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

+758新增论文
+578其中 AI 相关
+94已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 04:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 08:06 — 2026-11-17 08:06(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-17 04:58最近发现新增版本:2026-11-17 04:58库内论文最新更新时间:2026-11-14 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。

24,106 已收录论文20,158 AI 相关7,049 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 24,106 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
版本更新 · v2arXiv:2610.07473

From Dialogue to Diagnostic Hypotheses: Evaluating LLM Agents for Psychiatric Assessment

Milad Mohammadi, Fatemeh Akrami Shamsabadi, Zahra Mohseni, Amirhossein Safdarian, Malekfarhad Malek, Hadi Moradi, Hesham Faili

原文摘要

Although LLMs show promising diagnostic reasoning on supplied clinical evidence, their ability to elicit such evidence through free-form psychiatric interviews remains less understood. We evaluate interview quality and diagnostic hypotheses using simulated patients and human participants. For controlled simulation, we introduce PsyCPG, transforming clinical cases into structured patient profiles. On 30 paired cases, experts rate PsyCPG simulations higher in quality than raw-case role-play (4.50 versus 3.83/5). We introduce PsyCIDRA, a dual-agent framework: its interviewer agent uses a notepad tool, expert-written skills, and ICD-11 reference tools to guide interviews; its diagnostic agent analyzes the transcript and produces a report for expert review, ranking differential diagnoses with supporting, conflicting, and missing evidence. Across four models and 53 development cases, PsyCIDRA achieves higher observed diagnostic agreement than direct prompting. On 81 held-out simulated cases, exact-code rank-1 accuracy reaches 60.5% versus 51.9%. We conduct 101 interviews with human participants; two psychologists, blinded to interview condition and model reports, independently assess interview quality and transcript-supported hypotheses. In separate arms, PsyCIDRA agrees with experts on whether to issue a hypothesis in 79.6% of cases versus 65.4% for direct prompting. This study provides an empirical basis for understanding and evaluating LLM agents in free-form psychiatric interviewing.

cs.AI

新论文 · v1arXiv:2611.09746

基于连续小波变换特征提取的人血浆样本激光诱导击穿光谱分类

Continuous wavelet-based feature extraction for laser-induced breakdown spectroscopy classification of human plasma samples

Md Mahmudur Rahman, Atqiya Munawara Mahi, Nazim Ahmed Belabbaci, Mohammad Arif Ul Alam

AI 速读 基于摘要

该研究评估用连续小波变换(CWT)从激光诱导击穿光谱(LIBS)中提取谱峰特征,并结合SVM区分SARS-CoV-2阳性与阴性人血浆样本。

cs.AI

查看原文摘要

Extracting discriminative features from laser-induced breakdown spectroscopy (LIBS) spectra is important for the classification of complex biological samples. This study evaluates continuous wavelet transform (CWT)-based spectral peak extraction for distinguishing human plasma samples labeled as SARS-CoV-2-positive or negative. Plasma specimens from 181 individuals, comprising 53 positive samples and 128 negative controls, were deposited as 5 μL droplets on silicon substrates and dried before analysis. Spectra were acquired using a nanosecond Nd:YAG laser operating at 1064 nm, with 100 single-shot measurements collected per specimen and averaged after intensity-based outlier rejection. CWT-based peak detection was coupled with a support vector machine (SVM) classifier. The reported leave-one-out evaluation yielded an accuracy of 93.00%, sensitivity of 94.67%, and specificity of 91.61%; these estimates remain provisional pending reconciliation with specimen-level predictions. Features identified by the CWT pipeline included emission lines assigned to Ca II, K I, and N I. The workflow provides a basis for examining spectral features associated with the studied plasma groups. Independent validation and assessment of specimen, substrate, and acquisition-related variability are required to establish generalizability and diagnostic relevance.

新论文 · v1arXiv:2611.09745

多尺度闭运算指数(MCI):用于度量二维点集间结构相似性

Multiscale Closing Index (MCI) for measuring structural similarity between 2D point sets

Nicolò Zava, Angel Franco-Alvarez, Samy Blusseau, Santiago Velasco-Forero, Maria-Jose Jimenez

AI 速读 基于摘要

作者提出一种基于多尺度数学形态学、取值在0到1之间的二维点集结构差异度量MCI,并在合成点云上考察其对多种扰动的响应。

math.MG · cs.CG · cs.CV

查看原文摘要

We introduce Multi-scale Closing Index (MCI), a new dissimilarity measure for evaluating the alignment of two 2D point sets. MCI is bounded between 0 and 1 and is based on multiscale mathematical morphology operations, with smaller values indicating greater structural agreement. The measure was motivated by the need to assess the quality of registration between point sets representing cell populations in biological images. To evaluate its behaviour under controlled conditions, we generated synthetic point clouds from Perlin-noise-based spatial structures, following established approaches for simulating biologically plausible spatial organization. We assessed MCI between those point clouds and different transformed versions, obtained by local perturbation, point removal, translation, rotation and addition of impulsive noise. Across these experiments, the dissimilarity MCI increased gradually and consistently with perturbation severity, while showing a clear discontinuity between clouds originating from the same underlying spatial structure and point clouds generated from different structures. We further compared MCI with commonly used point-set distances, including Hausdorff-based measures and Sliced Wasserstein distance. These experiments show the ability of MCI to capture structural agreement and quantify deviations between point sets, highlighting its potential as a complementary metric for evaluating two-dimensional point-set registration.

