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

+2新增论文
+2其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-12 21:36 · 全站最近入库：2026-11-12 06:37各信源进度 →

统计口径与数据新鲜度

统计 2026-11-11 22:20 — 2026-11-12 22:20（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-12 21:36最近发现新增版本：2026-11-12 06:37库内论文最新更新时间：2026-11-11 08:00

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。

21,675 已收录论文18,323 AI 相关6,056 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 12,277 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-12 21:30（北京时间）
版本更新 · v2arXiv:2605.14786

Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces

William Lugoloobi, Samuele Marro, Jabez Magomere, Joss Wright, Chris Russell

原文摘要

As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model powers an agent? Doing so would represent a significant security risk, enabling targeted attacks tailored to known model vulnerabilities. Across 14 frontier LLMs and four web environments spanning information retrieval and shopping tasks, we show that an agent's actions and interaction timings, captured via a passive JavaScript tracker, are sufficient to identify the underlying model with up to 96\% F1 within a fixed harness. Although fingerprints are harness-specific, with cross-harness transfer falling to near chance, pooling traces across harnesses recovers model identification at 0.74 to 0.81 Macro-F1. We further show that strong classifiers can be trained from roughly one third of the available traces, and that identification improves steadily as more events are observed. Injecting randomised timing delays between actions substantially degrades classifier performance, but does not provide robust protection: a classifier retrained on delayed traces largely recovers performance. We release our code and a labelled corpus of agent traces at https://github.com/KabakaWilliam/known_actions.

cs.CR · cs.AI · cs.HC · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14196

Joint Quantization and Dynamic Partitioning for Context-Aware Edge Vision Transformers

Zhu Jiaqi, Jain Prakriti, Katare Dewant, Kumar Saurabh

原文摘要

Deploying vision transformer models across connected and automated vehicles (CAVs) requires joint management of computation and Vehicle-to-Vehicle (V2V) communication. Static split-inference methods use fixed partition points and cannot adapt to time-varying link bandwidth, processing load, and concurrent multi-stream traffic. This paper proposes an edge orchestration framework that jointly selects model partition points, per-layer quantization bitwidths, and execution placement across heterogeneous vehicular compute nodes. The joint partitioning and mixed-precision allocation problem is formulated as a Mixed-Integer Linear Program (MILP) that minimizes compute and communication energy subject to end-to-end latency and task-quality constraints. The framework is evaluated on Jetson Orin Nano (8~GB), Jetson Orin NX (16~GB), and Jetson AGX Orin (32~GB) nodes using OPV2V-driven multi-stream workloads with $K \in \{2,4,6,8\}$. Across the evaluated configurations, the proposed formulation reduces V2V communication energy by $33.3$--$36.0\%$ relative to a Uniform INT8 split. At $K=8$, end-to-end task completion latency is reduced by $34.0\%$ on the Orin Nano and $33.1\%$ on the Orin NX relative to the same baseline, while limiting the reduction in 3D detection accuracy to $3.1$--$4.1$ percentage points in $\mathrm{mAP}_{50}$ relative to FP16 execution.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14182

Quantum-Assisted Counterfactual Regret Minimization for Bounded-Payoff Imperfect-Information Games

Gabriel Maresch, Erik Schulze, Jnan Yalla

原文摘要

Imperfect-information games with a graded-reward structure present significant computational challenges for equilibrium computation, since the payoff expectations must be estimated across exponentially large strategy spaces. Counterfactual Regret Minimization over the years has proven effective for approximating Nash equilibria, but Monte Carlo variants create a large overhead of sampling costs when the counterfactual values are estimated from sampled game-tree trajectories. We propose a novel Quantum-Assisted Counterfactual Regret Minimization, a framework that uses Quantum Amplitude Estimation to reduce the computational complexity of the regret updates in bounded-payoff imperfect-information games, while preserving the convergence of its classical counterpart. We give a theoretical analysis of the resulting exploitability bound, discuss NISQ-compatible amplitude-estimation variants, the structure of their resource requirements, and outline what is needed to validate the potential advantage empirically.

quant-ph · cs.ET · cs.GT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.08577

Meituan-Robotics-0: A Vision-Language-Action Foundation Model for Desktop Manipulation

Meituan Robotics Team, Caicheng Wang, Chen Zhao, Chengpeng Jin, Duo Xu, Fengjiao Chen, Guanglu Wan, Heqing Yang 等 38 位作者

原文摘要

We present Meituan-Robotics-0 (MR0), a vision-language-action foundation model and embodied-agent system for stationary-base desktop manipulation. MR0 combines 147 million vision-language samples with 15,060 hours of curated robot trajectories spanning 12 embodiments. A three-stage training recipe aligns multimodal representations with robot behavior through discrete action-token pre-training, transfers these priors to continuous cross-embodiment control through flow-matching mid-training, and adapts the policy through real-world post-training. We introduce Rollback, which pairs replaced policy segments with human corrections to provide positive and negative supervision for CFG-DAgger without value learning or advantage labeling. A unified end-effector interface supports heterogeneous embodiments, while asynchronous action-chunk merging maintains smooth execution under variable inference latency. An event-driven agent maintains persistent task events and reassesses plans when progress or feasibility changes, enabling cross-task retrieval and conditional task resumption. MR0 achieves 93.6% success on RoboTwin 2.0 and ranks fifth in the RoboDojo VLA track. Under matched HG-DAgger post-training, MR0 achieves higher average success rate and progress score than $π_{0.5}$ across three real-robot tasks. On Ethernet insertion, CFG-DAgger trained with Rollback data reaches 70% success and a progress score of 0.90. Qualitative agent deployments demonstrate cross-task event retrieval and recovery from temporarily unsatisfied task conditions.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14168

