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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 06:41 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 07:45 — 2026-11-22 07:45(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:2026-11-22 06:41最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

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

找到 21,490 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 06:39(北京时间)
新论文 · v1arXiv:2611.20316

Solving the Discretised Shallow Water Equations on Distorted Structured Grids with Neural Physics

Boyang Chen, Claire E. Heaney, Christopher C. Pain

原文摘要

This paper presents a method for solving the shallow water equations on highly distorted structured grids using convolution-based operators following the Neural Physics approach. By mapping distorted physical grids to a uniform computational domain with Jacobian transformations, the governing advection and diffusion operators are reformulated in a structured convolutional form. This enables the use of efficient stencil-based operations and, following the Neural Physics concept, we do this through convolutional layers whose weights are determined by the chosen numerical methods rather than by training. The method introduces consistent mass-lumped formulations, conservative and non-conservative advection forms, and a diffusion operator, all expressed as convolutions. A nonlinear Petrov-Galerkin stabilisation is incorporated to control numerical oscillations on distorted meshes. Two approximations for the Laplacian operator are also proposed to accelerate pressure and diffusion solves. The framework is validated using the Carlisle 2005 flood event, demonstrating accurate predictions of water depth and velocity on distorted meshes for both linear and quadratic discretisations. The results show that distorted structured grids can retain conservation, stability and accuracy, whilst adapting the mesh statically. The convolutional formulation makes the method well suited to Neural Physics implementations and GPU acceleration, offering a scalable approach for flood modelling and large-scale geophysical simulations.

physics.comp-ph · cs.CE · physics.flu-dyn

新论文 · v1arXiv:2611.20314

NF-VLA: A Normalizing-Flow Baseline for Vision-Language-Action Learning

Ruichen Deng, Qinyu Zhao, Yong-Hyun Park, Mutian Tong, Liang Zheng, Jiatao Gu

原文摘要

Autoregressive normalizing flows (NFs) provide a tractable density for learning and sampling continuous robot actions. We show that a single maximum-likelihood objective can train vision--language--action (VLA) policies competitive with leading methods on manipulation benchmarks. We present NF-VLA, which combines conditional autoregressive normalizing flows with score-based action refinement. Its deep--shallow architecture concentrates visual, language, and proprioceptive prefix conditioning in a high-capacity deep block, while unconditioned shallow blocks provide a shared invertible action transformation. The vision--language backbone and flow are jointly trained by exact maximum likelihood on Gaussian-smoothed action chunks. The same learned density supplies a single score-based correction at inference, refining generated actions to account for training-time smoothing without a separately trained denoiser. Trained on LIBERO from a pretrained vision--language backbone without robot pretraining, NF-VLA achieves 98.35\% success across the four standard suites and 72.6\% on LIBERO-Plus using the same checkpoint without further fine-tuning. Ablations show that deep-only prefix conditioning and score-based refinement both improve closed-loop success. Together, these results establish carefully structured autoregressive flows as a competitive approach to VLA control, with one learned density supporting policy training, action generation, and refinement.

cs.RO · cs.AI

新论文 · v1arXiv:2611.20311

Reveal: A Provenance-Aware System for Multimodal Urban Data Exploration

Leonardo Ferreira, Joao Rulff, Maryam Hosseini, Aline Paes, Daniel de Oliveira, Fabio Miranda, Marcos Lage

原文摘要

Urban sensing initiatives increasingly produce multimodal datasets that combine visual and textual information to capture city characteristics and subjective factors such as safety, comfort, and accessibility. Yet, analyzing such data at scale remains difficult, as manual inspection is unfeasible and automated methods struggle to interpret subjective cues and uncover relationships across diverse data modalities. Moreover, existing workflows rarely make exploration steps explicit, hindering reproducibility. To address these challenges, we introduce Reveal, a provenance-aware visual analytics system for exploring heterogeneous urban data. Reveal enables users to build dataflows by combining text and image searches across coordinated views, chaining queries into pipelines, and applying set operations within an exploration diagram while capturing analytical provenance. We evaluate Reveal through two case studies focused on accessibility and walkability.

cs.HC · cs.CY · cs.MM

版本更新 · v3arXiv:2610.35235

Reconstructing False Alarm and Detection Rates in Quantum Machine Learning for Intrusion Detection

Roberto Fernández-Barrios, Iker Pastor-López, Asier González-Santocildes, Pablo García Bringas

原文摘要

Published results in quantum machine learning for intrusion detection (QML-IDS) require joint interpretation of false-positive rate (FPR), attack true-positive rate (TPR), and evaluation provenance. We reconstruct operating points in the 25-entry frame selected by Kaissar and colleagues: 21 included articles, 20 identified documentary families, substantive methodological material consulted for 15, and 24 descriptive points from five. In one test-labelled comparison, a quantum support vector machine reduces FPR from 6.875% for random forest to 3.329%, while TPR decreases from 93.955% to 93.682%; both rates improve against three other comparators. In another study, a complete benign row identifies FPR as 12/6000 (0.200%), despite incomplete attack-side allocation that requires additional assumptions for TPR. Normalized matrices identify detection ranges rather than a unique aggregate rate. A uniform provenance rule separates training-described and test-adjusted results from six conditional illustrations whose independence remains unverified. The contribution is a reproducible interpretation of favorable comparisons and detection trade-offs, without converting descriptive results or hypothetical calculations into operational guarantees.

