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

+479新增论文
+361其中 AI 相关
+64已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 21:56各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 01:14 — 2026-11-17 01:14(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 21:56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。

23,827 已收录论文19,941 AI 相关6,922 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 17,708 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.14780

RE-PRESENT: Evidence Triangulation across Alternative Candidate-Space Views for Efficient LLM Ensemble Inference

Juming Xiong, Weixin Liu, Kevin Guo, Congning Ni, Chongyu Qu, Junchao Zhu, Katherine Brown, Chao Yan 等 10 位作者

原文摘要

Heterogeneous large language models (LLMs) exhibit complementary strengths, motivating routing and multi-model inference methods that seek to identify reliable predictions for each input. However, exploiting this complementarity remains challenging even when a correct prediction is available within the ensemble. We investigate this challenge across heterogeneous LLM ensembles and find that a simple single-round aggregation rule is highly competitive with learned routing methods, yet substantial oracle headroom remains. Further analysis shows that the evaluated single-round response signals provide limited discriminative power for identifying reliable predictions. In contrast, controlled re-presentations of the same question elicit complementary evidence about prediction reliability. Motivated by these findings, we introduce RE-PRESENT, a training-free framework that selectively re-presents disputed questions and directly aggregates candidate-level evidence across alternative views. Across seven multiple-choice benchmarks and two heterogeneous model ensembles, RE-PRESENT improves over strong single-round aggregation while offering a favorable accuracy--cost trade-off compared with self-consistency and multi-model debate.

cs.MA

版本更新 · v4arXiv:2603.05066

Reward-Conditioned Reinforcement Learning

Michal Nauman, Marek Cygan, Pieter Abbeel

原文摘要

Sample-efficient reinforcement learning typically uses a fixed reward function both to guide exploration and to supervise learning. However, the same experience can provide supervision under multiple related reward specifications, even when the objective of interest remains fixed. We introduce Reward-Conditioned Reinforcement Learning (RCRL), an off-policy approach that collects experience under a nominal objective while training a reward-conditioned agent using counterfactual rewards recomputed from replay. RCRL constructs alternative reward specifications by perturbing the nominal reward, providing diverse supervision without additional environment interaction. Across single-task, multi-task, and vision-based control benchmarks, RCRL improves nominal task performance and sample efficiency when integrated with strong RL backbones. As a secondary capability, the learned policies support zero-shot behavioral adjustment toward related objectives without further training. These results demonstrate that diverse reward supervision can improve learning of a predefined objective while also enabling policy steerability.

cs.LG

版本更新 · v2arXiv:2607.01494

Insights from GitHub Community on the Matter Standard: Developer Perspectives and Challenges

Muhammad Hassan, Carl Gunter, Susan Landau, Masooda Bashir

原文摘要

Matter seeks to resolve longstanding interoperability problems in the Internet of Things (IoT), yet little is known about how developers experience the standard in day to day work. This paper examines over 13,000 issues from the official Project CHIP GitHub repository to understand the kinds of problems contributors report when implementing and integrating Matter. Using topic modeling and qualitative analysis, we identify four recurring areas of concern, Testing, Interoperability, Development, and Platform and Network, and describe how they manifest in the evolution of the codebase and tooling. The findings reveal systematic technical and integration challenges and point to concrete opportunities to refine Matter's test infrastructure, cross vendor guidance, and documentation as the standard continues to mature.

cs.SE · cs.ET · cs.HC · cs.SI

新论文 · v1arXiv:2611.14777

Mach2: Scientific Discovery Platform with Deterministic Execution Constraints

Vansh Sharma, Venkat Raman

原文摘要

Language-model agents can formulate workflows and invoke specialized tools, yet compliance with natural-language operating rules is not guaranteed by prompting alone. Mach2 addresses this limitation by coupling Eigen orchestration to deterministic, lint-like checks of tool requests, source changes, acceptance tests, and artifact contracts. Domain requirements are represented as executable predicates: mandatory failures prevent advancement of the checked operation, while diagnostic findings are retained for correction or review. User-specified test-driven development (TDD), CodeGrapher's abstract-syntax-tree analysis, and history-guided evolutionary search provide complementary verification and optimization mechanisms. Mach2 also generates task-specific agent packages for execution through independently selected endpoints. The originating harness validates returned artifacts against declared interfaces and evidence requirements without assuming continuous supervision of the remote run. Model-internal-knowledge (MIK) dependencies are recorded separately from source-grounded and test-supported findings. This paper formalizes the rule-gated execution model and the agent-package lifecycle, and proposes measurable criteria for evaluating rule compliance, engineering validity, and cross-endpoint task continuity.

