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

+0新增论文
+0其中 AI 相关
+0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：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 06:26 — 2026-11-16 06:26（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：2026-11-14 15:09库内论文最新更新时间：2026-11-13 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

23,348 已收录论文19,580 AI 相关6,729 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 23,348 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）
版本更新 · v2arXiv:2603.29288

Sima AIunty: Caste Audit in LLM-Driven Matchmaking

Atharva Naik, Shounok Kar, Varnika Sharma, Ashwin Rajadesingan, Koustuv Saha

原文摘要

Social and personal decisions in relational domains such as matchmaking are deeply entwined with cultural norms and historical hierarchies, and can potentially be shaped by algorithmic and AI-mediated assessments of compatibility, acceptance, and stability. In South Asian contexts, caste remains a central aspect of marital decision-making, yet little is known about how contemporary large language models (LLMs) reproduce or disrupt caste-based stratification in such settings. In this work, we conduct a controlled audit of caste bias in LLM-mediated matchmaking evaluations using real-world matrimonial profiles. We vary caste identity across Brahmin, Kshatriya, Vaishya, Shudra, and Dalit, and income across five buckets, and evaluate five LLM families (GPT, Gemini, Llama, Qwen, and BharatGPT). Models are prompted to assess profiles from the perspective of a caste-identified prospective bride or groom along dimensions of social acceptance, marital stability, and cultural compatibility. Our analysis reveals consistent hierarchical patterns across models: same-caste matches are rated most favorably, with average ratings up to about 30% higher (on a 10-point scale) than inter-caste matches, which are further ordered by distance along the traditional caste hierarchy, with higher-caste candidates generally favored at equal distance and an additional penalty for Dalit candidates. These findings highlight how existing caste hierarchies are reproduced in perspective-conditioned LLM evaluations and underscore the need for culturally grounded evaluation and intervention strategies in AI systems deployed in socially sensitive domains, where such systems risk reinforcing historical forms of exclusion.

cs.CY · cs.AI · cs.CL · cs.HC · cs.SI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.01264

Sub Terahertz LEO Satellite Communication: Is Doppler Shift a Major Challenge?

Seongjoon Kang, Parisa Ramezani, Ki Won Sung, Vitaly Petrov

原文摘要

In this work, we investigate the impact of Doppler frequency shift on sub-terahertz low Earth orbit (LEO) satellite communications using OFDM transmission. To comprehensively evaluate the severity of the Doppler shift impact on sub-terahertz satellite-to-ground links, we first put together an evaluation framework that jointly accounts for major Doppler-induced and non-Doppler-induced signal impairments in such systems. We then compare and contrast three possible engineering approaches to deal with Doppler shift in such a communication system. Our study concludes that (i)~while just ignoring the Doppler effect in such high-frequency and high-mobility systems substantially compromises the performance and reliability, (ii)~most of the negative effects can be eliminated by implementing only a small set of low-complexity measures. We particularly show that even a single Doppler shift estimation over a 5-min-long satellite pass over the ground user location may be sufficient to ensure high performance throughout the entire connectivity period. Hence, while Doppler shift is an important effect to account for in sub-terahertz LEO satellite communications, it should not constitute a critical design challenge for these emerging systems.

cs.IT · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15700

AskALCF: A Self-Improving Agentic System for Intelligent HPC User Support

Jingyan Jiang, Akhilesh Bondapalli, Krishna Rauniyar, Murat Keceli, Yasaman Ghadar, Haritha Siddabathuni Som, Venkatram Vishwanath, Michael E. Papka 等 10 位作者

原文摘要

AI-based question-answering systems are increasingly used for user support, including at high-performance computing (HPC) facilities. However, existing systems lack a systematic, deployment-oriented approach for evaluating final-answer quality and attributing failures to specific components. They also remain largely static after deployment, apart from periodic knowledge-base updates. We present AskALCF, an agentic log-analysis and improvement pipeline for HPC user support. AskALCF evaluates production interactions at a fine-grained level, identifies whether failures arise from missing knowledge, retrieval, prompting, model behavior, or tool execution, and routes each failure to an actionable repair. Its diagnostic core combines answer-quality assessment with a two-scope sufficiency test that distinguishes information missing from the documentation corpus from information present but not retrieved. We further introduce a controlled harness-training process that uses expert references, null edits, and explicit ship, revert, or decline decisions to improve the diagnostic pipeline reliably. Across 2,174 support turns, AskALCF reduced unattributable failures from 41.4% to 14.2%, while harness training improved expert agreement from 108/150 to 123/150 turns. These results demonstrate a governed form of self-evolution in which production evidence drives targeted system improvements. By turning production interactions into fine-grained diagnoses and actionable repairs, AskALCF provides a systematic foundation for continuously improving deployed AI support systems beyond knowledge-base updates alone.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15698