新论文 · v1arXiv:2611.09744

面向分层架构恢复的QAOA:可行性、局限与分解的作用

QAOA for Layered Architecture Recovery: Feasibility, Limits, and the Role of Decomposition

Julien Cardinal, Andrew Chedid, Imen Benzarti, Ghizlane El Boussaidi, Christophe Pere, Jean-Marc Robert

AI 速读 基于摘要

该研究将分层架构恢复(LAR)建模为QUBO并用QAOA求解,发现分解比增大电路或采样预算更关键。

cs.SE

查看原文摘要

Layered architecture recovery (LAR) reconstructs a system's architectural layers from its package dependencies, and is defined as a combinatorial optimisation problem solved with classical search. We investigate whether the Quantum Approximate Optimization Algorithm (QAOA) can be applied to LAR, and with what practical limitations. We formulate LAR as a Quadratic Semi-Assignment Problem, transform it into a Quadratic Unconstrained Binary Optimisation (QUBO) problem in which each package is penalised unless it is assigned to exactly one layer, and encode it as an Ising Hamiltonian solved by QAOA. To reach instances beyond the qubit budget of a single circuit, we also apply an impact-guided decomposition that solves the problem as a sequence of smaller sub-problems. We evaluate the approach on three real Java systems ($15$, $18$, and $24$ qubits), studying the effect of circuit depth and sampling budget (RQ1), a comparison with a classical Tabu Search baseline (RQ2), robustness to simulated quantum noise (RQ3), and the decomposition (RQ4). We find that monolithic QAOA is feasible and accurate on the two smaller systems but fails on the $24$-qubit instance, that the sampling budget rather than circuit depth governs its accuracy, and that it is competitive with but does not outperform Tabu Search. Decomposition restores reliable recovery on the $24$-qubit instance, raising the optimal rate from $6.7\%$ to $93.3\%$; its accuracy is governed by the size of each sub-problem and, unlike the monolithic pipeline, improves as the sampling budget is reduced. Our results indicate that, in the current noisy intermediate-scale regime, problem decomposition, rather than larger circuits or more sampling, is the key to applying QAOA to software architecture recovery.

新论文 · v1arXiv:2611.09741

NIH资助的图谱计划中学科内与跨学科的研究合作

Research Collaborations Within and Across Disciplines in NIH-Funded Atlas Programs

Michael P. Ginda, Yongxin Kong, Katy Börner

AI 速读 基于摘要

该研究比较HTAN、HuBMAP和SenNet三个NIH图谱联盟的内部合作模式及其与科学影响力的关系。

cs.SI · cs.DL

查看原文摘要

The National Institutes of Health (NIH) fund several programs (aka consortia) that support the construction of organ-specific or whole person atlases. These initiatives are designed to build comprehensive open reference datasets while advancing knowledge graphs, analytics, visualizations, and user interfaces needed to explore multiscale human atlas data. Here, we compare the Human Tumor Atlas Network (HTAN), Human BioMolecular Atlas Program (HuBMAP) and Cellular Senescence Network (SenNet) to examine collaboration by consortium component (CC) and researcher role and its relation to scientific impact. We retrieved 884 NIH award records and identified 1,255 focal publications acknowledging these awards, involving 8,952 researchers; compiled 99,108 citing publications covering 93% of the focal publications; constructed co-authorship networks; and as single-project publications or internal collaborations (IC), including intra-CC and inter-CCs collaborations. within each atlas program. Results show that IC publications are rare but involve many funded projects and principal investigators (PIs). Technology-oriented CCs tend to engage in intra-CC collaboration, whereas experimental-oriented CCs often collaborate across CCs of the same type. Compared with other researchers, PIs exhibited a significantly stronger association with inter-CCs than with single-project publications. IC publications have higher mean Relative Citation Ratios than single-project publications. Inter-CCs publications have significantly higher cumulative and annual citation levels in the first five post-publication years. Study methods and results can be used to inform the funding, management, and impact reporting for future Big Science programs that bring together 300+ experts from different disciplines to address major research challenges.

新论文 · v1arXiv:2611.09740

统一多模态模型在浅水无人机图像畸变评估与复原中的零样本基准测试

Zero-Shot Benchmarking of Unified Multimodal Models for Shallow-Water UAV Image Distortion Assessment and Restoration

Dario Scilla, Omar A. Lopez, Mattia Rosso, Kasper Johansen, Matthew F. McCabe

AI 速读 基于摘要

作者报告了首个针对统一多模态大模型在浅水无人机图像水致畸变评估与复原上的系统性零样本基准,结果显示识别畸变并不等于能可靠复原。

cs.CV

查看原文摘要

Shallow-water UAV imagery provides centimeter-scale observations of benthic environments, but water-induced distortions complicate interpretation. To our knowledge, we present the first systematic zero-shot benchmark of unified multimodal large language models (MLLMs) for both assessing water-induced distortions and restoring shallow-water imagery within the same model framework. We evaluate five open-weight unified MLLMs with frozen pretrained weights and without access to paired reference images or descriptions of the true seabed. The benchmark contains 1,000 image pairs: 600 semi-synthetic UAV scenes created by applying synthetic water distortions to real shallow-water imagery and 400 fully synthetic through-water scenes. Three independent human annotations cover five distortion types. We evaluate four assessment prompts (P0-P3), from direct instruction to structured task decomposition, on all 1,000 images and four diagnosis-guided restoration prompts (R0-R3) on a common 100-image subset. Assessment varies substantially by model and prompt, with systematic prediction biases and a best pooled balanced accuracy of 0.654 for distortion presence. The best pooled PSNR gain is +0.255 dB, no unified MLLM improves pooled LPIPS, and some outputs alter scene structure or hallucinate content. Two restoration-only baselines also show limited transfer: InstructIR achieves a pooled PSNR gain of +0.040 dB, while PromptFix degrades all four pooled metrics under every prompt. These results show that recognizing shallow-water degradation does not imply reliable physical restoration and provide a reproducible baseline for future work.