cs.CR

新论文 · v1arXiv:2611.20307

PoCoAttn: Position-Content Collaborative Sparse Attention for Fast and High-Fidelity Video Generation

Jianwen Wu, Meiling Wang, Junkang Zhou, Yipeng Shen, Haoran You

原文摘要

Video diffusion transformers rely on 3D full attention over tens of thousands of spatiotemporal tokens, and its quadratic cost dominates inference latency. Sparse attention reduces this cost, but existing methods face a dilemma: static methods apply predefined masks and cannot capture input-dependent attention, whereas dynamic methods reconstruct the sparse mask repeatedly, paying online to rediscover positional structure that is largely stable across inputs. To this end, we propose PoCoAttn, a training-free sparse attention framework that separates input-stable from input-dependent attention and resolves the former offline and the latter online. PoCoAttn features: (1) A relative-offset analysis of 3D query-key pairs, which shows that video attention decomposes into an input-stable positional prior that carries most of the attention mass and a small content-dependent residual. (2) A position-content collaborative sparse attention mechanism, which retrieves positional keys from offline-calibrated tables, selects content keys online with a head-adaptive ratio between the two sources, and compensates for the discarded keys to approximate full attention. (3) A step-adaptive budget allocation algorithm, which models how early-step sparse attention errors are amplified along the denoising trajectory and derives the optimal sparsity budget per step. Extensive experiments across four video diffusion models and three tasks show that PoCoAttn consistently achieves a better speed-fidelity Pareto frontier than state-of-the-art (SOTA) methods, improving PSNR by 1.9 to 5.0 dB over baselines and delivering up to 4.1$\times$ attention and 2.0$\times$ denoising speedups over dense FlashAttention-3 attention.

cs.CV · cs.LG

新论文 · v1arXiv:2611.20306

Ontology-Compiled Control Barrier Functions for Heterogeneous Robot Teams

Peng Wu, Seyede Fatemeh Ghoreishi, Nathan Bastian, Mohsen Imani, Tian Lan, Mahdi Imani

原文摘要

Safety filters for heterogeneous robot teams fail because of missing constraints, overestimated braking capabilities and conflicts between individually satisfiable constraints. We present OntoCBF, which compiles a domain ontology with a class taxonomy, typed relations, safety axioms and a dynamics profile per robot class into a control barrier function filter with one quadratic program per agent. Description-logic entailment supplies the constraints of any team online, including those that follow from chains of relations and from classes defined by what a robot carries, so the existing safety axioms cover new robot classes, payload classes and combinations. We prove that a subclass may reuse the braking capability of its parent whenever it can produce every velocity of the parent, a property separate from subsumption. For box-bounded double integrators this property is also necessary, and every loss of safety then begins with a conflict. Once three robots interact, the safe set of pairwise barriers contains states from which a collision is unavoidable, and such states persist in larger teams under any fixed capability reduction. In a simulated warehouse where humans ignore the robots, a filter written for the design classes violates safety in 89-100 % of the episodes with unseen classes. In all scenarios, including one with 32 robots, OntoCBF violates safety in 20-70 % of the episodes, each time after a conflict, with a median deepest intrusion of 10-17 % of the keep-out distance. A multi-agent PPO policy trained with the filter in the loop lowers the rate of infeasible quadratic programs, nearly all of them conflicts, by 18-41 %.

cs.RO · cs.LG

新论文 · v1arXiv:2611.20301

Multi-output neural network surrogate for double-pulse femtosecond optothermal control of thin silicon films on fused silica

George D. Tsibidis

原文摘要

We introduce a multi-output feedforward neural network surrogate trained on a coupled multiple-reflection and two-temperature model to map double-pulse femtosecond laser excitation (1030 nm) of crystalline silicon films on fused silica across film thicknesses (50-500 nm) and inter-pulse delays (0-10ps). Trained via Levenberg-Marquardt optimization on 2000 physical simulations, the dual-hidden-layer network ([40,30] neurons) simultaneously predicts six strongly coupled optothermal observables, peak electron temperature, peak lattice temperature, peak carrier density, minimum and maximum absorptivity and minimum refractive index achieving coefficients of determination R2 larger than 0.9998 across all targets. Evaluating a dense 200 by 200 design grid in milliseconds resolves pronounced thin-film interference fringes and carrier-induced index modulation, identifying an optimal optothermal coupling regime at d=156 nm and Dt=4.572 ps. This unified machine-learning workflow eliminates computationally expensive multi-physics runtime bottlenecks for real-time laser processing control and inverse photonic thin-film design.

physics.optics · cond-mat.dis-nn · cond-mat.mtrl-sci · cs.AI

版本更新 · v2arXiv:2605.06288

A Topological Sorting Criterion for Random Causal Directed Acyclic Graphs

Alexander G. Reisach, Antoine Chambaz, Gilles Blanchard, Sebastian Weichwald

原文摘要

Random directed acyclic graphs (DAGs) based on imposing an order on Erdős-Rényi or scale-free graphs are widely used to generate synthetic data from causal models, in particular for evaluating causal discovery algorithms. We show that the set of nodes reachable via open paths, termed relatives, never decreases along the causal order in all DAGs. We find that it tends to increase strictly for DAGs with certain density parameters, and demonstrate that this pattern can be exploited for causal discovery via sorting by the estimated number of relatives. We note that many simulations in the literature are focused on a narrow range of parameter settings where sorting by relatives yields an excellent proxy for the causal order, and show that a strict increase of relatives leads to a singleton Markov equivalence class. We propose sampling time-series DAGs as a possible alternative and discuss implications for causal discovery and synthetic data generation. Implementations of our algorithms can be found at https://causaldisco.github.io/CausalDisco/.

