raw read gradient follows the activation spectrum, the optimiser attenuates the concentration it inherits, and cancellation between tokens sets the scale of the update but not its direction. A write direction derived from the unembedding still changes predictions after alignment, and adaptation restricted to any single group of matrices remains effective, so the signature describes where training places its updates, not which matrices can carry them.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2610.37174

Deep Holes and Aperture: Sign Laws for the Empirical Correlation of Lattice-Sampled Random Wave Fields

Tianhao Guo, Hao Luo, Xianzhong Li, Yuzhi Yang

原文摘要

A Gaussian random wave field is sampled on a lattice within a bounded aperture. After displacement, re-indexing leaves a residual in the Voronoi cell. We study whether the empirical lag correlation has positive real part throughout the cell. For each realization in a single-output reciprocal link with noiseless over-the-air return, this is equivalent to the negative returned gradient being a descent direction for all residuals and differentiable losses with nonzero error signals. Return noise is treated exactly. For isotropic fields, ball-shaped apertures, unshifted lattice points, and dilations approaching the critical covering radius, every minimizer is a deep hole except with exponentially small probability. A Gaussian vector on the deep holes determines the limiting failure probability, with explicit covariance and lattice-independent limiting normalization. Square, hexagonal, simple cubic, and body-centered cubic lattices have two, three, four, and twelve sign classes. At fixed target failure probabilities below the critical limiting value, this covariance determines the exact leading aperture constant. When the margin and target failure probability vanish jointly, that constant is common to lattice shapes within each dimension. A cubic correction yields vanishing relative tail error in a moderate-deviation regime. A non-asymptotic two-sided aperture law has explicit constants. With a Rayleigh-faded specular path and positive diffuse margin, a failure floor occurs at every positive path power exactly when the cosine of its phase change is negative somewhere in the cell. The floor vanishes for all directions exactly when the covering radius is at most a quarter wavelength.

cs.IT · eess.SP

新论文 · v1arXiv:2610.37172

DomeGS: Perceptually Consistent Background Completion for Unbounded 3D Gaussian Splatting in Virtual Reality

Anastasiya Pechko, Agata Szymańska, Piotr Borycki, Joanna Szelewska, Michał Mnich, Sławomir Tadeja, Przemysław Spurek

原文摘要

The growing need for high-quality 3D content remains among the most prevalent challenges in virtual reality (VR). Recently, novel view synthesis techniques have enabled rapid content creation, with 3D Gaussian Splatting (3DGS) emerging as one of the most promising methods for generating high-fidelity 3D scenes. However, using 3DGS to reconstruct unbounded outdoor scenes can leave horizons incomplete due to missing data or a lack of distant geometric constraints. Such incompleteness can break immersion, compromising VR's core characteristic. A typical workaround in traditional VR systems is a textured cube (skybox) or sphere (skydome) surrounding the environment to create the illusion of a distant background. However, these approaches struggle to blend seamlessly with the reconstructed 3DGS geometry. To address these issues, we introduce the DomeGS framework, which incorporates the skydome concept not as a flat background shell, but as a part of the reconstructed Gaussian Splatting 3D scene. By integrating the horizon and sky into the 3DGS representation, our method provides a unified, scene-consistent environment bridging foregrounds and backgrounds for greater realism. Experimental evaluation with N=36 users demonstrates that DomeGS significantly increases spatial presence (p=0.042) and realism (p=0.042) compared to the skybox baseline.

cs.GR

新论文 · v1arXiv:2610.37170

From 12 to 200 Demonstrations: How ACT, Diffusion Policy, SmolVLA and $π_{0.5}$ Scale on a Low-Cost Arm

Simon Cowling

原文摘要

We trained four widely used imitation-learning policies, ACT, Diffusion Policy, SmolVLA and $π_{0.5}$, on nested subsets of 12, 25, 50, 100 and 200 teleoperated demonstrations of one pick-and-place task with distractor objects, using one fixed training recipe per policy. Every trained model was then run on a physical SO-101 arm on a fixed set of object placements: 1,340 scored episodes in 126 blocks. ACT, trained from scratch, rose from 1 success in 40 episodes at 12 demonstrations to 37 in 40 at 100. $π_{0.5}$ with its action expert fine-tuned was the best policy when data was scarce (16 of 40 at 12 demonstrations, 28 of 40 at 25) and then stayed near 70%; from 100 demonstrations ACT was ahead, by a margin this study does not fully resolve. SmolVLA and Diffusion Policy peaked near 50%, and both were affected by a failure to start: SmolVLA's arm never started moving in 47% of episodes, and Diffusion Policy hardly ever started until an idle lead-in was trimmed from the demonstrations. For $π_{0.5}$ the fine-tuning recipe mattered more than the amount of data: low-rank adaptation succeeded in 4 of 110 episodes, against 130 of 200 for action-expert fine-tuning. From the joint and camera recordings we place every episode on a four-stage ladder (started, reached the ball, carried it, delivered it) and show that for ACT more data moves failures from reaching, to grasping, to none, while the failures $π_{0.5}$ retains are in grasping. We also measure how weak a ten-episode block is as a measurement (the same checkpoint tested twice differs by 2 successes in 10 on average), separate seed-to-seed variation from that noise, and audit the human scoring against the recordings. Training length was fixed within each recipe, so the amount of data and the number of times it was seen change together; we state which conclusions survive that confound and which do not.