新论文 · v1arXiv:2611.10098

Autonomous Code Review: Hidden-Test Results on GitHub Issues

Adam Shakhabov

原文摘要

Can an autonomous cross-provider review step change whether code written for a real issue passes hidden tests? We report a retrospective benchmark of 12 historical GitHub issues (five C#, five JavaScript, and two Python) from five repositories. Two directed author--reviewer pairs, OpenAI GPT-6.1-Sol and Anthropic Claude Sonnet 5.5, each ran twice per issue, yielding 48 planned workflows. A bounded terminal agent produced an initial patch; a cross-provider model reviewed it; the author model adjudicated findings and could revise the patch. The same hidden evaluator assessed initial and final patches. Forty workflows completed, while eight terminated before a complete evaluator outcome. Four completed workflows passed, and all four already passed before review. No initial-to-final pass/fail transitions occurred among completed workflows.

cs.SE

新论文 · v1arXiv:2611.09736

安全是 Π₁,可证性是 Σ₁:一个统一框架解读 Hugging Face 泄露事件与 OpenAI 的数学证明

Safety Is $Π_1$, Provability Is $Σ_1$: One Framework for the Hugging Face Breach and OpenAI's Mathematical Proofs

Jinho Kang, Jinsook Kim

AI 速读 基于摘要

作者用其混合框架把 Hugging Face 泄露与 OpenAI 大量 AI 生成数学证明视为同一“统计提议器+演绎验证器”循环,并以 Π₁/Σ₁ 的逻辑形式差异解释为何安全难以保证而可证性可由单个证明实例确认。

cs.LG · cs.AI · cs.CR · cs.LO

查看原文摘要

OpenAI's agents breached Hugging Face in July 2026, and the same company released more than seven hundred AI-generated manuscripts of mathematical proofs in October 2026. The first event is read as a failure in security, while the second is read as a success in mathematics. We read both through the hybrid framework of our paper (Kim and Kang, 2026, arXiv:2611.01914), in which coding, proving, and learning from data are derivations by one and the same deductive mechanism, distinguished by the kinds of premises from which they are derived. Under this framework, the AI systems behind the two events ran the same loop, in which a statistical proposer produces candidate exploits or proofs and a deductive verifier settles each one by a derivation. What separates the events is the logical form of the statement wanted by each of the two domains, security and mathematics. The safety of a program is a $Π_1$ statement, for it says that no exploit exists, which is not assured by any finite list of tests that have been passed by the program. By contrast, the provability of a sentence is a $Σ_1$ statement, for it says that a proof exists, which is assured by a single instance, namely a proof that has been checked by the deductive verifier. The theorem behind both is Turing's Undecidability Theorem: the halting set is $Σ_1$ but not decidable, so its complement is $Π_1$ and not $Σ_1$, which is to say that membership has a finite witness but non-membership has none. We prove that attaching a statistical proposer to a deductive verifier does not change this undecidability result, however good the proposer is. We then discuss what does assure safety and where the residual risk goes.

新论文 · v1arXiv:2611.09735

5G-NetBotSim: A Synchronized Co-Simulation Framework for Connected Robots over ROS and srsRAN-based 5G Network

Narges Golmohammadi, Bhaskara Venkata Raju Garuda, Ayan Joshi, Sabur Baidya

原文摘要

Connected robotic applications increasingly rely on wireless communication for teleoperation, coordination, and distributed autonomy. However, robotic simulators often use ideal links or abstract delay models that do not capture cellular scheduling and protocol processing effects. We present 5G NetBotSim, a realtime co simulation framework integrating ROS/Gazebo workloads with an executable, full stack srsRAN 5G network emulator. The framework provides isolated User Equipment (UE) robot contexts and stage level timing across the host, gNB, UE, ROS, and robot execution stages. We evaluate human to robot teleoperation and robot to robot leader follower coordination under controlled channel quality conditions. Results show how CQI and MCS variations propagate to throughput, communication latency, and robot performance. In leader follower coordination, higher channel quality reduces mean tracking error from 0.558 m to 0.460 m, a 17.6% reduction. These results demonstrate protocol stack in the loop co simulation for joint network and robotic-application evaluation.

cs.NI

新论文 · v1arXiv:2611.10097

A Privacy-Aware Deep Learning Benchmark for Facial Emotion Recognition

Larissa Palhares, Maria Machado, Hudson Bruno, Raphael Ramos, Andrew Vale, Barbara Barbosa, Inara Souza, Fabio Grassiotto

原文摘要

Facial Expression Recognition (FER) traditionally relies on raw RGB images, introducing privacy risks, sensitivity to illumination variations, and susceptibility to identity-confounding visual shortcuts. As an alternative, this work proposes a lightweight, privacy-aware pipeline using exclusively geometric representations-facial landmarks (478 points) and blendshapes (52 coefficients, ARKit standard)-eliminating persistent raw video storage. Six neural architectures trained from scratch on fused CREMA-D and RAVDESS datasets were benchmarked against an ImageNet-pretrained ResNet50 baseline under a 5-fold subject-independent cross-validation protocol. Geometric models consistently outperformed the pixel baseline on unseen subjects with 12-124 times fewer parameters, while demonstrating superior robustness on subtle emotional expressions such as sadness. Ablation studies reveal that blendshapes capture the primary discriminative signal, while landmarks provide essential complementary spatial topology. These results demonstrate that compact geometric representations preserve affective semantics, eliminate downstream transfer learning dependency on visual backbones, and enable efficient, privacy-aware emotion recognition.