stat.ME · cs.AI

新论文 · v1arXiv:2611.20297

Reliable Mining of Heterogeneous AI Coding-Agent Data: Context-Aware Prediction and Resource-Aware Ranking

Haoran Yu, Lifei Liu, Danping Zhang

原文摘要

Operational records from AI coding agents differ across agents, repositories, tasks, and workflows. We study 71,677 pull requests (PRs) from six agents and show that pooling these records can reverse descriptive and predictive conclusions. PRs carrying a co-authorship trailer have a 55.6% merge rate, compared with 77.5% without the trailer, but removing the dominant agent flips this -21.8 percentage-point gap to +23.7 points. We treat this Simpson-type reversal as a data-veracity problem and represent source, environment, and workflow context in a feature cascade. Gradient-boosting merge-prediction AUC increases from 0.774 to 0.832; the advantage persists under temporal evaluation (0.801) and unseen repositories (0.807). The co-authorship coefficient changes from -1.09 to +1.44 after conditioning, whereas repository-clustered AIPW intervals show no stable adjusted trailer association. A strict PR-creation-time model reaches 0.741 AUC in standard evaluation and 0.710 on unseen repositories, although its temporal AUC falls to 0.641. Finally, a separately cross-fitted analysis of an observed-mode functional estimates a +12.3-point doubly robust gain at a 30% allocation budget on the non-Codex population, only 0.5 points above risk ranking. This last result is retrospective decision support over metadata states, not a causal effect of assigning human review.

cs.SE

版本更新 · v4arXiv:2608.27296

LLMs Can Design Near-Optimal OR Algorithms

Jackie Baek

原文摘要

We ask whether large language models (LLMs) can design effective algorithms for well-specified operations research (OR) problems. We study inventory control, queueing network control, and assortment optimization, using benchmark instances from recent papers in each area. We evaluate two levels of LLM use: at level 1, the model receives one problem instance and returns a solution for that instance; at level 2, it receives only the problem class description and broad parameter ranges, and returns an algorithm that maps instance parameters to solutions. Human input is minimal: we give one untuned prompt that describes the problem, and the model has access to a Python sandbox tool with a fixed compute budget. The strongest model we test, gpt-5.6-sol, matches or outperforms the best method reported in those papers on almost all evaluated instances. This holds even at level 2, where the returned algorithm is fixed before seeing the evaluation instances. Performance also improves sharply across models released less than eight months apart, suggesting that this capability is moving quickly. Thus, for the well-specified operations problems we study, a single untuned LLM query can already produce algorithms competitive with specialized methods. These results suggest that frontier LLMs can be a serious empirical baseline for algorithm design in well-specified OR problems.

cs.AI · cs.LG

版本更新 · v2arXiv:2611.13058

The Indic Token Tax in 2026: Measuring Tokenizer. Disparity and Its Cost for the Languages of India

Johin Johny Arimbur, Ankur Ashit Ghosh, Shervin Sam

原文摘要

Commercial language model APIs bill per token, so a tokenizer that needs more tokens for the same content in one language makes that language more expensive, slower, and able to fit less text in a fixed context window. We measure this disparity for nine public tokenizers, including those of GPT-4, GPT-4o, Qwen2.5, DeepSeek-V3, Mistral-Nemo and four Sarvam models, on all 25 languages of India available in FLORES-200 (2,009 professionally translated sentences aligned with English) and on 13,732 human-translated Hinglish-English social media pairs from PHINC. On GPT-4o's tokenizer the same content needs between 1.57 times (Hindi) and 5.01 times (Odia) the tokens of English, and 13.7 times for Santali in Ol Chiki script; GPT-4's tokenizer needs up to 12.8 times. Sarvam-30B/105B is the only third-party tokenizer that stays below 2.6 times on every language (median 1.53). In an illustrative scenario using official list prices accessed on 5 November 2026 and stated assumptions, a support bot handling 100,000 chats a month on GPT-4o would cost about INR 56,640 in English and INR 102,829 in Marathi; these are estimates, not measured production costs. Against an openly licensed Hindi and Marathi morphological segmentation set, no tokenizer places more than 35% of its word-internal boundaries on morpheme boundaries (boundary F1 at most 0.48). In a companion paper we present a tokenizer that reduces this tax. Code, pinned artifacts and raw token counts are available at https://github.com/HavonAI/indic-token-tax.