cs.SE · cs.AI · physics.app-ph

新论文 · v1arXiv:2611.14776

SlipStream: Enabling HBF for GPU Systems by Mitigating the Latency and SRAM Overheads

Anish Saxena, Hritvik Taneja, Christos Kozyrakis, Aamer Jaleel

原文摘要

Large language model (LLM) inference demands ever more memory capacity for larger models and batch sizes. High-Bandwidth Flash (HBF) replaces the DRAM dies of HBM with NAND flash and provides up to 16x the capacity at comparable read bandwidth. However, HBF can incur a read latency of nearly 20$μ$s, 20x that of HBM, so on-demand HBF accesses slow inference by up to 12.8x. Conventional cache-line prefetchers require 20x more in-flight tracking state to cover this latency. Tensor-streaming designs, such as H3, follow virtual-address order as opposed to kernel-demand order, and therefore need hundreds of megabytes of buffering. We propose SlipStream, a software-hardware co-designed prefetcher that turns prefetching into a demand-paced producer-consumer pipeline. In software, SlipStream profiles the repeatable weight-page demand order of data-independent LLM kernels and inserts a staging warp that replays this order with non-blocking STAGE instructions. In hardware, the staging warp acts as the producer and the work warps as consumers. Our key insight is to retire each STAGE tracking entry only when demand first accesses the page, as opposed to when the page returns from HBF. Demand thus paces staging and bounds how far staging leads consumption. SlipStream tracks 4 KB pages instead of cache lines and allocates buffer slots only when pages return, which decouples the buffer size from outstanding traffic. Across seven dense models spanning 16-800 GB, SlipStream with a 40 MB staging buffer achieves 92.4% of the performance of an ideal HBF with HBM-like latency. H3 achieves only 43.1%, even with a 320 MB buffer. The buffer sizing of SlipStream is independent of HBF latency and workload. SlipStream with 16 MB buffer, 20x smaller than that of H3, performs within 4% of SlipStream-40MB. SlipStream also supports Mixture-of-Experts models and reaches 91.2% of ideal performance (40 MB buffer).

cs.AR · cs.DC · cs.LG

新论文 · v1arXiv:2611.14775

DeNA-SGN: Deterministic Neighborhood Aggregation for Verified Spiking Graph Inference

Sanjay Das, Xi Zhang, Emily Herron, Prasanna Date

原文摘要

Graph learning on neuromorphic substrates requires an explicit spiking realization of neighborhood aggregation, supporting control and classification. We propose DeNA-SGN, which combines fixed OR and tie-inclusive Majority aggregation of binary node features with a learned signed-weight threshold classifier. A degree-dependent inhibitory construction implements Majority through shared control neurons, enabling a complete circuit compilation into SuperNeuroMAT. Across seven datasets and 41 mapped classifiers, native simulation matches the exported ANN on every evaluated class decision and output-spike pattern. On the new confirmatory Amazon Photo dataset, DeNA-SGN achieves 83.93+-0.93% current-readout accuracy and 71.61+-2.22% strict output-spike accuracy; Wiki-CS reaches 75.99+-0.54% over 20 public masks. In the matched Cora study, we achieve 74.90+-2.67% on current-readout and 68.57+-2.94% strict spike accuracy. Complete circuit and activity accounting supports analytical energy comparisons and identifies the cost of clocking inactive neurons in large deployments. Current argmax is decoded on the host, and energy is modeled rather than measured on hardware. These findings establish a reproducible route to useful graph classification with decision-matched spiking execution and explicit implementation costs.

cs.NE

版本更新 · v3arXiv:2607.12075

Calibrated selective prediction using deep ensembles for thyroid nodule ultrasound classification under dataset shift

Md. Sadibul Hasan Sadib, Md. Mohayminul Mukit, Rahmatul Kabir Rasel Sarker, Tahmid Alam Tamim, Md. Nazmul Hasan, Md. Monir Hossain Shimul