cs.RO

新论文 · v1arXiv:2610.37169

Rènyi-Regularized Flow-Based Variational Inference for Bayesian Calibration

Exaucè Luweh Adjim Ngarti, Élise Arnaud, Léo Nicoletti, Victor Trappler, Arthur Vidard

原文摘要

Variational inference with normalizing flows provides a flexible posterior approximation for Bayesian model calibration, but struggles when the posterior has several modes separated by regions of low probability mass. We study this behavior in a two-parameter twin experiment and regularize the variational objective. Under Gaussian observation errors and a Gaussian prior, the corresponding minimization objective is the expected Tikhonov calibration objective minus the differential entropy of the approximating distribution. However, the expected Tikhonov term favors concentration near one of the modes, while entropy maximization does not guarantee multimodality. We introduce a regularization term based on Rényi divergence that encourages the approximate posterior to cover the prior support. In the connected bimodal case, a flow approximation represents both modes; in the case with well-separated modes, the flow and Gaussian mixture frequently miss one mode. The introduced regularization reduces the near-collapse fraction from 50% to 25%. While the regularization improves mode coverage in this experiment, it changes the Bayesian variational objective, introduces a trade-off in approximation accuracy, and does not provide a general solution to mode collapse.

cs.AI · stat.ML

版本更新 · v2arXiv:2610.34717

VLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware

Borui Xu, Hongshi Tan, Wenqi Jiang, Bingsheng He, Ming Wu, Jason Zeng, Michael Heinrich

原文摘要

Vision-language-action (VLA) models increasingly run on edge devices aboard robots, where inference latency constrains closed-loop robot control. However, it remains unclear how to design VLA models, their inference software and edge hardware so that robots can run VLA inference in real time. Most VLA models report only task success, while prior studies cover limited action-generation strategies, divide inference into at most three stages, and lack comparisons of inference optimizations on the same models. Therefore, we introduce VLA-HWBench, a benchmark that measures 18 open VLA models on NVIDIA Jetson AGX Thor and AMD Ryzen AI Max+ PRO 395, with a seven-stage inference breakdown. Our study reveals three insights. First, action-generation strategy matters more than model size. It dominates 14 of 19 Jetson configurations, latency varies by $82\times$ on Jetson and $157\times$ on AMD, and parameter count explains at most 15% of latency variance. Models that generate long action chunks in a few flow-matching steps keep up with control, whereas token-by-token decoding does not. Second, kernel fusion with 4-bit weights helps most, running $π_{0.5}$ and GR00T N1.7 2.6-2.9$\times$ faster than PyTorch with torch.compile, but it exists for only these two models and only on the Jetson. Optimization also moves the time to the stages it shortens least, as CPU preprocessing grows from 12% to 39% of the GR00T N1.7 call. Third, after optimization, memory bandwidth limits only the stages that process few tokens on the Jetson, such as the denoising steps, whereas software limits all other stages, from unfused kernels to serial preprocessing on the host CPU. Overall, low-latency edge VLAs should use few action-generation iterations, inference software should extend kernel fusion and low-bit weights to more models and platforms, and edge hardware needs high memory bandwidth and a fast host CPU.

cs.RO · cs.AI

新论文 · v1arXiv:2610.37162

Coverage Under Contradiction: A Benchmark for Negation-Aware Retrieval

Pasha Abrishamchian, Eugene Yang, Andrew Yates, Nazli Goharian, Ophir Frieder

原文摘要

Coverage-evaluation benchmarks quantify whether retrieved evidence covers the different pieces of information needed to satisfy an information need. Existing benchmarks mostly consider factual claims that may already be known to pretrained retrieval components, leaving open whether retrievers find corpus evidence when it contradicts those priors. We study how retrievers behave when their parametric knowledge and the information in a corpus disagree. To do so, we develop a process to augment a nugget-based coverage benchmark with controlled contradictions. For each nugget, we create a negated counterpart and edit its supporting documents to support that negation while preserving the context. Applying this process to CoverageBench, a benchmark measuring information coverage, we create CoverageBench-Negate, spanning six datasets and roughly 63,000 original-edited evidence pairs (one per nugget-document link). We attach rich construction metadata to every pair and additionally provide out-of-family LLM judgments over all pairs and a human audit of a sample. In baseline experiments, BM25 separates original from edited near-twin evidence substantially better than dense retrievers (Qwen3 and Jina), which stay near chance. We release the benchmark on Hugging Face Datasets (nuggets, documents, pairs) together with the construction materials, including the prompts used to create it.

cs.IR · cs.CL