Representational Atoms in Neural Networks

Chenhui Hu, Pengfei Cao, Kang Liu, Jun Zhao

原文摘要

Understanding the internal representations of neural networks and characterizing their relationship with human conceptual structure are two critical questions for elucidating model mechanisms. The former reveals how learned knowledge is organized in internal representations, whereas the latter provides a basis for interpreting these representations through human conceptual structure. Here, we formally define fundamental representational units (FRUs) and establish two evaluation criteria: fidelity and stability. We further prove that threshold-activated sparse autoencoders (TSAEs) can identify FRUs with high fidelity and stability under appropriate conditions, and validate this result through large-scale experiments. Further analyses reveal that FRUs with higher stability exhibit greater monosemanticity and can be composed across layers to recover semantic organization corresponding to human conceptual structure. These results provide a unified framework for defining, evaluating and identifying FRUs in neural networks, and establish a foundation for characterizing the relationship between neural network representations and human conceptual structure.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14164

An Empirical Study on CVE-based Vulnerabilities Propagation from one System to another System (IntraProject vs InterProject)

Junaid Akram, Ali Hassan, Danish Vasan

原文摘要

Vulnerabilities in applications, including browsers, media players, online services and document readers, etc. are often exploited and cause a serious damage. The vulnerabilities could exist in your system maybe because of some coding errors, design oversights, outdated software, AI generated codes or maybe transferred from another system during development (e.g., code clones). The propagation of software vulnerabilities is a critical concern in cybersecurity. This study examines the root cause problem of vulnerabilities propagation with experiments. We analyzed the propagation of CVE (Common Vulnerabilities and Exposures) based vulnerabilities within and between different software projects (IntraProject vs. InterProject). We performed several experiments on CVE based vulnerability dataset (retrieved from NVD source) by using our vulnerability detection tool (SQVDT). In the results, we discovered similar patterns of vulnerable code in several very famous recently used software, including latest version of Linux, Android operating systems, and in thousands of open source projects available on GitHub. We found several very high severity level (CVSS) vulnerabilities that propagated from one system to another system, just because of copy/paste (reuse) the code. Furthermore, we performed an empirical evaluation and verification of these vulnerable patterns that propagated to other systems by also considering the frequency of their propagation. Finlay, we recommended the impact of these vulnerabilities propagation on the interconnected systems.

cs.CR · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14158

Neural network scaling and generalization for 3D strain fields in heterogeneous materials

Lucas Fourel, Paul Devianne, Marine Debouvry, Tristan Destruhaut, Russell Gunn, Ashwini Gupta, Lori Graham-Brady, Jean-François Molinari

原文摘要

Computational homogenization and coupled multiscale simulations of heterogeneous materials require repeated solution of mechanical fields on Representative Volume Elements, which becomes prohibitively expensive for high-resolution three-dimensional microstructures. Machine-learning surrogates can accelerate these computations, yet most existing approaches predict fields for fixed macroscopic loadings and provide limited guidance on how to scale network architectures for high-resolution 3D tensor-field prediction. This work presents a U-Net surrogate trained to predict the full 36-component strain localization tensor field in voxelized concrete mesostructures at resolutions up to $256^3$. Training localization tensors are generated with an FFT-based linear elastic solver, and an extensive hyperparameter optimization is performed to derive scaling rules and an accuracy-speed trade-off analysis. The results show that only network width and depth need to be scaled with problem complexity, while several conventional U-Net design choices, such as doubling channels after downsampling, are suboptimal for this problem. The final neural network achieves a Mean Absolute Error of 1.118% on both the validation and the held-out test sets, and an inference speedup of approximately 8.7x over the FFT-based solver on an Nvidia H100 GPU. Generalization experiments reveal transfer across aggregate volume fractions and highlight the importance of training on diverse morphologies. To safeguard reliability, a Maximum Mean Discrepancy metric computed on internal feature maps is proposed for detecting out-of-distribution microstructures without costly reference computations.

physics.comp-ph · cs.CE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.05156

Temporal Cliques Admit Linear Spanners

Julia Baligacs

原文摘要

A temporal graph is a graph in which every edge carries a non-empty set of time labels, and it is temporally connected if for every two vertices $u$ and $v$, there exists a $u$-$v$-path with non-decreasing time labels. A spanner is a subset of its edges preserving temporal connectivity. Unlike static graphs, temporally connected graphs need not admit sparse spanners; nonetheless, minimizing spanner size is a central and widely studied problem. A particularly intriguing question is whether temporal cliques admit spanners of linear size. Despite considerable effort over the past years, the best known upper bound remained $O(n \log n)$. We finally resolve this question, proving that every temporal clique on $n$ vertices admits a spanner of size $7n$. Moreover, such a spanner can be computed in polynomial time.

cs.DM · math.CO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.37105

Text Generation in Low-Resource Languages Using Human-Curated Vocabularies

Michael Christlambert Sinanta, Muhammad Dehan Al Kautsar, Amanda Nurul Izzah, Thanh-Nhi Nguyen, Phan Phuong Mai Chau, Zheng Wei Lim, Fajri Koto