cs.CV · cs.AI

版本更新 · v2arXiv:2605.11884

Sobolev Regularized MMD Gradient Flow

Chenyang Tian, Bharath K. Sriperumbudur, Arthur Gretton, Zonghao Chen

原文摘要

We analyze Sobolev descent, a regularized variant of maximum mean discrepancy (MMD) gradient flow based on a gradient penalty on the MMD witness function. This regularization mitigates the non-convexity of the MMD objective, and yields provable \emph{global} convergence guarantees in MMD, in both continuous and discrete time. A surprising appeal is that our convergence analysis does not rely on isoperimetric assumptions on the target distribution. Instead, it is based on a regularity condition on the difference between kernel mean embeddings. We extend Sobolev descent such that it is applicable in both sampling (from an unnormalized target distribution)---using Stein kernels---and generative modeling settings, unlike previous works, where a gradient flow is suitable for only generative modeling or sampling but not both. We empirically validate the method on a broad range of tasks across both settings.

cs.LG

新论文 · v1arXiv:2611.09734

GuardrailAgent: An Agentic Framework for Jailbreak Defense

Tianze Chang, Junjie Chu, Yixin Wu, Michael Backes, Yang Zhang

原文摘要

Despite undergoing safety training to align with human values, large language models (LLMs) remain vulnerable to jailbreak attacks that circumvent built-in safeguards and elicit malicious behaviors given by the adversary. Existing defenses are mostly static and fail to adapt to new or unknown attack strategies, providing limited resilience. To address these, we propose a multi-agent defense framework, GuardrailAgent, that offers adaptive, end-to-end protection. The system autonomously gathers and summarizes attack characteristics into a continuously updated knowledge base that supports both input- and output-side detection. A feedback module integrates misclassified cases for iterative improvement at minimal cost. Tested on over ten representative jailbreaks, the framework achieved a 93.1% input-side detection rate, 93.9% overall detection, and a 95.8% F1 score, while rapidly adapting to unseen attacks. These results demonstrate GuardrailAgent's outstanding capability to maintain LLM safety in the face of evolving jailbreak tactics.

cs.CR

新论文 · v1arXiv:2611.09733

Metric Dimension Parameterized by Bag-Connected Treewidth and Bag-Connected Pathwidth

Dibyayan Chakraborty, Sebastian Ordyniak, Sebastian Siebertz

原文摘要

The metric dimension of a graph is the minimum size of a set of vertices whose distance vectors distinguish all vertices of the graph. We prove that \MetricDimension{} is NP-complete on planar graphs of treewidth and bag-connected treewidth exactly three. The graphs in our construction have no induced cycle longer than four and have (prefix-connected) pathwidth at most four. In particular, the problem admits no XP algorithm parameterized by bag-connected treewidth unless $\mathrm P=\mathrm{NP}$. This answers questions of Bonnet and Purohit and of Bousquet, Deschamps, and Parreau. We prove that the problem is fixed-parameter tractable when parameterized by bag-connected pathwidth.

cs.CC

新论文 · v1arXiv:2611.10096

Coordinated Mixed-Precision KV Cache Quantization for Efficient LLM-based Multi-agent Systems

Weizhong Huang, Jinchao Zhang, Xiawu Zheng

原文摘要

LLM-based multi-agent systems solve complex tasks through collaboration, but their growing, simultaneously resident key-value (KV) caches create a memory bottleneck. Applying single-model quantization policies independently ignores differences in agents' precision needs, potentially degrading collective reasoning. We introduce Coordinated Mixed-Precision KV Cache Quantization (CoMixKV), which combines online sensitivity estimation with joint agent-layer bit-width allocation under a shared memory budget. To our knowledge, CoMixKV is the first mixed-precision KV-cache quantization framework to jointly allocate precision across simultaneously resident agent caches under such a budget. The estimator derives sensitivity from a local attention-error bound using recent queries, keys, and values, without calibration data, trial quantization, or additional model passes. A shared controller combines these scores with remaining quantizable capacity and byte-level storage costs to minimize total estimated error. Allocations are refreshed as agents start or finish and new observations become available. Selected widths apply only to newly quantized blocks; recent states retain native precision and previously quantized blocks remain unchanged. Across four benchmarks and three LLM backbones at average 2-bit, 3-bit, and 4-bit settings, CoMixKV achieves strong accuracy against the evaluated quantization baselines. At the average 3-bit setting on Gemma-4-31B-it, it achieves 68.35% average accuracy, exceeding the strongest quantized baseline by 0.59%. On Qwen3-32B, it reduces peak KV-cache memory by 32.08% and achieves a 1.38x inference speedup over FullKV.

cs.LG

新论文 · v1arXiv:2611.09730

What to Delegate, What to Preserve: Human Preferences for Agentic AI Across Everyday Life and Work

Sarah Wheeler, Veronica Rammouz, Yaoyao Qian, Zexuan Liu, Mengyi Wei, Anthony Rios, Tianzhi He, Kyrie Zhou