Learning Mixtures of Exponential Family

Mansi Sood, Devavrat Shah

原文摘要

Motivated by causal inference and physical computing systems, we consider the problem of learning mixture of two bounded-support exponential-family distributions with a shared interaction parameter matrix and mixture component-specific linear parameter vectors. The unknown sequence of component labels belongs to a known structured class. We propose an estimator based on a convex loss that avoids the log-partition function; for each fixed label assignment, estimation is a convex optimization problem. We show that the conditional population loss uniquely identifies the interaction matrix and the linear parameter attached to each sample. For a global empirical minimizer, we establish finite-sample bounds on the interaction error in Frobenius norm and the average squared linear-parameter error. The bounds depend on the logarithm of the number of admissible label assignments, and, for fixed dimension and model bounds, imply consistency when this complexity grows sublinearly with sample size. Additional occupancy and separation conditions yield component and label recovery.

stat.ML · cs.LG · eess.SP

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.12737

Inference Validation for Regulated AI: A Governed Decision Pipeline for LLM Serving

Dev Akre, Roman Bobalo, Manoj Dobbali

原文摘要

Deploying large language models in regulated industries requires more than picking the fastest inference engine: it requires evidence that a configuration meets contractual and legal obligations before it serves a single customer request. We describe Runway, an internal validation harness built at MasterControl that builds a governed decision pipeline around NVIDIA AIPerf. The key insight is separating concerns: AIPerf provides the trusted measurement, while Runway provides the experiment design that comes before it and the compliance, cost, and audit decisions that come after. We describe the architecture and the storage model that makes caching and audit one mechanism. We report three findings from Runway sweeps: TensorRT-LLM and vLLM rankings invert with concurrency; a newer, pricier GPU instance can be the cheaper one per request; and speculative decoding behaves differently across engines under load, so engine configuration can outweigh engine choice.

cs.SE · cs.LG · cs.PF

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2512.02551

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

Songqiao Su, Xiaoya Li, Albert Wang, Guoyin Wang, Jiwei Li, Chris Shum

原文摘要

In this paper, we propose CUDA-L2, a system that combines large language models (LLMs) and reinforcement learning (RL) to automatically optimize Half-precision General Matrix Multiply (HGEMM) CUDA kernels. Using CUDA execution speed as the RL reward, CUDA-L2 automatically optimizes HGEMM kernels across 1,000 configurations. CUDA-L2 systematically outperforms major matmul baselines to date, from the widely-used torch.matmul to state-of-the-art Nvidia's closed-source libraries, i.e., cuBLAS, cuBLASLt. In offline mode, where kernels are executed consecutively without time intervals, CUDA-L2 yields +22.0% over torch.matmul on average; +19.2% over cuBLAS using the optimal layout configuration (normal-normal NN and transposed-normal TN); +16.8% over cuBLASLt-heuristic, which queries cuBLASLt library and selects the algorithm based on the heuristic's suggestion; and +11.4% over the most competitive cuBLASLt-AutoTuning model, which selects the fastest algorithm from up to 100 candidates from cuBLASLt's suggestions. In server mode, where kernels are executed at random intervals simulating real-time inference, the speedups further increase to +28.7%, +26.0%, +22.4%, and +15.9% for torch.matmul, cuBLAS, cuBLASLt-heuristic, and cuBLASLt-AutoTuning respectively. CUDA-L2 shows that even the most performance-critical, heavily-optimized kernels like HGEMM can be improved through LLM-guided RL automation by systematically exploring configuration spaces at scales impractical for humans. Project and code can be found at github.com/ornith-ai/CUDA-L2

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2511.12635

LLM4SCREENLIT: Recommendations on assessing the performance of large language models for screening literature in systematic reviews

Lech Madeyski, Barbara Kitchenham, Martin Shepperd

原文摘要

Context: Large language models (LLMs) are increasingly used to screen literature for systematic reviews (SRs), but the standard confusion-matrix metrics used to evaluate them can mislead under the imbalanced, cost-asymmetric conditions of screening. Objective: We develop and justify LLM4SCREENLIT-practical recommendations for researchers conducting LLM-screening evaluations and for editors and reviewers assessing such studies-differentiated by study type (retrospective benchmarking vs deployment for a specific SR). Method: Using Delgado-Chaves et al. (2025), an 18-LLM benchmark across three biomedical SRs, as a motivating example, we reviewed 28 additional papers and extracted their reported metrics. We propose a Weighted Matthews Correlation Coefficient (WMCC) that integrates MCC's chance-correction with asymmetric misclassification costs, and validated it on three software-engineering (SE) reanalyses, the largest covering 9 LLMs x 24 SE secondary studies (34,528 articles). Results: Across the 29 papers, only 10% reported MCC, only 24% reported full confusion matrices, and none of the five papers claiming workload savings priced false-negative cost. In the largest SE reanalysis, MCC and WMCC disagree on the best LLM in 55% of evaluable studies; in the most striking 9,695-article SE study, the Accuracy-best LLM loses 63.3% of relevant evidence (Lost Evidence), the MCC-best 43.9%, but the WMCC-best only 5.8%. Sensitivity analysis (median crossover at w~=2.7, all <7) supports w=10 as a conservative default. Conclusions: SR-screening evaluations should prioritize Lost Evidence and use cost-sensitive WMCC alongside MCC for ranking. Reporting must include the full confusion matrix and treat unclassifiable outputs as positives requiring human review. Designs should be leakage-aware, with non-LLM baselines when the study aims to inform SR practice and labels are available.

cs.SE · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.22608

Understanding LLM Performance Degradation in Multi-Instance Processing: The Roles of Instance Count and Context Length