原文摘要

Synthetic text generation offers a promising approach to alleviating data scarcity in low-resource languages. However, its effectiveness is inherently limited for languages that are scarcely represented, or entirely absent, in an LLM's pretraining data. At the same time, many such languages have human-curated vocabularies that provide rich lexical and semantic information, often accompanied by grammatical information such as part-of-speech labels. In this work, we ask whether LLMs can leverage these resources to generate coherent text in extremely low-resource and unseen languages. We introduce a framework that combines human-curated vocabularies with a small number of human-written exemplars that provide syntactic signals, while sampling candidate words according to a Zipfian distribution. Across languages with varying levels of resource availability, we evaluate the generated text using lexical diversity, off-target ratio, and human judgments of fluency. Our results show that reasoning-enabled LLMs can generate fluent text even in extremely low-resource languages, with particularly strong results at the sentence level and promising performance at the paragraph level. Our findings highlight a practical pathway for bootstrapping synthetic data in low-resource languages, expanding the amount of usable text even when existing digital resources are extremely limited. Our source code is available at https://github.com/michaelsinanta/vocab2text.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.19557

Density-Ratio Losses for Post-Hoc Learning to Defer

Alexander Soen, Ragnar Thobaben, Joakim Jaldén, Richard Nock

原文摘要

We study post-hoc Learning to Defer (L2D) through the lens of ideal distributions: divergence-regularized reweightings of the data distribution under which a model attains low task loss. We define deferral via the density-ratio between a model's and an expert's ideals. Using the reduction from density-ratio estimation to class-probability estimation, we derive the DR CPE losses for post-hoc L2D scorers. Deferral decisions are then made by thresholding the scorer. For KL-based ideal distributions, our deferral rule recovers Chow's rule under the original distribution and a connection to an expert-tilted Bayes posterior---which incorporates the expert's performance---depending on if the ideal distributions are marginal or joint distributions. This leads to two variants of the DR CPE losses, with the joint variant being computationally convenient in practice. We establish consistency properties of the joint DR CPE losses when considering the zero-one task loss and strongly proper composite CPE losses. Experimentally, our approach is competitive compared to common baselines and is more robust across dataset settings. More broadly, our results cast post-hoc L2D as density-ratio estimation between ideal distributions, bridging Chow-style rules, expert comparison, and elucidating connections to related learning settings including anomaly detection.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14136

HaiRuo: Forecasting Ocean Eddies as Fields and Objects with a Satellite-Altimetry Foundation Model

Xukun Qin, Haochen Sun, Yuyang Tian, Ge Chen

原文摘要

Mesoscale eddies carry most of the ocean's kinetic energy and move heat, salt and nutrients across basins, yet where an eddy will be two weeks ahead is still read off ocean models with post-hoc tracking heuristics. We introduce HaiRuo, which forecasts eddies as fields and as objects at once: from 30 days of satellite sea-level maps, one forward pass returns 15 days of sea level and geostrophic velocity, daily eddy masks and the trajectory of every eddy alive today. HaiRuo pairs two components with a clear division of labour: (1) HaiRuo-1B, an open-weight 1.05-billion-parameter foundation model pretrained without labels on 24 years of global satellite-altimetry observations, which supplies the 15-day physical fields and masks (+0.14 field skill and +1.1 mIoU points under the same decoder) and further lowers 15-day centre error by 1.2 km frozen (1.35 km over training from scratch); and (2) XuanJi, a Lagrangian object decoder that samples the evolving forecast in each eddy's co-moving polar frame and refines the 15-day path across three look-ahead rounds, removing 2.5 km on HaiRuo-1B (2.9 km with joint fine-tuning) and 2.5-3.3 km via its object attention across six published backbones. Under one pre-registered global evaluation over the whole ocean, HaiRuo improves on fourteen methods on every endpoint (25.2 vs. 30.6 km 15-day centre error, -18%), holding its margin outside the labelled regions and through both phases of the El Nino-Southern Oscillation (ENSO), while reproducing westward drift, 50-60 deg S eastward reversal and poleward cyclone-anticyclone deflection. Over ten days through one fixed tracker, HaiRuo's forecast field cuts the eddy-centre error of WenHai and XiHe by 37-43% (-2.8 km vs. day 0 while they degrade +4.3-8.7 km), and its object trajectories cut pipeline error by 77-78% globally. Open-weight checkpoints, code and project page: https://github.com/xkqin/HaiRuo

cs.LG · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14135

Sim(3)-TurboReg: Robust and Efficient Scale-Aware Registration via Tri-Scale Consistency

Zijun Zhou, Shaocheng Yan, Zhenjun Zhao, Yutong Hu, Ke Yang, Yingdong Gu, Pengcheng Shi, Jiayuan Li

原文摘要

Feed-forward 3D foundation models recover geometry at high fidelity, yet inference memory constraints keep them from processing long sequences natively. Current streaming systems work around this limit with sliding-window chunking, which introduces severe monocular scale ambiguity. Resolving this ambiguity requires Sim(3) registration that stays accurate and efficient under outlier contamination. We introduce Sim(3)-TurboReg, which reformulates the compatibility graph construction of TurboReg by replacing absolute distance constraints with a strict Tri-Scale Consistency (TSC) criterion. Our analysis shows that TSC suppresses both mismatching and coordinate-distortion outliers. We integrate the resulting solver into existing streaming systems and obtain high-fidelity, kilometer-scale reconstruction for feed-forward models. On controlled unknown-scale registration at 90% outliers, ours matches RANSAC accuracy with 92.5% lower median latency. In DA3-Streaming on KITTI, ours improves mean ATE RMSE by 22.2% and reduces mean end-to-end time by 16.6%. Code: https://github.com/ivan-zzj/Sim3-TurboReg