原文摘要

AI agents can execute multi-step tasks on users' behalf, yet the boundaries of acceptable delegation remain unclear. We report a scenario-based survey of 289 U.S. adults with prior AI experience covering 45 use cases across nine life domains. Each respondent evaluated one scenario per domain, producing repeated measures of automation preference, trust, collaboration, AI leadership, privacy concern, and willingness to pay. Automation preferences varied substantially across domains. Generalized estimating equation models showed that greater trust in the AI agent, desired AI leadership, prior task-specific AI use, and anticipated financial savings were associated with greater automation preference. In contrast, concerns that automation would reduce personal fulfillment predicted lower automation preference. Open-ended responses further revealed a preference for bounded autonomy, with participants often favoring substantial AI execution while retaining human involvement, oversight, or final authority. We argue that delegation is best understood as a configuration of execution, collaboration, leadership, and authority.

cs.AI · cs.HC

新论文 · v1arXiv:2611.09729

One Run Is Not Enough: A Monte Carlo Protocol for Evaluating LLM Reliability on Data Science Tasks

Wenqi Ni, Ozan Evkaya, Miguel de Carvalho

原文摘要

Large language models (LLMs) have shown promise for automating data science workflows. Benchmarks such as DataSciBench (2026) and StatQA (2024) have advanced the evaluation of their capabilities across data science and statistical tasks. Assessing their reliability requires examining both the quality of their responses and their consistency across repeated runs, task types, and difficulty levels. With this aim, we introduce DS-QA, a benchmark comprising 100 data science and statistics questions drawn from UK university courses, spanning 16 datasets and three difficulty levels. We develop a three-layer evaluation framework that combines general response properties (runtime, verbosity and text similarity), coarse-grained metrics (accuracy, code executability and completeness), and task-specific metrics. We evaluate OpenAI models using a Monte Carlo protocol with 100 repeated runs. The results reveal substantial variability in responses to data visualisation and supervised learning tasks, particularly at medium and hard difficulty levels, highlighting the importance of evaluating consistency alongside response quality. We also find that an increase of 0.1 in the word verbosity ratio corresponds to an increase of about 0.013 in the token verbosity ratio.

cs.LG

新论文 · v1arXiv:2611.10095

Adaptive Budgeted Data Acquisition for Robust Off-Policy Evaluation from Multiple Loggers

Amitakshar Biswas, Ruoqing Zhu

原文摘要

We consider off-policy evaluation when additional data can be purchased from several existing logging policies (or loggers) with heterogeneous costs per observation. While existing work on multiple loggers presumes a fixed number of observations from each logger, we study how to allocate a limited budget across them sequentially to evaluate a finite class of target policies. We propose Adaptive Greedy, an algorithm that purchases observations sequentially from the affordable logger that has the most cost-normalized variance reduction across the target policies. It turns out that each such purchase is an 'approximate conditional-gradient step' for the corresponding design problem. Under mild assumptions, we establish that the empirical allocation converges almost surely to the optimal design at an explicit rate. We also derive the asymptotic normality of the final pooled estimator and show that it attains the semiparametric efficiency bound. Simulations and a semi-synthetic application based on the AIDS Clinical Trials Group Study 175 show that Adaptive Greedy outperforms standard allocation strategies, remains accurate if stopped early, and matches the final accuracy of repeated integer programming at a fraction of its computational cost.

stat.ML · cs.LG

新论文 · v1arXiv:2611.09728

SAGE-PAIR: Source-Pretrained Routed Residual Adaptation for Sparse-Feedback Recommendation

Weiqing Zeng, Zida Yang, Guquan You, Jiexin Zheng, Cong Wang

原文摘要

Recommendation systems often enter a new serving window before enough outcomes are available to retrain the deployed model. We study this regime with 0.05-1.0% target feedback, a range that spans our stress tests while keeping supervision far below the degrees of freedom of the source recommender. At this scale, existing fine-tuning and meta-learning methods still estimate target-specific updates from extremely sparse feedback, leaving the update direction weakly identified. SAGE-PAIR instead transfers a source-supported residual correction space and only calibrates this space using target outcomes. We introduce SAGE-PAIR, a staged adapter that pretrains a low-dimensional global residual on an adjacent source period and adds a soft router over residual experts conditioned on source user profiles. Target feedback then calibrates this residual state rather than relearning the recommender. On a locked test split of KuaiSAR-v2, SAGE-PAIR (Full) achieves a 1.77% relative improvement in NDCG@10, while a core-protocol comparison shows a further 0.25% gain from routed experts beyond source-pretrained PAIR. Matched source-pretrained LoRA and Adapter-Tuning baselines remain near the source model, supporting the need for a different adaptation space. Thus, SAGE-PAIR improves ranking quality with millisecond-scale adaptation and inference costs. Sparse-feedback adaptation is fundamentally governed by the identifiability of the update space rather than by label count alone. Source pretraining supplies estimable correction directions for scarce labels, while user-conditioned routing contributes a consistent, differentiated cross-user correction on top of the global correction. Our code is available at https://anonymous.4open.science/r/SAGE-PAIR-610E/.

cs.IR

版本更新 · v2arXiv:2605.09630

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models

Lin Zheng, Vasilisa Bashlovkina, Timothy Dozat, Dan Garrette, Laura Rimell, Joshua Maynez

原文摘要

Tokenizer-free language models eliminate the tokenizer step of the language modeling pipeline by operating directly on bytes; patch-based variants further aggregate contiguous byte spans into patches for efficiency. However, the average patch size chosen at the model design stage governs a tight trade-off: larger patches reduce compute and KV-cache footprint, but degrade modeling quality. We trace this trade-off to patch lag: until a patch is fully observed, byte predictions within it must rely on a stale representation from the previous patch to preserve causality; this lag widens as patches grow larger. We introduce Scratchpad Patching (SP), which inserts transient scratchpads inside each patch to aggregate the bytes seen so far and refresh patch-level context for subsequent predictions. SP triggers scratchpads using next-byte prediction entropy, selectively allocating compute to information-dense regions and enabling post-hoc adjustment of inference-time compute. Across experiments on natural language and code, SP improves model quality at the same patch size; for example, even at $16$ bytes per patch, SP-augmented models match or closely approach the byte-level baseline on downstream evaluations while using a $16\times$ smaller KV-cache over patches and requiring roughly $3$-$4\times$ less inference compute than the byte-level baseline.