Jingxuan Chen, Mohammad Taher Pilehvar, Jose Camacho-Collados

原文摘要

Users often rely on Large Language Models (LLMs) for processing multiple documents or performing analysis over a number of instances. For example, analysing the overall sentiment of a number of movie reviews requires an LLM to process the sentiment of each review individually in order to provide a final aggregated answer. While LLM performance on such individual tasks is generally high, there has been little research on how LLMs perform when dealing with multi-instance inputs. In this paper, we perform a comprehensive evaluation of the multi-instance processing (MIP) ability of LLMs for tasks in which they excel individually. The results show that all LLMs follow a pattern of slight performance degradation for small numbers of instances (approximately 20-100), followed by a performance collapse on larger instance counts. Crucially, our analysis shows that while context length is associated with this degradation, the number of instances has a stronger effect on the final results. This finding suggests that when optimising LLM performance for MIP, attention should be paid to both context length and, in particular, instance count.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.20910

Whose Agent Are You? Multi-Layer Fingerprinting and Attribution of Autonomous Web Agents

Dayeon Kang, Hyejun Jeong, Jade Sheffey, Pubali Datta, Amir Houmansadr

原文摘要

As AI web agents proliferate, combining large language models with autonomous, browser-level control, indiscriminate content scraping by web agents has emerged as a privacy and security challenge. Existing defenses, such as robots.txt and active bot-blocking, are insufficient, as they are widely violated and easily circumvented. In this work, we demonstrate that AI web agents can be effectively distinguished from humans and traditional crawlers using a multi-layer fingerprint based on both network layer characteristics (e.g., TLS, HTTP) and browser interaction behavior. We implement this mechanism as a programmatic logging framework that can be deployed on a live, instrumented domain. By analyzing six prominent agent frameworks (AutoGen, Browser Use, Claude, Gemini, ChatGPT, and Skyvern), we uncover latent structural differences in how these systems assemble HTTP requests, establish TLS/HTTP connections, and execute autonomous browser actions. Feeding these multi-layer features into a decision tree classifier, our framework achieves high-fidelity identification (100% accuracy), successfully isolating distinct agent architectures and differentiating agent traffic from both human browsing baselines and legacy crawlers. Our findings demonstrate that cross-layer agent tracking provides a robust approach to content protection and web security policy enforcement.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15694

Optimization of Finite Alphabet Message Passing Decoding on Fully Node-Parallel Architectures for 5G LDPC Codes

Alexander von Bank, Oliver Griebel, Eike-Manuel Edelmann, Norbert Wehn, Laurent Schmalen

原文摘要

In this paper, we propose a novel design method for the lookup tables (LUTs) of the minimum reconstruction, computation, and quantization (min-RCQ) LDPC code decoding algorithm. The proposed design method uses Bayesian optimization and samples from a subspace of the design space. The novel design method does not require knowledge about the channel or the modulation format and uses the frame error rate (FER) as loss function. The design method is applicable to irregular low-density parity-check (LDPC) codes with puncturing and shortening. Furthermore, the design method creates a set of iteration-agnostic LUTs that can be used over all iterations, which makes this approach suitable for fully node-parallel decoder architectures. We show that our proposed approach achieves a 38.6 % better energy efficiency than a state-of-the-art normalized min-sum (NMS) decoder without loss in error correction performance.

cs.IT · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15692

CGOcc: Learning Cross-Gaussian Dependencies for 3D Semantic Occupancy Prediction

Zirui Huang, Jiongle He, Yunfan Zeng, Yuanzhi Lu, Guangye Li, Boyan Tang, Weite SU, Pedro V. Sander 等 9 位作者

原文摘要

In Gaussian-based semantic occupancy prediction, overlapping primitives can provide ambiguous class predictions, making their joint interpretation important for voxel classification. However, current methods using spatially weighted mixtures neglect explicit modeling of cross-primitive dependencies, limiting the readout's ability to utilize category-specific relational evidence. Hence, we introduce CGOcc, a supervised multi-camera framework that explicitly models Cross-Gaussian dependencies for 3D semantic Occupancy prediction. CGOcc integrates appearance and geometric observations to refine Gaussian states and encodes cross-Gaussian dependencies in a diagonal-plus-low-rank representation. To incorporate these dependencies into voxel classification, CGOcc uses a class-conditional projection to extract diagonal and signed cross-Gaussian statistics without constructing a dense dependency matrix. The readout then refines occupied-class probabilities using these statistics while preserving a learned reference's occupied mass and free probability. Extensive experiments on nuScenes demonstrate CGOcc achieves state-of-the-art performance, with larger gains at high Gaussian overlap and improved predictions near boundaries. Ablation studies validate the effectiveness of covariance-aware prediction and support its synergy with geometric interaction.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15691

Dynamic Block-Online Streaming ASR for Low-Resource Agglutinative Code-Switching Speech with Morphology-Aware Evaluation

Kazi Rafat, Afifa Imran, Md. Ismail Hossain, Md. Romzan Ali, Fuad Rahman, Sifat Momen, Shafin Rahman, Nabeel Mohammed