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02536

FORGE: Fault-Oriented Rework Code Generation for Executable Interlocking Assembly

Fuqiang Wang, Jiahao Fu, Ren Hefeng, Yining Qian, Chuanting Zhang, Cheng Tan, Yuwen Liu, Jingxuan Wei

原文摘要

Large language models have demonstrated strong capabilities in structured reasoning and code generation, yet identifying an assembly fault does not guarantee the ability to generate executable rework programs. In interlocking assemblies, a locally plausible repair program may violate blocking dependencies, omit required recovery operations, or terminate in an incorrect configuration. We identify this challenge as fault-conditioned executable rework generation, where models must jointly reason about structural failures and generate programs that restore constrained assembly states. To benchmark this capability, we introduce FORGE-Bench, containing 4,000 tasks across 26 interlocking assemblies with five assemblies held out for evaluating generalization to unseen structures. We further propose FORGE (Fault-Oriented Rework Code Generation for Executable Interlocking Assembly), a structured state-to-program framework that decomposes rework generation into Rework Structuring and Action Grounding. Rework Structuring captures fault-induced recovery dependencies, while Action Grounding maps these dependencies into state-conditioned executable actions. Experiments show that locally reasonable repair code is insufficient for reliable assembly recovery, and that connecting structural recovery reasoning with executable action realization is essential for verified target restoration.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14124

CroCoMAE: Cross-modal self-supervised collaborative representation learning for SAR-optical remote sensing data

Vito Recchia, Giuseppe Guarino, Cássio Fraga Dantas, Giuseppina Andresini, Annalisa Appice, Dino Ienco

原文摘要

Remote sensing increasingly captures the Earth's surface through complementary sensors such as SAR and optical, yet ground-truth annotations remain scarce, limiting supervised approaches. Self-supervised learning (SSL) addresses the label scarcity, and cross-modal SSL further exploits the complementarity between co-located sensors, but existing cross-modal frameworks align modalities mostly through global image-level representations or treat them as largely redundant, leaving their fine-grained complementary structure underexploited. We propose CroCoMAE, a cross-modal SSL framework for SAR-optical remote sensing that unifies contrastive learning and masked image modeling within a ViT-based architecture, operating at two complementary levels. At the image level, an intra-modality contrastive loss on the class token yields globally discriminative, augmentation-invariant representations. At the patch level, masked image modeling drives fine-grained per-modality representations, while a cross-modal contrastive objective aligns a shared subspace across SAR and optical patch tokens, leaving the complementary subspace unconstrained to retain modality-specific information. On two SAR-optical benchmarks covering scene classification and semantic segmentation, CroCoMAE improves over uni-modal SSL baselines and outperforms state-of-the-art cross-modal frameworks in most configurations, with gains in both single-modality and multi-modal evaluation across varying label regimes and the largest improvements on semantic segmentation.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.12497

Allocating Human Oversight in AI-Enabled Analytics

Zikun Ye, Jiameng Lyu, Rui Tao

原文摘要

Artificial intelligence provides low-cost predictions for many analytics tasks, but their reliability and the value of another human label vary across tasks. We study how to allocate a shared human-validation budget when task-level uncertainty is unknown and each acquired label informs both estimation and subsequent allocation. For known difficulty levels, the benchmark follows a cost-adjusted Neyman rule that accounts for task importance and label cost. Within our Tuned Rectification-Difficulty framework, we develop an upper-confidence-bound policy that jointly learns the correction coefficients of tuned prediction-powered inference and the resulting difficulties from paired human labels and predictions, and establish an allocation-regret guarantee for the confidence-radius policy. In synthetic experiments and a real digital-twin survey with 68 tasks and over 2,000 respondents, our method closes most of the gap to the oracle on the allocation objective. It matches the estimation error of uniform allocation with up to 22.7% and 4.5% fewer human labels, respectively. The same allocation structure extends beyond scalar means to vector-valued decision models, including regression and choice/conjoint estimation, by replacing the scalar residual variance with a scalarized sandwich covariance. The value of AI depends not only on model accuracy but also on the operational policy that targets human oversight where it matters most.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14083

Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models

Tomer Solberg

原文摘要

We present Sable, an argument system and single-GPU prover for the statement that a committed, integer-quantized transformer produced a given token sequence from a given prompt, bit for bit. Sable fixes an integer function F_O with no floating-point step, in which every rounding, normalization, softmax and sampling decision is determined by its inputs, and proves it with a constraint system whose relations provably never wrap modulo the 31-bit KoalaBear prime. The proof batches zerochecks and LogUp-GKR lookups into one sumcheck per domain, and commits to every witness tensor and weight in one multilinear commitment built from Reed-Solomon codes, BLAKE3 Merkle trees and a mixed-length BaseFold opening. The prover streams the model layer by layer on one GPU. On one NVIDIA RTX PRO 6000 Blackwell GPU, Sable proves all 64 layers of Qwen2.5-32B in 92.5 s for 4,096 tokens and 398 s for 16,384 tokens, and covers Qwen3-32B and the mixture-of-experts Qwen3-30B-A3B (4,096 tokens in 121.8 and 84.7 s). A proof costs 41 to 50 times the serving time, or 6.4 cents per 4,096-token request at public GPU prices, and 40 to 64 times less time per parameter and token than zkLLM. On WikiText-2, F_O's greedy token matches the BF16 model's at 86.3% of positions; on Qwen3, F_O is within 1.6 points of BF16 on MMLU and 1.7 points on GSM8K. A verifier with a compiled core checks a proof on one CPU core in 19 to 56 s. In the random-oracle model, the interactive proof has round-by-round soundness error 2^-103. The proof is not zero-knowledge, so the system targets open-weight models. Code: https://github.com/moonmath-ai/Sable

cs.CR · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.16382

Rotated Robustness: A Training-Free Defense against Bit-Flip Attacks on Large Language Models