原文摘要

Background: Deep learning can classify thyroid nodules on ultrasound, but discrimination alone does not establish clinical reliability. We developed a calibrated deep-ensemble framework with uncertainty-aware selective prediction and conservative image-based triage. Methods: Nested five-fold cross-validation with three-fold inner architecture selection chose ConvNeXt-Tiny with a squeeze-and-excitation block, used to build a deterministic five-member ensemble. Training, early-stopping, calibration, and threshold subsets were separated within each fold; outer-test data remained isolated. Mutual information (MI), predictive variance, and maximum-softmax-probability (MSP) uncertainty were compared by risk-coverage and triage analyses, and predictive values across assumed malignancy prevalences of 5%-70%. The frozen TN5000 ensemble was applied to TN3K without recalibration. Results: On TN5000, pooled out-of-fold AUC-ROC was 0.9377, average precision 0.9708, expected calibration error 0.0138, and Brier score 0.0827. Under the primary MI-guided policy, 8.86% of images received a No-FNA suggestion, 60.00% an FNA recommendation, and 31.14% radiologist review; of 3574 malignant images, 14 (0.39%) received No-FNA and 708 (19.81%) review. Predictive variance and MSP ranked errors better than MI (AURC, AUGRC); no measure optimized all triage outcomes. Across prevalences of 5%-70%, NPV ranged 99.95%-97.93% and PPV 29.28%-94.75%. On TN3K, AUC-ROC was 0.7870, average precision 0.7254, expected calibration error 0.1899, and radiologist-review rate 83.7%. Conclusion: The ensemble showed strong internal discrimination and calibration, but performance deteriorated substantially on TN3K, indicating limited transportability under dataset shift. Multicentre validation, site-specific recalibration, threshold validation, and prospective evaluation are needed before clinical use.

eess.IV · cs.AI · cs.CV

版本更新 · v2arXiv:2605.27913

Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMs

Safal Thapaliya, Jiatan Huang, Chuxu Zhang

原文摘要

Node classification on graphs often requires labeled nodes, yet obtaining labels at graph scale is expensive. When node attributes contain semantic content, such as paper abstracts, web pages, or product descriptions, large language models (LLMs) can provide low-cost supervision by annotating a small subset of nodes. However, these LLM-generated labels are noisy, and existing label-free graph learning methods usually treat this noise as either global or class-conditional. We find that LLM annotation errors are not only class-dependent but also region-dependent: within the same class, reliability can vary sharply across feature-space clusters. In light of this, we propose Cluster-Aware Noise Estimation (CANE), a label-free learning framework that estimates cluster-conditional LLM reliability without ground truth labels, and uses this estimate to decide which pseudo-labels to trust, and which labels to correct. Across various graph benchmarks and GNN backbones, CANE improves over the strongest label-free baselines, with the largest gains on datasets exhibiting stronger cluster-conditional noise. The code is available at https://github.com/thapaliya19/CANE.

cs.LG

版本更新 · v2arXiv:2605.16588

Policy Library CBF: Finite-Horizon Safety at Runtime via Parallel Rollouts

Taekyung Kim, Hideki Okamoto, Bardh Hoxha, Georgios Fainekos, Dimitra Panagou

原文摘要

Safety-critical autonomy in unstructured environments poses significant challenges for online safety certification under evolving constraints, particularly when a single backup policy is not effective across operating conditions. We propose the Policy Library Control Barrier Function (PL-CBF), a runtime safety filter that evaluates a library of fallback policies via parallel finite-horizon rollouts. Among policies with constraint-satisfying rollouts and feasible CBF constraints, PL-CBF selects the policy maximizing the volume of its admissible control set and solves a single quadratic program to minimally modify the nominal input within that constrained input set. Using a finite-horizon language metric over closed-loop behaviors, we characterize when a finite policy library contains a constraint-satisfying rollout. Five simulation studies cover indoor robot navigation with a double-integrator model (4 states), highway driving under abrupt friction changes with a nonlinear vehicle model (8 states), and quadrotor flight control among dynamic obstacles (12 states), demonstrating improved safety performance compared with the evaluated baselines while maintaining millisecond-scale mean computation times. Hardware experiments on a mobile robot among moving pedestrians and a custom-built quadrotor among dynamic obstacles demonstrate real-time operation of PL-CBF.

cs.RO · eess.SY

新论文 · v1arXiv:2611.14770

Nonlinear homogenization of periodic unit cells composed of mixed continuum and structural elements with variationally consistent boundary-member reduction