原文摘要

Low-resource, agglutinative languages challenge low-latency ASR, as fixed lookahead windows fail when grapheme order diverges, suffixes cross code-switch boundaries, or code-switching data is imbalanced. We present the first comprehensive study of streaming ASR for intra-sentential Bangla-English code-switching, identifying a mismatch between strict causal streaming and long-range morphological dependencies. We introduce a Dynamic Block-Online framework with VAD-aligned inference that balances semantics, latency, and context, enabling global bidirectional attention to preserve morphological integrity. To mitigate data scarcity, we propose Script-Anchored Loanword Injection, augmenting training text with English loanwords to model phonotactic transitions. We introduce CS-WER to diagnose switch, root, and suffix errors, and show that flexible latency budgets enhance recognition of agglutinative and mixed-language speech, with successful transfer to menstrual-medical domains.

cs.CL · cs.SD

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15689

What World Model Does Active Object Search Need? A Study under Imperfect Detection

Kyeongryeol Go

原文摘要

In active object search, a robot must decide where to look and when to stop. Imperfect detection complicates both decisions: a non-detection may indicate occlusion, an out-of-view target, or a false negative, while a detection may be a false positive. This raises the question of which representations a world model needs to support reliable search under imperfect detection. We introduce Bayesian Active Miss-aware Object Search (BAMOS) to investigate how target belief, occupancy belief, and detector errors affect search decisions. Through comprehensive ablations in Isaac Sim and HSSD houses, we examine the roles of these representations and their update mechanisms across different detector configurations. Notably, target belief and its update mechanisms are critical to search performance, with their contribution generally increasing as detection errors become more prevalent. These findings highlight the importance of maintaining and updating target beliefs to support reliable active search under uncertain detector observations, providing insights into the design of world models for embodied agents. Code is available in https://github.com/gokyeongryeol/BAMOS.

cs.RO · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15686

Integrating Slides, Mathematics, and Simulation in One Page: GenAI-Assisted HTML Learning Objects for Engineering Courses

Xuan-Quy Dao, Ngoc-Bich Le, Xuan-Dung Phan, Le-Minh Nguyen

原文摘要

Engineering courses spread their materials across slides (PPTX), typeset notes (LaTeX/PDF), and MATLAB, leaving students to connect them. We describe an instructor-in-the-loop workflow in which generative AI (GenAI) converts these assets into single-file HTML learning objects that combine presentation, mathematics, visualization, simulation, and assessment; a page is released only after its simulations pass numerical verification. Six open demonstrators implement 18 tasks from six engineering courses. In the eight tasks with quantitative cross-checks, every quantity met its tolerance at default settings (1\%, or 2\% for the finite-difference time-domain simulation) and agreed with a separate Python re-computation and a value-blinded MATLAB re-computation run by a colleague not involved in development; the checks also flagged under-resolved settings. In a perception survey, students (19 after post-hoc screening of 28 responses) reported that the pages linked equations with simulation, and 74\% preferred them to separate files, but usability was marginal (System Usability Scale 56.8). Twelve lecturers rated the approach as useful (item means 4.25--4.58) but were hesitant to adopt it; their median ratings on a 12-criterion capability rubric agreed moderately with the first author's ($κ_w=0.60$; individual median 0.31). The results show technical feasibility and preliminary positive perceptions; learning outcomes were not measured.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15681

Energy Aware Optimization of Non-Deterministic Task-Based Intermittent Computing Nodes with Thimble

John Madden, Morgan Masters, Alec Levy, Steve McGuire, Colleen Josephson

原文摘要

Intermittent computing nodes run on harvested energy, which they store in capacitors and spend in short bursts of computation. Choosing those capacitors is a trade-off: large capacitors can power large tasks but leak more current, wasting harvested energy, while small capacitors leak less but cannot power large tasks. Recent work, LEACS, showed that selecting capacitors and mapping tasks to them at compile time improves inference throughput. However, LEACS optimizes the mapping for a predetermined workload, whereas sensor nodes often run data-dependent workloads in which the next task depends on the outcome of earlier ones. We present Thimble, an energy storage system that maps a node's tasks to capacitors at runtime. Thimble models the workload as a Markov chain over tasks and assigns each task to a capacitor by weighing capacitor leakage, the task's energy demand and, when it replans, the likelihood of each future task. We compare Thimble against a reimplementation of LEACS, which ranks every static plan by simulation. When the training trace resembles deployment, Thimble's single design-time solve comes within 0.3--4% of LEACS's throughput. When the deployment conditions drift from the characteristics of the training set, LEACS's throughput-focused static plans can fail sharply. On the lowest-power source we consider, LEACS's plan stalls on deployment traces that harvest less than its training trace, and on some never wakes; Thimble avoids this, with 22--29% higher throughput at the reference workload. A sensitivity sweep over 25 workload profiles on that source shows that Thimble with depth replanning leads LEACS by 22--42% throughout, and what run-time remapping adds: replanning at a fixed interval matches or improves on the static map at 21 of 25 points, by up to 7%.