Deng Liu, Song Chen

原文摘要

Bit-flip corruption of quantized weights poses a serious reliability threat to Large Language Models (LLMs), as even a small number of weight faults can trigger catastrophic model degradation. We show that such failures can be strongly amplified when corrupted weights are coupled to high-sensitivity activation channels. Based on this observation, we propose Rotated Robustness (RoR), a training-free sensitivity-aware hierarchical rotation that applies matched orthogonal transformations to activations and weights, redistributing sensitive channel contributions across feature dimensions while preserving the underlying linear mapping in exact arithmetic. Across eight evaluated LLMs, RoR matches or exceeds all compared methods in the number of cumulative PBS flips sustained before PPL exceeds 100 within the 100-flip evaluation horizon. Under BER-based random bit-flip injection, no RoR failures are observed in the evaluated 1,000-trial experiments for the tested models. Under defense-aware SPoF reconstruction, RoR increases the cost of reproducing specified one-bit catastrophic failures to thousands of deployed INT8 bit changes. RoR also preserves downstream-task utility under PBS perturbations. On NVIDIA H200 at batch size 8, RoR incurs 0.097\%--0.584\% persistent storage overhead, 5.2\%--14.1\% Prefill overhead, and 0.5\%--9.8\% Decode overhead across four representative models. These results show that sensitivity-aware hierarchical rotation provides a practical approach to improving the bit-flip robustness of quantized LLM Linear weights.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14076

ZoomGain: Mining Global-to-Zoom Perception Gaps for Fine-Grained Visual Supervision

Haozhan Shen, Liangbo He, Jun Lan, Huijia Zhu, Weiqiang Wang, Tiancheng Zhao, Jianwei Yin

原文摘要

Fine-grained visual perception requires Vision-Language Models (VLMs) to locate and interpret subtle evidence within complex scenes. Constructing supervision for this ability is challenging: questions must have correct, unambiguous answers that depend on actual fine-grained visual details rather than coarse cues or language priors. Verifying these properties makes manual annotation labor-intensive and automatic generation difficult for models that themselves struggle with fine-grained perception. Yet the same models can often recognize such details once the region is zoomed in. We exploit this global-to-zoom perception gap and introduce ZoomGain, a data construction pipeline that constructs questions about the full image from visual information gained only by zooming in. It verifies each answer on the zoomed view with multiple models, ensures that each question remains unambiguous in the full image and cannot be answered from language priors, and specifically generates high-quality distractors for multiple-choice questions. With this pipeline and human-only screening (no manual QA editing), we build ZoomGainBench, a 1,000-question bilingual benchmark on which the best of 28 VLMs achieves only 61.08. Failure analysis reveals that models favor a particular type of distractor when answering multiple-choice questions incorrectly. Beyond evaluation, training on just 9K ZoomGain samples substantially improves the visual perception capabilities of our 4B/9B models, enabling them to outperform several hundred-billion-parameter models across various perception benchmarks. The trained 9B model achieves SoTA performance on several benchmarks, such as 90.25 on HR-Bench 4K. These results establish global-to-zoom perception gaps as a practical basis for scaling fine-grained visual supervision for both evaluation and training. Our code is available at https://github.com/inclusionAI/ZoomGain.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2511.14521

A Generative Data Framework with Reliable Supervision for Underwater Image Restoration and Enhancement

Yufeng Tian, Yifan Chen, Zhe Sun, Libang Chen, Mingyu Dou, Jijun Lu, Ye Zheng, Xuelong Li

原文摘要

Learning-based underwater image restoration and enhancement rely heavily on high-quality paired training data. However, obtaining clear reference images for real underwater scenes remains challenging. Existing datasets often use the outputs of enhancement algorithms as references, which may introduce uncertainty into supervision targets. To address this issue, we propose a generative data framework that preserves clear source images as restoration references and synthesizes corresponding underwater inputs through unpaired image-to-image translation. Using representative underwater appearances to guide the translation, we construct UWNature from natural photographs. We systematically examine the reliability of the generated supervision through its agreement with real underwater appearances, structural consistency, and depth-related degradation characteristics. Experiments across 6 restoration architectures and 3 test sets evaluate its effectiveness through objective metrics, human perceptual assessment, and the correspondence between synthetic degradation and learned restoration behavior. The results demonstrate competitive restoration performance and favorable perceptual quality on real underwater images. Further analysis reveals that greater spatial plausibility of synthetic degradation does not necessarily improve restoration performance, highlighting the importance of evaluating both the intrinsic properties of synthetic data and their effectiveness for model learning. These findings support a scalable framework for constructing and evaluating reliable paired supervision for underwater image restoration and enhancement. The generated datasets are available at: https://github.com/tianyufengcn/SynUIEDatasets.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.02157