cs.CL · cs.LG

新论文 · v1arXiv:2611.10093

Contrastive fine-tuning against stain and scanner bias improves robustness and downstream performance across pathology foundation models

Ryan Kim, Hassan Muhammad, Anish Dulal, Paul S. Scotti, Tanishq Mathew Abraham

原文摘要

Histopathology foundation models achieve strong performance across diverse downstream tasks, yet their representations have been shown to encode scanner- and site-specific biases, creating generalization gaps and potentially limiting real-world utility. We introduce SPECTRA (Scanner and Pathology Embedding Contrastive Tuning for Robust Alignment), a model-agnostic contrastive learning post-training framework which explicitly encourages scanner- and stain-robust representations, to optimize performance and generalization on downstream applications. Using parameter-efficient LoRA adapters trained on matched multi-scanner and multi-stain whole-slide images sourced from the PLISM dataset, our method aligns spatially corresponding regions across acquisition conditions (scanner, stain), using other locations within each candidate condition as negatives. SPECTRA improved PathoROB robustness index, gene-expression prediction on HEST, slide-level classification AUC on CPTAC, and held-out PLISM retrieval for every model. Overall tile-level classification on THUNDER also improved, with exceptions for segmentation and calibration tasks. We open-source our training and evaluation codebases and release adapters and model weights for selected backbones.

cs.CV

新论文 · v1arXiv:2611.09725

TriNetra: Thermal-Reliability-Guided RGB-Thermal Fusion and Tracking for Surveillance

Sadique Khatib, Aditya Ahirrao, Vedant Sonawane, Disha Kapse, Y. D. Bhise

原文摘要

Visible cameras fail at night and thermal sensors fail under saturation, blur or loss of contrast, yet most RGB-thermal (RGB-T) detectors mix the two streams with fixed weights and cannot tell when one modality has become unreliable. TriNetra is a reliability-aware surveillance framework built around this problem. The proposed solution computes a frame-level Thermal Reliability Coefficient (TRC) from five label-free image cues, uses it to gate the thermal features of a dual-branch YOLOv8m detector whose visible branch, neck and head are frozen and COCO-pretrained, and passes the same score to a ByteTrack-based tracker that feeds a rule-based behaviour analyser. On the M3FD benchmark (2,940/630/630 split) the detector reaches 87.6% precision, 79.4% recall, 70.0% mAP@50 and 47.8% mAP@50:95 on the test split, with 17.0 M of its 42.9 M parameters trained. TRC stays near 0.78 on clean frames (standard deviation 0.012), decreases with the severity of thermal saturation and blur, reaching 0.53 and 0.69 at full severity, and is insensitive to RGB-thermal misalignment. With identical weights, the adaptive gate matches a fixed gate on clean data (70.0% versus 69.8% mAP@50) but keeps 43.6% mAP@50 when the thermal stream is corrupted, against 38.4%, 29.2% and 25.0% for a fixed gate, full thermal admission and a closed gate; the 5.1-point gain over the fixed gate has a 95% bootstrap confidence interval of +3.6 to +6.5 points. In tracking, the TRC-gated association performs on par with ByteTrack on a synthetic benchmark with exact ground truth and on 14 M3FD clips, and is slightly less stable under thermal saturation, so its measured benefit is confined to the detector. The limitations of the current evaluation are reported together with the results.

cs.CV

版本更新 · v2arXiv:2605.28001

What Does a Copyright Budget Certify? An Exact Threshold for Per-Token Meters, and a Length-Independent Certificate for Selection

J. Vijayavallabh

原文摘要

Certified inference-time copyright defences publish a divergence budget between the served model and a safe anchor trained without the protected works. We ask what such a budget certifies. Proved: a budget of K nats says nothing about a work whose surprisal under the anchor is at most K, at every Rényi order. Anchored decoding charges per token, so its budget grows with the output. Measured: at its authors' setting, the budget exceeds the anchor's surprisal of every one of the 758 protected passages we test, so it certifies nothing about them. Proved: serving one of n anchor draws, by any rule, is certified at log n nats for the whole output, at any length; in installments, a window is certified only given the text up to a block boundary. Measured: over a vetted anchor, with an adversarial scorer, selection reproduced no protected passage near-verbatim. Its draws cost 21.8x a metered decode on an anchor-only server. Judged: in the headline configuration, at the only published meter budget that bounds a 50-token window, selection's gain over one anchor draw is reliably positive and the meter's is, by a post-hoc equivalence test, zero. At matched compute selection loses. At the authors' sampling settings on the 8B, the two tie at that budget. Where the meter's certificate is vacuous, the ranking depends on how the stronger model is served. It reverses under a chat template, at the authors' sampling settings on the 8B, and on AlpacaEval.