cs.CL · cs.AI

版本更新 · v3arXiv:2603.00902

Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents

Ben Dong, Zhonghao Guo, Tianyi Lu, Qian Wang

原文摘要

Tool-calling LLM agents rely on third-party skills to extend their capabilities, but this openness exposes a supply-chain attack surface in which malicious skill instructions can manipulate agent execution across multiple turns. In this work, we present Clawdrain, a Trojanized OpenClaw skill that induces resource exhaustion through a Segmented Verification Process (SVP). SVP combines stateful progression, repair-driven repetition, and termination to create costly tool-calling chains while preserving a legitimate final payload. We evaluate Clawdrain in a production-like OpenClaw deployment with real API billing across Gemini 2.5 Pro, DeepSeek V4 Flash, and Claude Sonnet 4.6. Clawdrain achieves 2-16 times token amplification with plain SVP, while the three models exhibit distinct behaviors, including autoregressive compliance, proactive scripting, and extended trial-and-error reasoning. Our findings reveal that agent resource exhaustion arises not only from output generation, but also from repeated context re-ingestion, tool coordination, reasoning, and recovery, motivating system-level controls over cumulative skill behavior.

cs.CR · cs.SE

新论文 · v1arXiv:2611.20289

Benchmarking LLM Inference on Desktop-Scale NVIDIA Grace Blackwell Clusters

Kevin Bhimani, Christian Escobar, Daniel Mihovch, Rudolf Eigenmann, Sunita Chandrasekaran

原文摘要

Two NVIDIA DGX Spark GB10 systems connect directly over 200 GbE to serve larger language models and increase inference capacity, but the benefits depend on how they are deployed. We benchmark 17 open-weight checkpoints spanning dense and mixture-of-experts architectures, 8B to 235B parameters and four weight precisions on one and two RDMA-connected systems. Using vLLM, we compare tensor parallelism (TP=2), pipeline parallelism (PP=2) and a two-replica baseline at concurrency 1 to 64, with three independent launches per configuration. TP=2 delivers a median 1.59x peak-throughput gain over one Spark, versus 1.39x for PP=2 and has higher throughput in 93 of 96 matched comparisons with separated 95% Welch intervals. It reduces unloaded inter-token latency to 0.52x to 0.73x of one Spark, whereas PP=2 provides little reduction. TP=2 also achieves the highest goodput under a strict 100 ms inter-token latency objective wherever both strategies are supported and the objective is met. For models fitting on one Spark, TP=2 generally favors low-concurrency serving, while replication offers higher throughput at high concurrency. One Spark uses less GPU energy per output token at matched concurrency. Across three precision ladders, NVFP4 reduces unloaded latency more than adding a second Spark at BF16. NCCL microbenchmarks and comparisons with an earlier TCP campaign suggest that collective communication overhead contributes to the advantage of TP=2. These results provide deployment guidance for desktop-scale inference.

cs.DC · cs.AI

版本更新 · v3arXiv:2605.27380

BioELX: Context-Aware Cross-lingual Biomedical Entity Linking without Task-Specific Supervision

Yi Wang, Corina Dima, Liangyu Zhong, Steffen Staab

原文摘要

Cross-lingual biomedical entity linking (BEL) maps mentions in any language to unique identifiers in a biomedical knowledge base, supporting clinical and biomedical NLP applications. We identify two issues affecting current systems. First, the UMLS (Bodenreider,2004) aliases used to train cross-lingual BEL retrievers are heavily skewed toward English, so retrievers generalize poorly to non-English mentions. Second, although context is often necessary for disambiguation, naively injecting context into retrievers trained only to align aliases severely degrades retrieval. We propose BioELX, a retrieve-rerank framework that addresses both issues. For retrieval, we continue training SapBERT_multi (Liu et al., 2021b) using Wikidata-derived cross-lingual alias supervision, forming shared concept neighborhoods across languages. For reranking, we adapt pretrained LLM rerankers to entity linking through mention-anchored prompting, which marks the target mention so that rerankers score candidates with respect to the intended mention rather than other salient tokens in the context. Experiments show that BioELX achieves new state-of-the-art results on four cross-lingual BEL benchmarks, improving Recall@1 by 4.8 to 18.2 percentage points over prior best results, without any task-specific BEL annotations. Our code and resources are available at https://github.com/AI4MedCode/BioELX.

cs.CL · cs.AI

版本更新 · v2arXiv:2605.22668

SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers

Javad Rajabi, Kimia Shaban, Koorosh Roohi, David B. Lindell, Babak Taati

原文摘要

Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resolutions beyond their training range. Existing training-free approaches mitigate this by modifying inference-time attention behavior, often through Rotary Position Embeddings (RoPE) extrapolation combined with attention scaling. However, these strategies apply a uniform and content-agnostic scaling across RoPE components with distinct frequency characteristics, inducing a trade-off between preserving global structure and recovering fine detail. We introduce SEGA, a training-free method that dynamically scales attention across RoPE components according to the latent's spatial-frequency structure at each denoising step. This adaptive scaling improves both structural coherence and fine-detail fidelity. Experiments show that SEGA consistently improves high-resolution synthesis across multiple target resolutions, outperforming state-of-the-art training-free baselines.

cs.CV

版本更新 · v2arXiv:2611.09767

From PAC bounds on the generalization error to PAC bounds on the parameter estimation error