RamanPFN: A physics-guided spectral foundation framework for in-context learning across diverse Raman applications

Xingyu Pan, Huan Wang, Jinjia Guo, Zhenlin Zhao, Siming Dong, Jixi Lu

原文摘要

Raman spectroscopy enables label-free molecular characterization across materials science, analytical chemistry, biomedicine, and industrial process monitoring. However, machine learning for high-dimensional spectroscopy remains constrained by limited labeled data and a mismatch between the physical organization of spectra and feature-agnostic models. Tabular foundation models such as TabPFN predict in context without parameter updates, but on wide spectra feature subsampling preserves channel coverage while losing joint visibility: in the five widest tasks, every channel was covered, yet only 4.4% of random channel pairs co-occurred in any forward pass. We present RamanPFN, a general-purpose spectral foundation framework for unified in-context inference through physics-guided spectral learning, which encodes the additive mixing of constituent spectra and the locality of vibrational bands. Global Compositional Unmixing decomposes distributed, multi-band mixture signatures into shared non-negative bases to couple covarying peaks across the full spectrum, while Local Vibrational Subspace Encoding extracts orthogonal modes within contiguous spectral neighborhoods to preserve peak morphology, intensity fluctuations, and peak shifts. Posterior marginalization over admissible unmixings unifies both scales into in-context prediction without updating the model. Across 74 public Raman datasets exceeding 330,000 spectra, RamanPFN outperformed 26 methods spanning chemometrics, spectral neural networks, deep tabular learners, and tabular foundation models on 129 regression targets, reducing backbone RMSE by 13.2%. We demonstrate across TabPFN-3, TabICLv2, and Kumo-Tabular that this advantage generalizes to both regression and classification tasks, reducing regression error by 12.3%-25.7% and multiclass log loss by 42.4%-63.5% to enable data-efficient quantitative analysis and sample identification.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2308.14527

MDS Array Codes With Small Sub-packetization Levels and Small Repair Degrees

Jie Li, Yi Liu, Xiaohu Tang, Yunghsiang S. Han, Bo Bai, Gong Zhang

原文摘要

High-rate minimum storage regenerating (MSR) codes are known to require a large sub-packetization level, which can make meta-data management difficult and hinder implementation in practical systems. A few maximum distance separable (MDS) array code constructions have been proposed to attain a much smaller sub-packetization level by sacrificing a bit of repair bandwidth. However, to the best of our knowledge, only one construction by Guruswami et al. can support the repair of a failed node without contacting all the surviving nodes. This construction is certainly of theoretical interest but not yet practical due to its requirement for very large code parameters. In this paper, we propose a generic transformation that can convert any $(\overline{n}, \overline{k})$ MSR code with a repair degree of $\overline{d}<\overline{n}-1$ into another $(n=s\overline{n},k)$ MDS array code that supports $d<n-1$ with a small sub-packetization level and $(1+ε)$-optimal repair bandwidth (i.e., $1+ε$ times the optimal value) under a specific condition. We obtain three MDS array codes with small sub-packetization levels and $(1+ε)$-optimal repair bandwidth by applying this transformation to three known MSR codes. All the new MDS array codes have a small repair degree of $d<n-1$ and work for both small and large code parameters.

cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v6arXiv:2409.18745

A study on the effects of mixed explicit and implicit communications in human-artificial-agent interactions

Ana Christina Almada Campos, Bruno Vilhena Adorno

原文摘要

Communication between humans and artificial agents is essential for their interaction. This is often inspired by human communication, which uses gestures, facial expressions, gaze direction, and other explicit and implicit means. This work presents interaction experiments where humans and artificial agents interact through explicit and implicit communication to evaluate the effect of mixed explicit-implicit communication against purely explicit communication and the impact of the task difficulty in this evaluation. Results obtained using Bayesian parameter estimation show that the task execution time did not significantly change when mixed explicit and implicit communications were used in neither of our experiments, which varied in the type of artificial agent (virtual agent and humanoid robot) used and task difficulty. The number of errors was affected by the communication only when the human was executing a more difficult task, and an impact on the perceived efficiency of the interaction was only observed in the interaction with the robot, for both easy and difficult tasks. In contrast, acceptance, sociability, and transparency of the artificial agent increased when using mixed communication modalities in both our experiments and task difficulty levels. This suggests that task-related measures, such as time, number of errors, and perceived efficiency of the interaction, as well as the impact of the communication on them, are more sensitive to the type of task and the difficulty level, whereas the combination of explicit and implicit communications more consistently improves human perceptions about artificial agents.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.18556

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling

Alireza Dadgarnia, Soroush Tabesh, Mahdi Nikdan, Michael Helcig, Eldar Kurtic, Maximilian Kleinegger, Dan Alistarh