cs.NI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2602.06285

MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Training

Lucia Gordon, Serge Belongie, Christian Igel, Nico Lang

原文摘要

Recent research in geospatial machine learning demonstrates that models pretrained with self-supervised learning on Earth observation data can perform well on downstream tasks with limited labeled data. However, most benchmark datasets have few data modalities and poor global representation, limiting the ability to evaluate multimodal pretrained models at global scales. In order to fill this gap, we introduce MMEarth-Bench, a collection of five new environmental tasks with 12 modalities, globally distributed data, and both random and geographic test splits. We benchmark a diverse set of pretrained models and find that while (multimodal) pretraining tends to improve model robustness in limited data settings, geographic generalization abilities remain poor. Moreover, a simple randomly initialized multimodal model is competitive given enough labeled data. Although data is abundant, models can currently only make use of the modalities on which they were pretrained. To solve this problem, we propose using all the modalities available at test time as auxiliary tasks for test-time adaptation. Our model-agnostic method for test-time training with multimodal reconstruction (TTT-MMR) can improve performance across all models and tasks on both test splits. Furthermore, geographic batching leads to a good trade-off between regularization and specialization during TTT, which can be beneficial for long-tail distributions. Our dataset, code, and visualization tool are linked on the project page.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.04543

Quantum Machine Learning Protection of Military Quantum Key Distribution Against Cryptographically Camouflaged Attacks

Muhammad Shaheer Bin Junaid

原文摘要

Quantum key distribution proves its protocol secure and says nothing about the hardware beneath it, so military and government operators fielding it for command-and-control keys monitor the channel for implementation attacks, and that monitoring has a blind spot. An adversary with a kleptographic foothold in the generator of a public per-block value \(x=g^v \pmod p\) can hide attacked blocks in honest noise, gating them on a predicate of its discrete logarithm, making detection a discrete logarithm problem that defeats every efficient classical monitor yet yields to a quantum kernel recovering \(v\) through Shor's algorithm. I formalise these cryptographically camouflaged attacks, reduce their hardness to an established learning separation, prove a single-frequency fidelity kernel cannot represent an interval predicate, and test them on Ghillie, a decoy-state BB84 simulator with a positive key rate to 142 km. From 10- to 14-bit groups over two seeds, a classical monitor reads 0.458 to 0.516 on camouflaged attacks while the quantum kernel reads 1.000, and both catch overt attacks above 0.99. Finite-precision recovery under depolarising noise and a hardened predicate lower the quantum result to 0.916 through 0.983 with the classical monitor at chance, and a feasibility probe on IBM Heron processors tracks the exact kernel within 0.034. A defender can therefore discard precisely the compromised key material, although the advantage is asymptotic, awaits fault tolerance, and holds only when the feature map matches the adversary's predicate, since a low-frequency map reads 0.545 on a residue pattern and 0.982 once aligned.

cs.CR · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15680

SpaceMCP: Vision Language Model Spatial Reasoning via Model Context Protocol

Ameen Izhac, Nobuko Yoshida, Ronald Clark

原文摘要

Despite impressive advances in large language models (LLM), vision-language models (VLM) still exhibit limited spatial reasoning capabilities. Recent progress in feed-forward 3D reconstruction has enabled precise, real-time geometric understanding from visual inputs. In this work, we propose SpaceMCP, a framework that leverages these advances to introduce an MCP-style paradigm for spatial reasoning. Our approach augments a VLM with structured function calls, allowing it to query a scene graph for spatial information such as distances, object positioning, and camera properties. The scene graph is constructed in real time using feed-forward 3D reconstruction to recover metric geometry, combined with open-vocabulary segmentation to identify and localize relevant objects within the scene. Paired with the VLM's strong reasoning capabilities, the VLM is able to combine this primitive information to solve more complex spatial tasks. Without any training, SpaceMCP achieves state-of-the-art results on VSI-Bench, MMSI-Bench and VSTI-Bench, outperforming recent spatially post-trained VLMs and improving its base VLM by 15-22 points per benchmark. We argue that, given the contrast between the relatively slow progress in native VLM spatial reasoning and the rapid advances in feed-forward 3D computer vision, this paradigm offers a promising path forward for enabling robust spatial reasoning.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.22010

Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks

Margalit Glasgow, Joan Bruna

原文摘要

We consider one-hidden layer neural networks trained in the feature-learning regime using gradient descent, and relate the output of the finite-width network $f_{\hatρ_t^m}$ to its infinite-width counterpart $f_{ρ_t^{MF}}$, which evolves in the mean-field dynamics. While constant-time horizon bounds for $\|f_{ρ_t^{MF}} - f_{\hatρ_t^m}\|$ may be obtained via standard Grönwall estimates, the long-time behavior of the fluctuation is a more delicate matter. Uniform-in-time bounds often rely on (local) strong convexity in the landscape or Logarithmic Sobolev inequalities present in noisy gradient dynamics. In this work, we establish non-asymptotic weak propagation-of-chaos that holds uniformly in time, obtained by exploiting instead the convergence rate of the mean-field deterministic Wasserstein-gradient-flow dynamics. Specifically, denoting by $L_t$ the mean-field excess MSE loss at time $t$ and $m$ the number of neurons, under standard regularity assumptions and the condition $\int_0^\infty L_t^{1/2} dt =O(\log d)$, we obtain the uniform in time bound $\|f_{ρ_t^{MF}}- f_{\hatρ_t^m}\|^2 \lesssim \text{poly}(d) m^{-\min(1,c/6)}$ whenever $L_t \lesssim t^{-c}$. Our result holds in a noiseless setting and does not make any assumptions on the geometry of the landscape near the optimum, and extends seamlessly to other forms of discretization, including finite number of samples and time discretization. A key takeaway of our result is that whenever the convergence rate of the mean-field, population-loss dynamics is faster than $t^{-2}$, we can attain a loss of $ε$ with only $\text{poly}(d/ε)$ neurons, training samples, and GD steps.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.16878