Jonathan Stollberg, Dominik Schillinger

原文摘要

Periodic architected materials may be represented by representative volume elements (RVEs) combining continuum, truss, beam, and shell constituents. Their mixed translational and rotational kinematics complicate a consistent scale transition to a macroscale Cauchy continuum. We establish a nonlinear first-order computational homogenization framework for such mixed-dimensional RVEs. An auxiliary finite-strain Cosserat continuum serves solely as a power-equivalent carrier of their virtual power and generalized boundary kinematics. Its uniform rotation is identified with the macroscopic polar rotation and its wryness vanishes, so the effective medium remains of Cauchy type. Under periodic translational and rotational constraints, the Hill-Mandel condition yields a common nodal-force virial for the effective first Piola-Kirchhoff stress, independent of element type. For lower-dimensional members on periodically identified cell boundaries, fractional ownership of internal virtual work is shown to be variationally equivalent to a topology-preserving reduction retaining one representative of each set of periodic element copies. Because this equivalence covers the complete element virtual work and consistent linearization, it applies to geometrically and materially nonlinear and path-dependent constituents without rescaling section properties, constitutive parameters, or internal variables. Numerical examples recover the analytical small-strain response and cubic symmetry of a mixed continuum-shell-beam cell, verify the reduction and discrete power balance, and demonstrate finite-rotation buckling of a hyperelastic Octet lattice and history-dependent yield-surface evolution of an elastoplastic sandwich cell. The open-source implementation abqhom couples the framework to Abaqus.

cs.CE

新论文 · v1arXiv:2611.14769

Leaderboard Hacking: Preference-Based Model Evaluations are Vulnerable to Manipulation

Eve Fleisig, Joachim Baumann, Dylan Hadfield-Menell, Dirk Hovy

原文摘要

Arena-style rankings of language models are a widely used evaluation framework in online leaderboards, research papers, and model evaluation in production. These rankings aim to realistically assess model performance using pairwise comparisons of anonymous models on user prompts, aggregating votes via the Bradley-Terry model to produce the final ranking. However, we find that these leaderboards are highly vulnerable to several manipulation strategies that unscrupulous providers could use to boost a model's rank: strategic voting (individual votes that boost a model's rank, including votes on irrelevant models), strategic prompting (choosing prompts that favor a model), and strategic nomination (boosting the rank of a model by inserting irrelevant models). We demonstrate these effects on public leaderboard data, analyze the circumstances that cause these vulnerabilities, and describe approaches to safeguard against each attack. Notably, these issues hold for any preference-based evaluation using the Bradley-Terry model that allows open prompting, voting, or model submission. These manipulations boost the rank of nearly every tested model; each attack can boost a model by up to 15-20 places in a ranking and, combined, they can boost a model by up to 45 places.

cs.AI

新论文 · v1arXiv:2611.14766

Rational Use of Time for Social Coordination in Humans and AI

Xiulin Yang, Sirisha Gudavalli, Jennifer Hu

原文摘要

All social interactions are situated in time. Previous studies have shown that humans are able to use implicit temporal cues, such as the duration of a pause, to infer others' mental states. But how do humans use temporal cues for dynamic, fine-grained social coordination? And can AI systems do the same, without ``experiencing'' continuous real-time as humans do? We study these questions using a cooperative card game task called The Mind, which requires players to achieve a shared goal across repeated interactions but forbids explicit communication: the only available signal is the passage of time. We evaluate 150 humans, and two classes of AI models which reflect different ways of operationalizing time in artificial systems: computer-use agents (CUAs), and standard text-prompted LLMs. We find that human behavior is best captured by a Bayesian strategy that infers a partner's belief from their timing---and similarly for frontier models. However, unlike humans, none of the tested models seem to efficiently adapt their behaviors to their partners' over the course of the game. From a cognitive perspective, our findings suggest that humans perform implicit probabilistic reasoning about continuous-time signals in dynamic social settings, and that such reasoning mechanisms may emerge without real-time experience. Practically, our study highlights new challenges for AI systems to coordinate efficiently with other agents by learning to interpret and adapt to their implicit signals in dynamic settings.

cs.AI · cs.CL

新论文 · v1arXiv:2611.14765

SynthCorp: A Platform for Creating Benchmarks for Data Agents

Jiani Zhang, Manav Garg, Eugenie Lai, Cheng Zhen, Eva Sharma, Yang Pan, Yaming Lin, Alon Halevy