原文摘要

Quantization has become a standard tool for efficient LLM deployment, especially for local inference, where models are now routinely served at 2-3 bits per parameter. The state of the art is currently split into simple scalar quantization techniques, such as GPTQ or AWQ, which are widely deployed but plateau in accuracy at 3-4 bits per parameter (bpp), and "second-generation" vector- or trellis-quantized methods, such as QTIP, GPTVQ and AQLM, which push the accuracy frontier but are notoriously hard to implement and to scale. In this paper, we ask whether this gap is fundamental, or whether a carefully optimized $\textit{scalar}$ quantizer can recover most of it. We answer in the affirmative, by introducing GSQ (Gumbel-Softmax Quantization), a post-training scalar quantization method which jointly learns the per-coordinate grid assignments and the per-group scales using a Gumbel-Softmax relaxation of the discrete grid. GSQ matches the cardinality of the relaxation to the small number of levels available in the target bit-width regime (e.g., 3-8 levels for ternary and 3 bpp, respectively), making optimization tractable. Practically, on the standard Llama-3.1-8B/70B-Instruct models, GSQ closes most of the gap between scalar quantization and the QTIP frontier at 2 and 3 bits, while using a symmetric scalar grid with group-wise quantization, and thus remains compatible with existing scalar inference kernels. We further show that the same discrete-assignment optimization can be applied to practical GGUF K-Quant checkpoints: starting from publicly released GGUF models, GSQ improves accuracy while projecting the result back into the same deployment format. Finally, GSQ scales to trillion-scale Mixture-of-Experts models such as Kimi-K2.5, where vector-quantized methods are difficult to apply. The source code is publicly available at https://github.com/IST-DASLab/GSQ.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.18585

RECURSUM: Automated Code Generation for Recurrence Relations Exceeds Expert Optimization via LayeredCodegen

Rubén Darío Guerrero

原文摘要

Automated code generation can systematically exceed expert hand-optimization for recurrence relations--computational primitives ubiquitous in orthogonal polynomials, special functions, numerical integration, and molecular integral evaluation. We present RECURSUM, a Python DSL generating optimized C++ for arbitrary recurrence relations via three backends--template metaprogramming, a novel LayeredCodegen backend, and runtime loop-based evaluation--specifying recurrences in 10--30 lines of Python that generate 650+ lines of production C++. LayeredCodegen achieves 9.8$\times$ speedup over expert hand-written code and 1.9$\times$ over template metaprogramming for McMurchie-Davidson Hermite coefficients, through zero-copy output parameters, guaranteed inlining, and exact-sized stack buffers. A DAG-topological generalization of this architecture--built to express the four-center electron-repulsion integral that LayeredCodegen's tower model cannot--beats libint2, a mature, two-decade-refined production library, on 12 of 14 Cartesian integral classes, with $\sim$2$\times$ faster contracted Coulomb/exchange (J/K) matrix construction (alkanes and 3-D DNA fragments alike) and 1.1--2.7$\times$ faster one-electron integrals, completing the full Hartree-Fock integral set from one DAG framework. We validate 24 recurrence types spanning pure mathematics, numerical analysis, and quantum chemistry; production benchmarks confirm these speedups propagate to complete algorithms, matching expert baselines within 3.3\%. By eliminating the dual expertise barrier of domain knowledge and C++ metaprogramming, RECURSUM establishes systematic code generation--not hand-tuning--as the performance ceiling for recurrence algorithms.

cs.PL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14062

A human-in-the-loop Control Paradigm for Construction Robotics: From VR-Guided Teleoperation to Semi-Autonomous Dual-Arm Operation

Jinhua Chen, Xiaoji Xu, Zhongyuan Liao, Huang Zhenmin, Zhang Ye, Changying Xiang

原文摘要

Construction tasks in hazardous and unstructured environments require both human adaptability and robotic precision, yet existing approaches often treat teleoperation and autonomy as separate control modes. This paper presents a human-in-the-loop control paradigm that enables structured transitions among VR-guided teleoperation, semi-autonomous shared control, and rule-based autonomous execution for contact-rich dual-arm construction tasks. The proposed system combines immersive VR guidance, a manually defined library of reusable skill primitives, and a shared-autonomy framework with explicit human-robot role allocation and command-priority rules. This integration allows operators to retain supervisory and corrective authority while delegating repetitive and precision-critical actions to the robot. The paradigm is validated on a dual-arm platform through representative facade-installation tasks. Results show that autonomous execution provides the best performance under well-calibrated nominal conditions, whereas semi-autonomous control improves resilience when environmental disturbances exceed the predefined autonomous pipeline's correction capability. Semi-autonomous control also substantially reduces subjective operator workload compared with full teleoperation. These findings demonstrate that effective construction-robot control should adapt human involvement to task and environmental uncertainty, using autonomy for repeatable operations and shared control for disturbance recovery.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14061

Isolation Is Not Confidentiality: Security Boundaries of Geometric Access Control in RAG

Steve Nouyep, Maxime Puys, Sébastien Salva

原文摘要

Retrieval-Augmented Generation (RAG) systems increasingly rely on vector databases containing documents governed by different access-control policies. Recent search-preserving geometric approaches enforce such access control by structuring the embedding space so that transformed embeddings, which we call protected representations, remain retrievable without exposing information across policy boundaries. We provide a unified security analysis of this paradigm, covering policy isolation, representation confidentiality, query forgery resistance, and policy-membership hiding. We consider both a curious cloud service provider observing the protected representations stored in the vector database and a curious user holding aligned pairs of original embeddings and protected representations. Evaluating the available implementations of the works proposing these geometric transformation mechanisms across three encoders, we find that geometric transformations preserve retrieval utility and provide strong policy isolation, but do not provide the other security properties. A curious user can recover the original embeddings from a few hundred pairs and forge policy-compatible queries at a higher cost that grows with encoder dimension for secret per-policy transformations. Moreover, policy-dependent geometry can leak policy membership even when unauthorized retrieval is prevented. These results show that policy isolation, confidentiality, forgery resistance, and membership hiding are distinct security objectives.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14051