A Foundation Model for Electrodermal Activity Data

Leonardo Alchieri, Matteo Garzon, Lidia Alecci, Francesco Bombassei De Bona, Martin Gjoreski, Giovanni De Felice, Silvia Santini

原文摘要

Foundation models have recently extended beyond natural language and vision to time-series domains, including physiological signals. Yet developing foundation models for electrodermal activity (EDA) remains hindered by the absence of large-scale, curated, openly accessible datasets. EDA reflects sympathetic activity and is widely used to infer cognitive load, stress, and engagement. However, few wearable devices feature EDA sensing, and the only large-scale EDA archive to date is proprietary. To address this gap, we compile EDAMAME, a collection of EDA traces from 29 public datasets comprising approximately 23,000 hours of data from 731 users. Using this collection, we train UME, the first foundation model for EDA. As a frozen feature extractor, UME outperforms generic handcrafted features and matches generalist time-series foundation models while requiring 20x fewer computational resources; fine-tuning on the downstream tasks further yields additional performance gains in most experiments. UME also generalizes to EDA from two devices unseen during training. We further show that UME's performance improves as the amount of pretraining data grows, underscoring the importance of large-scale data for effective foundation models. Our findings highlight intrinsic challenges of EDA signals, revealing future research opportunities. We share EDAMAME under tiered access and also release model weights and code.

cs.LG · cs.AI · eess.SP

查看论文
arXiv ↗PDF ↗
版本更新 · v13arXiv:2507.14111

CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning

Xiaoya Li, Albert Wang, Guoyin Wang, Jiwei Li, Chris Shum

原文摘要

The exponential growth in demand for GPU computing resources has created an urgent need for automated CUDA optimization strategies. While recent advances in LLMs show promise for code generation, current SOTA models achieve low success rates in improving CUDA speed. In this paper, we introduce CUDA-L1, an automated reinforcement learning framework for CUDA optimization that employs a novel contrastive RL algorithm. CUDA-L1 achieves significant performance improvements on the CUDA optimization task: trained on A100, it delivers an average speedup of x3.12 with a median speedup of x1.42 against default baselines over across all 250 CUDA kernels of KernelBench, with peak speedups reaching x120. In addition to the default baseline provided by KernelBench, CUDA-L1 demonstrates x2.77 over Torch Compile, x2.88 over Torch Compile with reduce overhead, x2.81 over CUDA Graph implementations, and x7.72 over cuDNN libraries. Furthermore, the model also demonstrates portability across different GPU architectures. Beyond these benchmark results, CUDA-L1 demonstrates several properties: it 1) discovers a variety of CUDA optimization techniques and learns to combine them strategically to achieve optimal performance; 2) uncovers fundamental principles of CUDA optimization, such as the multiplicative nature of optimizations; 3) identifies non-obvious performance bottlenecks and rejects seemingly beneficial optimizations that actually harm performance. The capabilities demonstrate that, RL can transform an initially poor-performing LLM into an effective CUDA optimizer through speedup-based reward signals alone, without human expertise or domain knowledge. This paradigm opens possibilities for automated optimization of CUDA operations, and holds promise to substantially promote GPU efficiency and alleviate the rising pressure on GPU computing resources.

cs.AI · cs.DC · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.19697

Optimistic Deadlock Handling with Redo Log-Based Speculative Versioning under High Contention

Hyejin Yoo, Seongjae Moon, Jonghyeok Park, Viktor Leis, Sang-Won Lee

原文摘要

Modern OLTP engines rely on multi-versioning to eliminate read-write conflicts, yet their concurrency is severely limited by write-write conflicts. With immediate, in-place updates, only one transaction updates a record at a time, and the others wait for it to commit or abort. Conflicting transactions are thus serialized. We propose RCC, a Redo log-based Concurrency Control scheme for high write contention. A transaction updates a record out of place by creating a speculative write version from its redo log entry. With multiple speculative versions per record, conflicting transactions are pipelined without waiting for predecessors to commit. RCC guarantees serializability using lock-based access-time conflict ordering and dependency graph tracking. Updates are installed lazily at commit, so a transaction aborts by discarding its speculative versions. Based on this, RCC introduces two novel techniques. Optimistic deadlock handling decouples deadlock detection from lock acquisition: it grants locks without checking for deadlocks and detects cycles asynchronously in the dependency graph. Columnar RCC (RCC-C) removes record-level false conflicts with column-level redo logs. We implemented RCC on MySQL, PostgreSQL, and DBx1000. In TPC-C at 128 threads on a 128-core server, RCC improves throughput by up to 3.3x over the state-of-the-art schemes, and RCC-C improves it further by avoiding false deadlocks and aborts. On high-contention YCSB, RCC remains robust up to 128 threads, whereas other schemes degrade beyond 32.