原文摘要

Current benchmarks for LLM-driven data agents saturate quickly and cannot target specific capabilities. We present SynthCorp, a platform that creates customizable data estates and benchmarks by simulating how business events produce and modify corporate data over time. Each data estate combines relational databases, a document store, and a data catalog, paired with evaluation tasks and executable gold programs. First, given a scenario and target complexity dimensions, SynthCorp synthesizes reusable event types and compiles each into a program over predefined simulation primitives. Second, SynthCorp schedules event instances on a virtual calendar, interleaving routine and disruption events so that tables, documents, and catalog entries remain consistent. Third, SynthCorp executes the calendar to materialize the data estate and records every operation in a simulation log. Fourth, SynthCorp generates analytical tasks and derives verified gold programs from the log. We use SynthCorp to generate initial evaluation benchmarks comprising seven data estates (up to 1K operational tables) and 256 tasks across five domains. The data estates pass deterministic pipeline checks (such as foreign-key violations, undeclared writes, recurrence violations, and database execution failures) with a near-zero error rate, introduce cross-asset complexities, and cover all requested dimensions. Evaluating three models across four data-context settings shows that the benchmarks separate data contexts and model tiers. Auditing candidate queries against causal provenance in the simulation log verifies gold programs without manual annotation, including on multi-event composite tasks that expose reasoning failures in state-of-the-art agents. We hope the community uses SynthCorp to generate more challenging and useful data estates and benchmarks that foster the development of enterprise data agents.

cs.AI · cs.DB

新论文 · v1arXiv:2611.14763

RECALL: Real-Time Recalibration of Multi-Camera Rigs via Learned OEM-Anchored Residuals

Mario Alberto Tapia de la Cruz, Charalambos Poullis

原文摘要

Multi-camera rigs ship pre-calibrated from the manufacturer, but their calibration goes stale each time the rig is repositioned, and drifts continuously through wear, thermal cycling, and vibration. Recovering it on-the-fly is hard: classical bundle adjustment needs a fresh multi-view capture and a global optimization whose cost grows with the rig, ruling out real-time use. In this paper we present RECALL, a feed-forward method that recalibrates a movable multi-camera rig in a single pass. From the nominal OEM calibration as an anchor and a brief observation of a known object, it predicts each camera's current intrinsics and extrinsics, written as a shared global rotation of the rig composed with a small per-camera drift. Instead of regressing the calibration in one shot, RECALL refines its estimate with a learned, rig-coupled recurrent operator that reprojects through a differentiable projection and applies attention across the cameras at each step, and solves for the shared rotational gauge in-network with a learned Gauss-Newton step rather than regressing it. Because the ground truth is synthesizable, we train entirely on data generated on-the-fly and need no captured dataset. On a synthetic 10-camera benchmark, RECALL is more accurate than per-camera and rig-coupled joint bundle adjustment ($0.26^\circ$ vs $0.47^\circ$ rotation, $5.4$ vs $8.9$ px focal) and runs about $10^5\times$ faster at about $0.12$ ms per rig. On real data (TotalCapture, CMU Panoptic) it matches or beats offline rig-coupled bundle adjustment on absolute and relative rotation while running four-to-five orders of magnitude faster, and on the Panoptic surround rig it also matches the strongest image-only foundation models (VGGT, VGGT-$Ω$, $π^3$) on relative pose while staying metric and about $15\times$ more accurate in focal length. Code: https://github.com/theICTlab/RECALL-multicam

cs.CV

版本更新 · v3arXiv:2602.02799

Joint Learning of Hierarchical Neural Options and Abstract World Model

Wasu Top Piriyakulkij, Wolfgang Lehrach, Kevin Ellis, Kevin Murphy

原文摘要

Building agents that can perform new skills by composing existing skills is a long-standing goal of AI agent research. Towards this end, we investigate how to efficiently acquire a sequence of skills, formalized as hierarchical neural options. However, existing model-free hierarchical reinforcement algorithms need a lot of data. We propose a novel method, which we call AgentOWL (Option and World model Learning Agent), that jointly learns -- in a sample efficient way -- an abstract world model (abstracting across both states and time) and a set of hierarchical neural options. We show, on a subset of Object-Centric Atari games, that our method can learn more skills using less data than baseline methods and possesses learning and generalization capabilities that the baselines do not have.

cs.LG · cs.AI

新论文 · v1arXiv:2611.14762

Open-Source Transtibial Prosthetic Bypass Preserving Joint Alignment: Gait Learning and Kinematic Evaluation