Can KV Cache Be Reused Across Model Updates? A DeepSeek-V4-Flash Case Study

Zhikun Tao, Fangyong Jin, Junping Zhao

原文摘要

Reusing key--value (KV) caches across language model updates could avoid repeated computation of shared context, but changes in model weights raise a fundamental question about what these caches preserve. We investigate direct cache reuse across four model updates, with a detailed study of DeepSeek-V4-Flash to Flash-0731. Our central finding is that caches can retain useful task information without faithfully reproducing the updated model's behavior. Retrieval accuracy varies substantially across updates, ranging from near-native performance to large losses. With source caches already available, reuse achieves median time-to-first-token speedups of $2.10$--$5.08\times$ on three longer-prefix QA benchmarks. To characterize the behavioral differences behind these outcomes, we introduce Functional Cache Divergence, which compares next-token distributions under reused and native caches. Direct KV cache reuse better preserves native model behavior in natural-text continuation, whereas compatibility degrades with increasing prefix length in single-token retrieval tasks. Answer-margin analyses help explain how correct retrieval decisions survive substantial internal state changes. Yet even agreement on the first generated token does not ensure agreement in answer content or stopping behavior. These findings establish task utility and fidelity to native inference as distinct criteria for evaluating cross-version KV cache reuse.

cs.DC · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14049

RedirectMimic: Local Motion Content Redaction for Humanoid Whole-Body Control

Zepeng Wang, Xiaochuan Shi

原文摘要

Humanoid motion interfaces should accommodate application-specific movement constraints while retaining useful reference behavior. Local content redaction requires a controller to replace selected movements even when it continues to receive the original reference. Removing the tracking incentive for those movements leaves their replacement unspecified. We introduce RedirectMimic, which separates the reference observed by the actor from the target used to train its execution. A rule-generated edited reference guides tracking rewards during proximal policy optimization, while the deployed observation and action interfaces remain unchanged. We evaluate pose- and speed-defined arm editing in Unitree G1 simulation using a tracker pretrained on 7,509 motion clips. On the overhead-arm task, RedirectMimic reduces core-window content occurrence to 2.7%, compared with 58.9% for reward zeroing and 32.8% for anti-tracking. It achieves 94.2% core-window joint success, combining content suppression, fall-free execution, and local retention. On the speed-defined task, fast outward arm movements occurred at similarly low rates under all three local editing methods. Across both tasks, RedirectMimic achieved the lowest replacement error among these methods and tracked unedited motions with accuracy comparable to that of the pretrained controller. Project page: https://xiaopeng-whu.github.io/RedirectMimic/.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14042

Resilient Integrated Access and Backhaul Network Planning via Graph Neural Network Curriculum Learning

Jie Zhang, Haochen Sun, Mingzhang Zhou, Paul D. Mitchell, Hamed Ahmadi, Qiang Ni

原文摘要

Integrated Access and Backhaul (IAB) is a key enabler for cost-effective millimeter-wave (mmWave) densification, yet practical deployments are strongly constrained by the spatial availability of fiber-connected IAB donors. Variations in donor topologies reshape both the initial coverage footprint and the feasible multi-hop backhaul expansion patterns, causing planning policies trained on a single topology to generalize poorly. This paper studies cross-topology generalization for resilience-aware IAB deployment under coverage and transport feasibility requirements. We formulate IAB deployment as a constrained Markov decision process that couples access coverage satisfaction with multi-hop transport feasibility, including hop-by-hop rate-budget degradation and a minimum parent-connectivity requirement for fault tolerance. To solve the resulting large discrete planning problem, we propose a graph-based actor-critic approach that uses a Graph Attention Network v2 (GATv2) encoder with Proximal Policy Optimization (PPO), and we develop a multi-stage curriculum learning strategy that progressively increases constraint difficulty and scenario diversity for stable training and transferable policies. In a 60 GHz urban simulation over a 1000 m x 1000 m area with multiple donor layouts, the trained policy satisfies the minimum coverage requirement of 98% with fewer deployed IAB nodes than learning and heuristic baselines, and maintains higher coverage under progressive backhaul failures. The results demonstrate that curriculum-trained graph-based reinforcement learning can improve deployment efficiency and resilience while transferring across heterogeneous IAB donor topologies without retraining.

cs.NI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.24337

Meet UD_Czech-PDTC: A Large and Genre-Rich Treebank in Universal Dependencies

Marie Mikulová, Barbora Štěpánková, Daniel Zeman, Jan Štěpánek, Milan Straka, Jan Hajič

原文摘要

Czech has been part of Universal Dependencies since its first release in 2015. It has also been one of the best represented languages, with the Prague Dependency Treebank being order of magnitude larger than most other UD treebanks. More recently, three other datasets from the Prague family were added and the annotations thoroughly revisited, forming the "Prague Dependency Treebank-Consolidated" (PDT-C). In comparison to the original PDT, PDT-C is more than twice as large, but it is also much more diverse in terms of genres and domains. In this paper, we describe the conversion of the new resource to Universal Dependencies. While the two annotation schemes are relatively similar at the first sight, there are numerous small differences in topology of the dependency structures and in granularity of the POS and relation type inventories. We demonstrate a selection of such differences on examples, discuss the diverging motivations, as well as ways to overcome the differences during conversion. We argue that while PDT is less "universal" and more tightly bound to one language, its multi-layer annotation is rich and provides all information needed for basic UD trees, and much more.

cs.CL

查看论文
arXiv ↗PDF ↗