Mihaly Petreczky, John Leth, Emma Lukacs, Balint Daroczy

原文摘要

Probably Approximately Correct (PAC) bounds on the generalization error, the difference between the true prediction error and the empirical prediction error, are an established tool in statistical machine learning, and there have been several extensions of these bounds to dynamical systems. In parallel, in recent years, there has been growing interest in finite-sample bounds for parameter estimation error in system identification. The latter bounds tend to be algorithm-specific, relying on reformulating the identification algorithm as a least-squares regression problem. This is in contrast to classical PAC bounds, which are algorithm-agnostic and can be applied to any identification algorithm based on minimizing a cost function involving the empirical loss. In this paper, we show how oracle bounds derived from PAC bounds can be used to obtain finite-sample bounds for dynamical systems. As an illustration of this approach, we present finite-sample parameter-estimation bounds for linear and bilinear systems with bounded inputs and noise. These bounds apply to identification algorithms based on minimizing the empirical loss function.

cs.LG

版本更新 · v2arXiv:2602.22505

Sharp Convergence Rates for Masked Diffusion Models

Yuchen Liang, Zhiheng Tan, Ness Shroff, Yingbin Liang

原文摘要

Discrete diffusion models have achieved strong empirical performance in text and other symbolic domains, with masked (absorbing-rate) variants emerging as competitive alternatives to autoregressive models. Among existing samplers, the Euler method remains the standard choice in many applications, and more recently, the First-Hitting Sampler (FHS) has shown considerable promise for masked diffusion models. Despite their practical success, the theoretical understanding of these samplers remains incomplete. Many existing analyses are conducted in Kullback-Leibler (KL) divergence, which often yields loose parameter dependencies and requires strong assumptions on score estimation. Moreover, these guarantees do not cover recently developed high-performance sampler of FHS. In this work, we first develop a direct total-variation (TV)-based analysis for the Euler method that overcomes these limitations. Our results relax assumptions on score estimation, improve parameter dependencies, and establish convergence guarantees without requiring any surrogate initialization. Also for this setting, we provide the first convergence lower bound for the Euler sampler, establishing tightness with respect to all of the data dimension $d$, the vocabulary size $S$, and the target accuracy $\varepsilon$, up to logarithmic factors. Finally, we analyze the FHS sampler and show that it incurs no sampling error beyond that induced by score estimation, which we show to be tight with a matching lower error bound. Our analysis introduces two techniques that may be of independent interest: a comparison with a reference unmasking schedule for the Euler method and a pathwise argument exploiting the decoupling structure of FHS.

cs.LG · stat.ML

新论文 · v1arXiv:2611.20279

Functional Information, Optimal Channel Simulation and Lossy Source Coding

Gergely Flamich, Spencer Hill, Fady Alajaji, Tamás Linder

原文摘要

We characterize, within a constant number of bits, the minimum achievable rate for several one-shot coding problems, such as channel simulation and lossy source coding. The basis of our work is a new information measure between random variables $X, Y$ that we call the functional information $I_F(X \to Y)$. We show that this quantity characterizes the minimum one-shot rate $R^*(X \to Y)$ of channel simulation, in which a sample $Y \sim P_{Y \mid X}$ is communicated in the presence of common randomness: $I_F(X \to Y) \leq R^*(X \to Y) < I_F(X \to Y) + 1.45$. For the achievability result, we construct an explicit code using the Poisson functional representation. Using these results, we develop new bounds for one-shot variable-rate lossy source coding: given some distortion measure $Δ$, we use $I_F(X \to Y)$ to define the functional rate-distortion function $R_F$. Then, letting $R_O$ denote the one-shot operational rate-distortion function with private encoder randomness and distortion measure $Δ$, we make use of our channel simulation result to show that $R_F(D) \leq R_O(D) < R_F(D) + 2.45$ at every positive distortion level $D$. Finally, we generalize our channel simulation result by introducing the Rényi $α$-functional information $I_{F, α}(X \to Y)$ and show that it characterizes the minimum Arimoto-Rényi conditional entropy for channel simulation, ${R^*_α(X \to Y)}$, associated with the Campbell cost: ${I_{F, α}(X \to Y) \leq R^*_α(X \to Y) \leq I_{F, α}(X \to Y) + O(1/α)}$.

cs.IT

新论文 · v1arXiv:2611.20278

Visual Marking as a Native Reasoning Capability for Multimodal LLMs

Jiazhen Liu, Yanghao Wang, Chaolei Tan, Long Chen

原文摘要

Visual reasoning often requires maintaining intermediate spatial states that are difficult to express in text. Existing approaches either rely on external drawing tools or image generators, or encode these states in latent tokens without explicit spatial correspondence to the input image. We introduce SelfMark, which enables MLLMs to construct and use visual marks directly in their native visual feature space. By treating the visual token grid as a canvas, SelfMark establishes explicit spatial correspondence between marks and images. This is achieved through a locate-mark-read procedure, where the model identifies relevant locations, constructs task-dependent mark features, and reads the resulting visual features to guide its reasoning. We jointly train a single model on spatial planning, dense counting, high-resolution VQA, and line tracing. Across six benchmarks, SelfMark outperforms state-of-the-art MLLM-based methods specialized for individual tasks. These improvements also persist with a stronger backbone, demonstrating the effectiveness of visual marking across different model capabilities. Overall, SelfMark provides a unified approach to visual reasoning by integrating spatially grounded marks directly into the visual feature space of MLLMs.