Apolline de Vaulchier, Pablo Nocito, Yann Corbel, Nathanaël Jarrassé

原文摘要

Prosthetic bypasses allow able-bodied individuals to walk with a prosthesis, enabling safe early-stage testing of new prosthetic devices before clinical trials. However, existing transtibial bypasses impose constraints, such as a contralateral shoe lift or a lateral offset of the prosthesis, and their effects on gait remain poorly documented. We present an open-source transtibial prosthetic bypass that preserves part of the sagittal knee mobility without these constraints. Six able-bodied participants familiarized themselves with the bypass for approximately 10~min, then walked on a treadmill with and without it, and joint kinematics were recorded with motion capture and then extracted with OpenSim. All participants were able to walk without handrail support, although single stance remained shorter on the bypass side (27% vs. 45% of the gait cycle). Bypass-side ankle kinematics were consistent with those reported for transtibial prosthesis users, whereas peak knee flexion during swing decreased from 61° to 36° (p<0.001) and hip range of the sound leg increased from 35° to 51° (p<0.01). Although gait with the bypass does not fully replicate that of prosthesis users, it yielded consistent gait patterns after only 10~min of learning. This bypass therefore provides a useful tool for the lower-limb prosthetics research community, facilitating preliminary experiments with able-bodied participants.

cs.RO

版本更新 · v3arXiv:2601.22510

Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic

Xingyu Zhao, Darsh Sharma, Rheeya Uppaal, Yiqiao Zhong

原文摘要

Large language models (LLMs) often achieve strong benchmark accuracy yet remain brittle under small distribution shifts. While recent mechanistic studies reveal the discrepancy between LLMs and humans in skill compositions, the learning dynamics of skill acquisition and the role of data distributions remain elusive. In this study, we train transformers on synthetic arithmetic tasks with black-box model-agnostic metrics for analyzing non-human skill compositions. We discover that transformers often acquire skills for arithmetic in reverse order or in parallel instead of human-like sequential rules--a phenomenon we refer to as shattered compositionality. To explain these behaviors, we provide evidence that correlational matching to the training data, rather than causal or procedural composition, shapes learning dynamics. As a consequence, this non-human acquisition creates competition between partially learned skills, producing characteristic mixing errors and weaker robustness under controlled distribution shifts. We further show that the same qualitative behavior persists in modern LLMs and is not mitigated by pure model scaling or scratchpad supervision. Our results highlight a mismatch between training-time skill acquisition and the human-like hierarchical compositions, with implications for reasoning reliability and out-of-distribution robustness.

cs.LG · cs.AI

版本更新 · v2arXiv:2606.18062

Security and Privacy Prompts in the Wild: What Users Ask LLMs and How LLMs Respond

Hobin Kim, Xiaoyuan Wu, Omer Akgul, Lujo Bauer, Nicolas Christin

原文摘要

Large language models (LLMs) are widely used to answer users' information needs: users ask LLMs about the weather, pose educational questions, and consult them for legal assistance. One particularly understudied area is digital security and privacy (S&P), where users may seek LLMs' help on how to secure their online accounts or protect their computers from cyber attacks. To the best of our knowledge, no prior study has collected or analyzed the S&P questions users ask LLMs; prior research on LLM response quality relied on expert-authored S&P misconceptions or FAQs rather than user queries. Drawing from WildChat, a dataset of 3.2M user-LLM conversations collected in the wild, our study identifies 14,727 S&P prompts and categorizes them into nine categories covering a wide range of S&P topics. We sampled 450 S&P prompts, and performed a thematic analysis to characterize the S&P questions users ask LLMs. Separate from the thematic analysis, we curated 270 advice-seeking S&P prompts, where users ask for recommendations, guidance, or specific S&P information. We measured LLM response quality and consistency when posing each prompt to the LLMs 10 times. We found that commercial LLMs outperform open-weight models (GPT 5.5 provided "good enough" responses on 98% of prompts; Llama 4 on 47%). However, among prompts that received high-quality responses on average, commercial models sometimes produce semantically inconsistent responses across runs (some are contradictory, and others are different in specificity), thereby risking confusing or misleading users.

cs.CL · cs.AI · cs.CR · cs.HC

版本更新 · v2arXiv:2608.04222

TIDE: A Physically Diverse 3D Turbulence Benchmark Dataset for Advancing Scientific Machine Learning