cs.DB

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15675

Optimal-Time Independent Subset Sampling over Acyclic Joins

Xuyang Liu, Zijian Zhang, Zhen Li

原文摘要

Join results can greatly exceed their inputs even when applications need only a small random subset. We study sampling that includes each result independently with a prescribed probability given by the product of its input-tuple weights (PRODUCT). For fixed full acyclic joins with static weights, we achieve input-linear preprocessing and index space together with output-linear expected sampling work, eliminating logarithmic factors from previous bounds. A shared join-tree index supports weighted draws over the entire join and locates high-probability results. Direct Bernoulli trials handle high-probability results, allowing Poisson thinning to generate the remaining independent inclusion decisions with bounded overhead. Our exact sampler uses expected $O(N)$ preprocessing, $O(N)$ index space, and expected $O(1+mμ)$ time per call including output construction. Here $N$ is the input size, $m$ counts relation occurrences, and $μ$ is the expected sample size. The guarantees hold on a real random-access machine with unit-cost exact arithmetic and logarithms, continuous uniform randomness, and expected-time hashing. The time bounds are optimal, matching input reading and explicit output writing. Our floating-point prototype has lower sampling latency than the fastest applicable baseline in 17 of 18 PRODUCT settings on three queries over the STATS benchmark. Construction savings on large joins can offset indexed materialization's faster sampling over a limited number of calls. On a real-data path at $μ=100$, our sampler achieves a $20.5\times$ speedup over indexed materialization for construction plus 300 calls, measured after common data preparation and loading.

cs.DB · cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15671

The Noise Floor of a Quantization Comparison: Engine, restart, batch and kernel drift, measured against 8-bit and 4-bit effects in two decision models

Aleks Blagojevich, Trevor Sunderland

原文摘要

A quantized model is usually judged by comparing it with its BF16 original, but that comparison changes more than the weights. It often changes the serving engine, it always runs on a different server instance, it may change how requests are batched, and on some stacks the library selects a different kernel depending only on which packages import. We measure each of these sources on the same 2,400 public decisions for two of Cloudflare's decision models, Clef-flash (9B) and Clef (27B), on an NVIDIA GB10, and state every quantization effect as the excess over them. Sources that are not quantization move between 0 and 0.92% of decisions. llama.cpp restarts are bit-identical on every record for both models. vLLM restarts flip 0, 5 and 20 decisions at BF16, FP8 and NVFP4 on Clef-flash and 4, 0 and 22 on Clef; a third instance of Clef's quantized builds (exploratory) leaves FP8 at 0 and puts NVFP4 at 4 to 22, depending on which two instances are compared. An engine change at BF16 flips 6 to 16, a batch-size change 8 to 15, and the Gated DeltaNet kernel transformers selects unasked 10 to 14. Quantization inside one engine moves more: for Clef-flash and Clef, 0.88% and 1.04% at Q8_0, 2.12% and 1.62% at FP8, 5.79% and 3.50% at Q4_K_M, and 5.79% and 5.67% at NVFP4. On both models, every 4-bit interval excludes every non-quantization source. Two of our five pre-registered predictions failed, and the same two fail when the tests are rerun on the 27B: FP8 is not inside restart noise, and changing engine moves fewer decisions than 8-bit quantization does. Accuracy hides most of this. Over the full 31,275 public questions, Clef's Q4_K_M build moves accuracy by a net six questions (-0.02 points [-0.20, +0.16]) while 436 of its decisions get worse (exploratory), and NVFP4 costs Clef-flash 0.95 points and Clef 0.65. We release the code, quantization recipes, per-record outputs and the pre-registration.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15669

Online Vertex Connectivity Augmentation

Yaowei Long, Sepideh Mahabadi, Jakub Tarnawski

原文摘要

Network design problems form a classic subfield of online algorithms, but almost nothing is known about their more challenging vertex-connectivity variants. We initiate the study of online vertex-connectivity network design for arbitrary demand pairs by considering the fundamental problem of connectivity augmentation. In an instance of \emph{Online Vertex Connectivity Augmentation} (OVCA), we are given a $k$-vertex-connected graph $F$ and a set of additional purchasable edges (with costs). Demand pairs $(s_1,t_1),(s_2,t_2),\dots$ then arrive online. Upon each arrival, the algorithm must irrevocably purchase edges so that $s_i$ and $t_i$ become $(k{+}1)$-vertex-connected in the union of $F$ with all edges purchased so far. Our main contribution is an $O((k+\log n)\log n)$-competitive online algorithm for OVCA. We also give an offline $O(k+\log n)$-approximation algorithm. We obtain our algorithms via a structural dichotomy on the minimum vertex cuts of $F$. We note that some dependence on $k$ in the approximation ratio is necessary -- i.e., the problem is hard to approximate within any $\mathrm{polylog}(n)$ factor independent of $k$ -- which shows a separation from the edge-connectivity setting. Finally, specializing to $k=1$, our methods yield the first polylogarithmic-competitive online algorithm for a vertex-connectivity survivable network design problem, namely an $\widetilde O(\log^3 n)$-competitive algorithm for online $\{1,2\}$-VC-SNDP (i.e., an SNDP variant where each demand pair comes with a vertex-connectivity requirement of $1$ or $2$).