cs.CV

新论文 · v1arXiv:2611.20277

A Bleichenbacher bit-by-bit oracle attack from partial message knowledge

Juan Carlos García Escartín

原文摘要

Oracle attacks show the importance of a correct implementation of cryptographic standards when translated into code. A notable example is the Bleichenbacher attack on RSA with PKCS#1 v1.5 padding and all the improvements that have been suggested over the decades. This paper shows how an attacker knowing a few least significant bytes of an RSA message can take advantage of a server with an oracle side-channel to decrypt the full message bit by bit. We will consider two oracles that can be tested with chosen ciphertexts: one revealing whether the decrypted message starts with the 00 02 bytes and a second one revealing if the decrypted message is fully PKCS compliant. For an attacker knowing the three least significant bytes of the message, the first oracle provides an attack where one oracle call gives the next least significant bit of the message and the second an attack which requires, with high probability, a small constant number of oracle calls to the oracle, with a constant which depends on the length of the message and the desired probability of success. The attack divides the message bits into two sections, one with the known part and one with the unknown part, and then chooses transformations that will keep the unknown part, except for the last unknown bit, orders of magnitude below the integer coming from the known part. The resulting string either gives a valid padding or not depending on the value of the unknown bit. The attacker can minimize the number of oracle calls at the cost of some local computation. Finally, the same method is adapted to show how it can also be used to extract the few least significant bytes of the message with an increased cost where the main complexity is finding a second valid message with a correct padding starting from the original captured ciphertext.

cs.CR

新论文 · v1arXiv:2611.20275

The Manifold-Index Model: provably and efficiently avoiding the statistical and computational curse of dimensionality

Yantao Wu, Mauro Maggioni

原文摘要

We study vector-valued regression with predictors filling a tube around an unknown $m$-dimensional manifold $\mathcal{M}$ in $\mathbb{R}^D$. In the Manifold-Index Model, the mean response is $F=f\circΠ_{\mathcal{M}}$, where $Π_{\mathcal{M}}$ is the nearest-point projection onto $\mathcal{M}$ and $f:\mathcal{M}\to\mathbb{R}^p$ is a possibly non-injective link function. Multiscale ANisotropic lOcal Regression (MANOR) estimates tangent planes by multiscale PCA of predictors with similar responses, then refines them by pooling outer products of local slopes. The neighborhoods narrow tangentially while retaining complete normal fibers. We assume a Lipschitz link differential and bounded response noise. For $p\ge m$, under our geometric and sampling conditions, $n$ independent observations give mean tangent-space error of order $n^{-2/(m+4)}$ and integrated squared prediction error at the $m$-dimensional nonparametric rate $n^{-4/(m+4)}$, up to logarithmic factors. In a scaling regime with fixed intrinsic dimension, model and scale parameters, and ratio of manifold volume to the $m$-th power of its reach, the required sample size grows polynomially in $D+p$, and computation is polynomial in $n$, $D$ and $p$. Numerical experiments on curves with non-monotone links and surfaces with vector-valued responses compare observed convergence rates with the theoretical bounds; a Langevin dynamics example tests prediction of hitting probabilities under an approximate manifold-index model.

stat.ML · cs.LG · math.ST

版本更新 · v2arXiv:2611.04033

Exploring the Power Consumption of ERC-4337 Bundling on Server Infrastructure

Claudiu-Nicu Bărbieru, Oana-Otilia Captarencu, Pascal Felber, Emanuel Onica, Valerio Schiavoni, Cosmin-Nicolae Vârlan, Boris Verdecia Echarte

原文摘要

The Ethereum ecosystem offers the most widespread support for Decentralised Applications (DApps), with over 120 networks currently documented as using variants of the Ethereum Virtual Machine (EVM) for core execution logic. The ERC-4337 standard provides convenient access to DApps for users who do not possess the required cryptocurrency or prefer flexible authorisation of DApp actions. The infrastructure for ERC-4337 implementation can be deployed on any EVM network. However, to aggregate user requests and submit them to the EVM network, ERC-4337 requires operating a bundler, an additional component. Recently, the potential use of ERC-4337 was boosted by another standard, EIP-7702, which can enable ERC-4337 utility for any existing user account. However, the use of the combined EIP-7702/ERC-4337 pattern remains considerably low at less than 6% of EIP-7702 activity. We believe that this underutilisation is at least partly caused by the low number of existing bundling services and their popularity, currently fewer than 15 publicly documented. Expanding the number of bundler nodes would benefit the ecosystem but would introduce operational costs, part of which is represented by the added nodes' power consumption. In this paper, we provide a thorough view of the bundling power consumption aspect using server-grade infrastructure, evaluating both CPU and RAM consumption, as well as the overhead of container-based deployments specific to production environments.

cs.NI · cs.PF

新论文 · v1arXiv:2611.20269

Self-supervised learning for zebrafish embryo phenotype evaluation: Systematic comparison of algorithms, label-efficient classification, and transfer learning

Thomas Lautenschlager, Gaëlle Hayot, Quentin Brassart, Angelo Jovin Yamachui Sitcheu, Linus Schilpp, Tijana Geroski, Tetyana Goldanova, Stephan Allgeier 等 13 位作者