cs.AI · cs.CR

新论文 · v1arXiv:2611.09723

Fixed-point acceleration on Neural Wasserstein manifolds

Vitalii Aksenov, Sebastian Gutierrez Hernandez

原文摘要

We propose a fixed-point acceleration method for optimization over probability measures, applicable to a variety of machine learning problems. We represent probability measures as pushforwards of a reference distribution through a neural network map and equip the parameter space with the induced pullback Wasserstein metric. This geometric structure allows natural gradient descent to be interpreted as a fixed-point iteration on a Riemannian manifold. We accelerate this iteration using Riemannian Anderson mixing method, which exploits historical residuals to capture approximate second-order information without forming Hessians. In the present parametric setting, the manifold is represented by Euclidean coordinates endowed with a point-dependent metric, simplifying retraction and vector transport. We evaluate the method on multimodal sampling, PDE-based inverse problems, aggregation dynamics, Bayesian logistic regression, and generative modeling. Across the tested tasks, Anderson mixing reduces the number of natural-gradient iterations and achieves competitive performance relative to SGD and Adam in terms of both loss-gradient evaluations and wall-clock time. These results suggest that fixed-point acceleration is an efficient tool for improving the computational efficiency of training on parametric Wasserstein methods.

cs.LG · math.OC

新论文 · v1arXiv:2611.09722

FOSCAR: Accelerating Decode Attention over 2- and 4-Bit KV Caches through Affine Folding

Donglin Zhuang, Pragaash Ponnusamy, Xiaoxia Wu, Shuaiwen Leon Song, Zhongzhu Zhou

原文摘要

Large-language-model decode attention streams the key-value (KV) cache for every generated token. Packing that cache into 2-bit or 4-bit quantized integers reduces memory traffic but does not automatically translate into latency saving. Existing 2-bit fused kernels reach under 31%/15% of peak HBM throughput on H100/B200. Converting each value and applying its scale and offset before feeding Tensor Cores is a major bottleneck because instruction-issue throughput is scarce on modern GPUs. Instead of applying scale and offset to each KV value, FOSCAR uses affine folding to apply them to the other operand or the output of decode-attention matrix products, depending on the quantization scheme (token-wise or channel-wise). This reduces scale-and-offset operations by up to two orders of magnitude while preserving the dequantized attention output in exact arithmetic. FOSCAR also uses bit manipulation to feed KV operands to Tensor Cores efficiently, requiring only 1 and 0.19 ALU instructions per INT2 element on H100 and B200, respectively. Finally, FOSCAR builds warp-specialized GPU pipelines for Hopper (H100) and Blackwell (B200) using wgmma and tcgen05. On H100, FOSCAR INT2 and INT4 kernels achieve geo-mean speedups of $3.36\times$ and $2.83\times$ over FlashInfer BF16, and $2.03\times$ and $1.71\times$ over TensorRT-LLM FP8. On B200, the corresponding INT2 and INT4 speedups are $2.67\times$ and $2.30\times$ over FlashInfer BF16, $1.48\times$ and $1.28\times$ over TensorRT-LLM FP8, and $1.16\times$ and $1.00\times$ over TensorRT-LLM NVFP4. We integrate FOSCAR into SGLang to benchmark serving efficiency. On long-context serving workloads, FOSCAR increases peak aggregate throughput by up to 170% and 341% over 2-bit and 16-bit baselines, respectively. We open-source FOSCAR as a kernel library at https://github.com/FutureMLS-Lab/FOSCAR.

cs.AI

新论文 · v1arXiv:2611.09721

MemoryDojo: Benchmarking Poisoning Through LLM Agent Memory

David H. Yang, Blake Bullwinkel, Amanda Minnich, Mohammad Mohammadi Amiri, Giorgio Severi

原文摘要

LLM agents benefit from using memory systems to improve performance on long-horizon, multi-session tasks. However, memory introduces a critical attack surface. Malicious instructions encountered in one session may be stored and propagated through memory before being retrieved and acted upon in later sessions. Because memory systems differ in how they process and retrieve information, the downstream effects of poisoning can vary significantly across systems. To quantify the effects of poisoning across different memory architectures, we introduce MemoryDojo, a benchmark for tracing the lifecycle of poisoned information through agent memory and measuring its influence on subsequent agent behavior. MemoryDojo is easily extensible, consists of 155 multi-session long-horizon trajectories covering four domains, and supports five different memory systems. Through our evaluation, we find that all memory systems are susceptible to memory poisoning, with substantial variation in downstream effects. We further propose a memory-aware poison optimization process that increases the poisoning efficacy, highlighting differences between memory architectures. We hope that MemoryDojo will support research on understanding and mitigating agentic memory risks.

cs.CR · cs.AI · cs.CL

版本更新 · v3arXiv:2605.07013

CoBit: Language Modeling with Bitstream Diffusion

Georgios Batzolis, Mark Girolami, Luca Ambrogioni

原文摘要

We introduce CoBit, a continuous diffusion language model that generates text by jointly denoising fixed-width binary token codes. Grouping each code's bits into a single Transformer patch preserves sequence length while replacing vocabulary-wide predictions with $\lceil\log_2 V\rceil$ bit logits. A matched-filter residual parameterization supplies the analytic isolated-bit posterior, leaving the network to learn contextual corrections. Stochastic sampling on an entropy-rate grid provides the largest empirical gain; the grid allocates both solver resolution and effective Langevin correction to noise levels where information is resolved. At 256 denoiser evaluations, CoBit-S (130M parameters) achieves generative perplexity 59.76 on LM1B and 27.06 on OpenWebText, at unigram entropies 4.31 and 5.26, respectively. Scaling to 462M parameters improves OpenWebText generative perplexity to 19.48 at entropy 5.40. Beyond open-ended text generation, CoBit achieves 65.9% exact-match accuracy on hard Sudoku. On GSM8K, score-temperature scaling with an untempered final integration step raises CoBit-S accuracy from 28.1% to 35.3% without additional denoiser evaluations, placing it within the reported range of temperature-tuned discrete diffusion baselines. Matched-trunk profiling also shows lower peak memory and higher throughput than a dense token-output baseline.