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15668

Beyond Reweighting: Certified Improvements from New Transitions in Discrete MCMC

Yishan Xi, Tinglan Wang

原文摘要

Optimizing transition probabilities on a fixed grap may leave substantial limitations on the efficiency of reversible Markov chain Monte Carlo (MCMC). We develop a framework for transition-support design that considers both allowed transitions and their stationary flows. For a fixed target distribution, observable, and node-flow budget, we derive a necessary and sufficient dual condition for support augmentation to strictly reduce the optimal value of the asymptotic variance, together with computable primal--dual certificates that establish improvements over every admissible original-support reweighting. We also construct a family in which adding a single edge reduces integrated autocorrelation time by an $Ω(n)$ factor relative to optimal original-support weighting, demonstrating that structural limitations can impose arbitrarily large relative losses in estimation efficiency. To realize these gains, we investigate energy-informed edge selection and constrained stationary-flow optimization. Experiments on molecular and Ising state graphs distinguish the potential value of new transitions from the performance of kernels constructed on them: on identical augmented Ising supports, full weight optimization certifies strict improvements in 24/24 conditions, whereas degree-based Metropolis--Hastings weighting certifies none. Our results provide a principled approach to characterizing, certifying, and exploiting transition-support improvements in explicitly represented finite state spaces.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.03999

Functional Stochastic Localization

Anming Gu, Bobby Shi, Kevin Tian

原文摘要

Eldan's stochastic localization is a probabilistic construction that has proved instrumental to modern breakthroughs in high-dimensional geometry and the design of sampling algorithms. Motivated by sampling under non-Euclidean geometries and the mirror descent algorithm in optimization, we develop a functional generalization of Eldan's process that replaces Gaussian regularization with regularization by any positive integer multiple of a log-Laplace transform. We further give a mixing time bound on the Markov chain induced by our localization process, which holds if our target distribution satisfies a functional Poincaré inequality. Finally, we apply our framework to differentially private convex optimization in $\ell_p$ norms for $p \in [1, 2)$, where we improve state-of-the-art query complexities in a zeroth-order model.

math.PR · cs.DS · cs.LG · math.ST · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.12491

Out-of-the-Box Tabular Foundation Models for Bayesian Optimization in Materials Discovery

Klemens Flöge, Simon Bing, Leo Grinsztajn, Eliott Kalfon, Lennart Purucker, Noah Hollmann, Frank Hutter

原文摘要

Bayesian optimization is widely used in active learning loops for materials science. Gaussian processes serve as the de-facto surrogate model family, but require task-dependent kernel choices and can lack the modeling capacity for complex relationships. Tabular foundation models (TFMs) have recently emerged as the state-of-the-art for predictive tasks on structured data, without requiring bespoke kernels or hyperparameter tuning. We evaluate two TFMs, TabPFN and TabICL, as out-of-the-box surrogate models on two standard materials science benchmarks, comparing against a large field of baselines encompassing Gaussian processes, random forests, and CatBoost. Our findings indicate that TFMs are highly competitive surrogate models across the two benchmarks, without task-specific training for active learning or GP kernel selection. Our results motivate developing TFMs further as surrogates for active learning in materials discovery.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15661

ALMeD: Medieval French Gold-Standard

Ragini Menon, Sabine Tittel

原文摘要

Medieval French is one of the Romance vernacular languages with a significant history of transmission and an enormous influence on other vernacular languages of the time. The sources convey valuable knowledge about all aspects of culture. The study of Medieval French has, over the last few years, increasingly benefited from NLP-based methods. There have been numerous efforts to parse medieval French; however, these efforts use corpora comprising legal texts and -- primarily -- literary texts as their foundation and training data. This means that, except for juridical resources, scientific literature is overlooked. We present ALMeD, an annotated, semantically rich corpus (work-in-progress) of medical and surgical treatises produced in medieval French, i.e., Old and Middle French, including Anglo-Norman. Our semantically disambiguated gold standard goes beyond existing resources, focusing on medical terminology, and accounts for morphological development, evolving syntactical structures and the lack of spelling normalisation in these languages.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15659

GraSLA: A Lightweight Spatial-Language-Action Model with Grasp Hypotheses as Geometric Priors

Jibao Yuan, Zixiang Zhao, Wensong Xu, Siqi Lu, Shaofei Chen

原文摘要

This paper focuses on improving the behavioral diversity and effectiveness of language-conditioned manipulation policies trained through imitation learning. Recently, continuous-action policies have become mainstream in robotic manipulation, but the lack of diverse demonstrations tends to restrict their behavioral diversity. For grasping, a fundamental subtask of manipulation, 6-DoF grasp detection provides diverse grasp hypotheses, but open-loop execution constrains responsiveness in dynamic environments. This motivates us to combine the diversity of grasp hypotheses with the adaptability of continuous-action policies. To this end, we propose GraSLA, a lightweight and effective spatial-language-action model with grasp hypotheses as geometric priors. In particular, we employ spatial and language foundation models to encode scene geometry and task semantics, and integrate them with grasp hypotheses through bidirectional cross-attention for continuous action prediction. On LIBERO, GraSLA achieves an average success rate of 99.30%.

cs.RO

查看论文
arXiv ↗PDF ↗