原文摘要

Zebrafish embryos are a prominent model organism for image-based phenotyping and especially suited for large-scale imaging studies, for which machine learning (ML) models can automate evaluation. However, training ML models usually requires large labeled datasets, and differences in imaging conditions often impede reuse across laboratories. Self-supervised learning (SSL) addresses both constraints by learning transferable representations from unlabeled images. Yet central aspects like the choice of algorithm remain underexplored for domain-specific applications. To close this gap, we benchmark popular SSL algorithms on the public EmbryoNet dataset, explore label-efficient learning, and test transfer to an unseen setting. Using representations from our strongest model, a ResNet50 network trained with SwAV, a simple linear classifier reaches 86.4% accuracy and a non-linear classifier 87.1%, rivaling the fully supervised EmbryoNet model (87.1%). The SwAV model decisively outperforms supervised training from scratch when labels are scarce (70.2% vs. 45.7% accuracy with 5% of labels). On a three-class problem (normal, dead, falsely cropped) with a small, previously unseen zebrafish toxicity dataset, recorded in a different setting, our model reaches 81.3% accuracy without retraining, while EmbryoNet achieves 75.9%. Overall, self-supervised models for zebrafish embryos seem to mostly facilitate label-efficiency and transfer to new settings rather than improving supervised results.

cs.CV · cs.AI · cs.LG

版本更新 · v2arXiv:2606.08377

From Estimates to Schedules: Learning-Augmented Restricted Assignment

Michalis Xefteris

原文摘要

In this work, we study Restricted Assignment scheduling on multiple machines, where each job can be processed only on a specified subset of machines and the objective is to minimize the makespan. We consider a learning-augmented setting in which the predicted assignment is not required to be feasible. The prediction error (moved-load) is measured by the total processing volume that must be reassigned in order to obtain an optimal feasible schedule. Using a single prediction, we obtain two types of guarantees. First, we design an algorithm whose approximation ratio degrades smoothly with the prediction error while retaining a worst-case guarantee independent of the prediction quality. More precisely, for any fixed constant, we can make the additive dependence on the prediction error arbitrarily small, at the cost of increasing the polynomial running time. This guarantee can also be combined with any approximation algorithm for the problem without predictions to obtain robustness. Second, given a makespan estimate, we provide a repair procedure that returns a schedule matching this estimate in time parameterized by the prediction error. This allows the algorithm to exploit the separation between estimation and approximation algorithms for Restricted Assignment. Finally, we complement the repair algorithm with a parameterized hardness result, showing that exact moved-load repair with a given target makespan is W[1]-hard when parameterized by the amount of moved-load.

cs.DS

新论文 · v1arXiv:2611.20268

GNN-Based Deep Reinforcement Learning for Coastal Emergency Response under Extreme Water Levels

Marcello Sano, Samuele Casagrande, Davide Ferrario, Sebastiano Vascon, Silvia Torresan, Andrea Critto

原文摘要

When a storm surge approaches a coastal town, the emergency plan must be put into action quickly using water-level forecasts, flood extent, road access, vulnerable residents and shelters. Bringing this information together under time pressure is slow and depends on the duty officer's expertise. This paper is one step in a wider research line from data to safe decisions: machine learning to understand the hazard, reinforcement learning and planning to choose actions, large language models (LLMs) to explain and cross-check them, and an assurance layer that keeps people in charge. Here we address the action step on a real place. We ask whether a policy can learn the timing of emergency actions from decades of real events. Lido di Venezia is represented as a heterogeneous graph built from public elevation, road, building and census data and driven by hourly tide-gauge records from 1983 to 2024, with seven actions taken from the municipal emergency plan. A PPO policy is trained on this graph and compared, on storm windows unseen in training, with a rule-based system simulating the officer's discretionary decisions. On 18 historical test scenarios, PPO achieves a similar reduction in population exposure to the rule. With uncertain forecasts and limited protection it again performs similarly but does not outperform the tuned rule, and removing graph message passing does not substantially reduce performance. PPO therefore learns an effective protective response from an outcome-based reward alone: it is given the plan's actions and when each is allowed, but not the thresholds that tell the comparator when to act. Next steps test harder edge cases, move closer to a digital twin of the territory, and replace the simulated officer with assessment by emergency-management stakeholders, supported by LLM-based interpretation of each recommendation.

cs.LG · cs.AI

版本更新 · v2arXiv:2506.15887

Fair Contracts in Principal-Agent Games with Heterogeneous Types

Jakub Tłuczek, Victor Villin, Christos Dimitrakakis

原文摘要

Fairness is desirable yet challenging to achieve within multi-agent systems, especially when agents differ in latent traits that affect their abilities. This hidden heterogeneity often leads to unequal distributions of wealth, even when agents operate under the same rules. Motivated by real-world examples, we propose a framework based on repeated principal-agent games, where a principal, who also can be seen as a player of the game, learns to offer adaptive contracts to agents. By leveraging a simple yet powerful contract structure, we show that a fairness-aware principal can learn homogeneous linear contracts that equalize outcomes across agents in a sequential social dilemma. Importantly, this fairness does not come at the cost of efficiency: our results demonstrate that it is possible to promote equity and stability in the system while preserving overall performance.

cs.GT · cs.LG · cs.MA

新论文 · v1arXiv:2611.20261

Estimating Outpatient Visit Prices from Hospital Price Transparency Data using Large Language Models