cs.CL

版本更新 · v2arXiv:2602.06909

Revisiting the Generic Transformer: Deconstructing a Strong Baseline for Time Series Foundation Models

Yunshi Wen, Wesley M. Gifford, Chandra Reddy, Lam M. Nguyen, Jayant Kalagnanam, Anak Agung Julius

原文摘要

The recent surge of interest in Time Series Foundation Models has rapidly advanced the field. Yet, heterogeneous training setups across studies make it difficult to determine whether performance improvements came from architectural innovations or effective data engineering. In this work, we investigate whether a standard patch Transformer architecture, paired with a straightforward training protocol, can match the zero-shot forecasting performance of state-of-the-art TSFMs. We conduct a comprehensive ablation study covering model scaling, data composition, and training techniques to examine the ingredients behind this performance. Our findings show that pretraining data composition, contiguous patch masking, and context length have a substantial effect on forecasting accuracy, and that the generic architecture itself can deliver high performance with good scalability. By strictly controlling these experimental variables, we provide comprehensive empirical results on model scaling across multiple dimensions. Furthermore, we establish that the effectiveness of this training protocol generalizes robustly across benchmarks and alternative architectures. We release our pretrained models and document the detailed training protocol and findings to establish a transparent, reproducible baseline for future research.

cs.LG

版本更新 · v2arXiv:2610.25344

TOMORI: A Tool-Orchestrated Mixing Operator for REAPER Interaction

Yining Wang, Tianjiao Li

原文摘要

Code-based agents can operate creative software, but mixing requests often describe an intended sound without specifying the edits needed to achieve it. We present TOMORI, a code-based mixing-agent harness for native digital audio workstation (DAW) control. Custom plugins provide REAPER project inspection, optional audio measurement, and execution of model-generated Lua code. All observations return as text; delivery includes an editable project and rendered audio. TOMORI-BENCH pairs 110 human-reviewed reference edits with three instruction forms and evaluates native DAW execution end to end through operation structure, parameter precision, and rendered-audio outcomes. Across 990 cases from three primary models, explicit instructions yield high reference agreement, while abstract requests reduce project agreement and audio improvement. Paired ablations show that the full workflow improves explicit execution over a single submission. Prompted audio measurement succeeds in all 28 selected abstract cases but yields no clear overall improvement on the reference-based metrics and increases tool calls. These results expose the gap between executable DAW control and precise realization of perceptual mixing goals.

cs.SD · eess.AS

新论文 · v1arXiv:2611.09717

Direct Regression and Geometric Recovery for Event-based Spacecraft Pose Estimation

Pruthvi Nandan Janga, Kashyap Hegde Kota, Bharatesh Chakravarthi

原文摘要

Event cameras offer high temporal resolution and dynamic range for uncooperative spacecraft pose estimation, but models trained on synthetic event streams must generalize to the noise, background activity, and contrast variation of physical sensors. We present a comparative systems study of two independently developed approaches to synthetic-to-real, event-based 6-DoF spacecraft pose estimation. The first is a modular pipeline that combines learned keypoint detection and unlabeled target-domain adaptation with geometry-based pose recovery and temporal smoothing. The second directly regresses translation and rotation from global and cropped event representations using an apparent-scale cue, physics-motivated synthetic corruptions, and feature-consistency regularization. We evaluate both systems under the same SPARK 2026 hidden-test protocol on the real-event split of SPADES, with predictions for all test frames. The results reveal a component-wise reversal concealed by the aggregate challenge score: direct regression reduces orientation error by 22.7% (1.1767 to 0.9101 rad) and obtains a 13.4% lower composite score, whereas the modular pipeline reduces relative translation error by 78.7% (0.1335 to 0.0285). Archived configurations and a qualitative failure case identify plausible explanations for these complementary error profiles, without isolating their causes. These findings motivate a testable hybrid design that combines direct orientation estimation with geometry-constrained translation recovery.

cs.CV

版本更新 · v2arXiv:2407.16897

HexTiles and Semantic Icons for MAUP-Aware Multivariate Geospatial Visualizations

Yuya Kawakami, Sarah Yuniar, Kwan-Liu Ma

原文摘要

We introduce HexTiles, a hexagonal-tiling based visual encoding design for multivariate geospatial data. Visualizing several geospatial variables at once is difficult because map position is already reserved for geography, and because variables are often reported on different, irregular spatial units whose aggregation is subject to the Modifiable Areal Unit Problem (MAUP). HexTiles bins data of differing spatial discretizations into hierarchical hexagons and encodes up to three variables per tile in a base color, an inner ring, and semantic icons whose count conveys value, letting the visualization designer guide attention to specific variables and their interactions. To make the effects of MAUP visible, we compute a spatially-weighted variance for each variable within each tile and encode it as a confidence value in every channel, so that the variability hidden by aggregation is not lost. Because interactive maps are increasingly viewed in tilted, 3D perspective, HexTiles encodes quantitative values only in channels that perspective does not distort, namely color and icon count. In a user study comparing HexTiles to Square-glyphs, participants rated HexTiles as significantly less demanding and frustrating, and performed more consistently with it. Domain experts in ecology and hydrology further noted its value for communicating regional patterns, and that the confidence encoding signals where aggregated values should be interpreted with care. Our results suggest that, although 3D is commonly discouraged, it can work for multivariate geospatial visualization when restricted to perspective-robust channels.

cs.HC