Kurmanbek Kaiyrbekov, Nicholas J Dobbins, Sean D Mooney

原文摘要

Objective: Hospital care prices in the United States have increased substantially, yet patients lack effective tools to access and compare costs. We aimed to develop and evaluate an LLM-based approach for improving access to and use of hospital price transparency (PT) data. Materials and Methods: To estimate visit prices, we used a retrieval-augmented generation (RAG) framework to analyze PT files from three major hospitals in Maryland and the surrounding region. We compared BM25, OpenAI embedding models, and a GPT-BM25 hybrid against a no-RAG baseline for cost estimation of individual procedures and procedure groups, then evaluated the best approach for symptom-based visit cost estimation using synthetic simulations. Results: Across hospitals, the GPT-BM25 retriever achieved the best performance, with average price MAPE of 19.44% for individual procedures and 4.90% for groups, compared with 147.98% and 82.82%, respectively, for the no-RAG baseline. In simulations, our framework correctly identified approximately 50% of reference procedures and reduced MAPE relative to the LLM-only baseline at two of the three hospitals, while achieving comparable performance at the third. Discussion: Our framework uses RAG to improve care price estimation in real-world settings. Compared with the no-RAG baseline, it substantially improved cost estimates for both individual procedures and procedure groups. Improvements were smaller in synthetic simulations, likely because inferring procedures from clinical information is more complex. Practical challenges remain, including heterogeneous PT file formats, unexplained duplicate entries, and limited availability of insurer-negotiated rates. Conclusion: LLMs that effectively integrate PT data show strong potential to provide patients with more accessible and accurate healthcare cost estimates.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.20259

Scaling large language model-assisted line-of-therapy adjudication with human-in-the-loop evidence-calibrated selection

Olatunji Oni, Sanhita Sengupta, Marc De Benedetti, Nathanial Eddy

原文摘要

Large language models (LLMs) have enabled the ability to scale clinical adjudication tasks traditionally dependent on exhaustive manual review. Line-of-therapy (LoT) adjudication, a major bottleneck in oncology cohort construction, is a prime example. Line boundaries must be inferred from longitudinal treatment histories according to nuanced, study-specific definitions, at every regimen transition for every patient. LLMs can apply this adjudication at scale, but their reliability varies across patients. Treatment histories differ in complexity, and ambiguous or atypical patterns depend on expert clinical judgment. Reliable automation thus requires verified support for model assignments and the ability to identify cases that warrant manual review. Here, we present evidence-calibrated selection (ECS), a human-in-the-loop framework for scaling LLM-assisted LoT adjudication. ECS derives confidence from observed clinician adjudications, prioritizes patients with the least-supported assignments for follow-up review, and returns completed adjudications to the model as precedent. As the evidence base grows, ECS continuously calibrates confidence to estimate residual error, thus enabling more efficient use of clinician time. In simulations on 136 clinician adjudicated patients with multiple myeloma, ECS achieved a residual error of 5% after review of 44.6% of patients, compared to 62.2% when review was directed by LLM self-reported confidence and 81.9% under random sampling. These results support a scalable approach to study-specific LoT adjudication, using clinician evidence to inform automated predictions, minimize error, and reduce review burden.

cs.LG · q-bio.QM · stat.AP

新论文 · v1arXiv:2611.20258

Microfitting: Continual Learning via Cached Test-Time Training

Nick Ryan, Peter A. Devine, Ben Sirb, Hannah Sansford, Alex Chiocchi

原文摘要

Continual learning is a promising approach to specialize language models to an organization's private data. However, current methods exhibit a number of drawbacks including catastrophic forgetting, where new training updates overwrite prior knowledge. We present microfitting, which trains and caches a small adapter for each document. Each adapter is trained once, offline, on synthetic questions targeted at demonstrated base-model shortcomings and reused whenever that document is queried. This method borrows from test-time learning literature and sidesteps the problem of continual learning through parameter isolation, allowing the system to specialize on new data without overwriting prior knowledge. The process that generates adapter training data also improves over time, revising its recipe from previous outcomes and fresh examples of the target workload. On DeepSeek V4 Flash, microfitting substantially improves accuracy over the base model. In Enterprise Document Operations (EDO), an open-book Q&A environment over real-world enterprise documents, our method achieves a 38.2% relative improvement over base-model performance. Microfitting makes continual specialization practical and cost-efficient: a frozen model can adapt to an evolving private corpus overnight on local hardware, without modifying the base model or previously cached adapters.

cs.LG · cs.AI

新论文 · v1arXiv:2611.20255

Deep Sequence Model for Genome Wide Discovery of Coding and Regulatory Element Signatures

Rayhaneh Shabani Nia, Ali Karkehabadi

原文摘要

Interpreting deep neural networks for genomic sequence classification remains challenging despite strong predictive performance. We develop a lightweight CNN with post-training gradient-based analysis to identify which sequence positions drive coding versus intergenomic classification. Applied to the standardized demo_coding_vs_intergenomic_seqs dataset, our model achieves 91.87% validation accuracy while revealing interpretable patterns: nine hot spots with consistently high importance, clear class-specific separation at positions 20-100 (coding) and 150-190 (intergenomic), and a strong mean-variance correlation (r = 0.530) indicating robust discriminative features. Gradient-based importance analysis shows that the model implicitly learns biologically meaningful sequence distinctions without explicit annotations. This work demonstrates that neural network interpretability and accuracy can coexist, providing a framework for understanding genomic sequence classification and enabling biology-driven hypothesis generation.

cs.LG · q-bio.GN