Yilong Dai, Yiming Sun, Yiheng Chen, Shengyu Chen, Peyman Givi, Xiaowei Jia, Runlong Yu

原文摘要

Turbulence is a central testbed for machine learning on physical dynamics because its governing laws are known exactly. However, most existing studies remain in 2D, while 3D turbulence has fundamentally different physics and is far more costly to simulate. Existing 3D resources also typically provide only one realization per configuration, making it difficult to distinguish learning the dynamics from fitting the statistics of a single flow. In this paper, we introduce TIDE (Turbulent Incompressible DNS Ensembles), a 256^3 DNS corpus and benchmark for 3D incompressible turbulence, with 15 configurations on eight controlled axes, independent ensembles, pressure fields, and equation-level verification. The benchmark includes five tasks, standardized learned baselines, controlled generalization splits, and physical-fidelity metrics alongside pointwise error. Across the main forecasting configurations, current learned models trained under a fixed reference recipe barely outperform persistence and still make about twice the error of a spectral solver given the true equations. Moreover, lower pointwise error can coincide with severely distorted small-scale dynamics, showing that accuracy alone does not ensure physical fidelity. Rollout stability depends on the configuration, the training seed, and how densely training samples each trajectory. Joint training across neighboring regimes does not close the transfer gaps we test, and the forced-to-decay contrast bounds a conditioning limit: an estimate of the current forcing state removes 20-41% of the error a spectral solver makes without forcing input, while history or forcing inputs help only some learned architectures. Closing these accuracy, fidelity, and conditioning gaps is the central open problem made measurable by TIDE. https://github.com/Dyloong1/TIDE-dataset-benchmark

physics.flu-dyn · cs.LG

新论文 · v1arXiv:2611.14760

Graph Label Alignment: A Diagnostic Atlas for Graph Classification

Neelam Akula, Varun Shiralkar, Murat Kantarcioglu, Baris Coskunuzer

原文摘要

Graph classification benchmarks vary widely in difficulty: some are solved by simple pooled baselines, while others remain challenging for GNNs and graph transformers. We take a data-centric view and ask whether benchmark success is driven by genuine structure--feature reasoning or by label signal already accessible from restricted marginal views. We introduce graph label alignment, a lightweight diagnostic that measures label accessibility through two supervised probes computed without training a graph encoder: structural label alignment (SLA), based on permutation-invariant topological and spectral summaries, and feature label alignment (FLA), based on pooled node features with edges removed. Across real graph classification benchmarks and multiple pooled backbones, the resulting SLA--FLA plane strongly organizes test accuracy, with low-alignment datasets forming a consistent regime where standard pooled pipelines struggle. To probe what lies beyond marginal accessibility, we introduce controlled interaction-dominated stress tests, including heterophilic ego-graphs and synthetic Twins tasks whose structural and feature marginals are matched across classes but whose role--feature couplings differ. These results show that high alignment explains much of easy benchmark performance, while low alignment reveals regimes where success requires preserving structure--feature correspondence beyond standard pooled representations.

cs.LG · cs.AI

新论文 · v1arXiv:2611.14758

Benchmarking Multilingual Document Understanding in Vision-Language Models

Matteo Gabburo, Daniela Baiamonte, Stefano Simonazzi, Silvia Gardini, Sean Cesare Lazzeri, Andrea Zugarini

原文摘要

Recent Vision-Language Models (VLMs) perform strongly on multimodal tasks, Document Understanding (DU) among them, but the benchmarks that measure them mostly cover English documents and narrow problems. How well current VLMs generalize across languages, tasks, styles and layouts therefore remains unclear. We introduce MDU, a multilingual DU benchmark of 23146 examples spanning 13 tasks and five languages: English, French, German, Italian, and Spanish. The tasks isolate complementary capabilities, from surface-level text and Markdown extraction through summarization, classification and named-entity recognition to layout-sensitive passage and layout extraction. We evaluate 45 state-of-the-art open-weight VLMs from 1.7B to 235B parameters, plus one commercial system under the same protocol. The benchmark is far from saturated: the best average is 69.0, only eight of the 45 evaluated systems reach 65, and the two best results come from 27B models rather than from the largest systems we evaluate. Performance is uneven in ways that scale does not fix. The gap between the strongest and weakest language does not close as models grow, and it survives controlling for the domain composition of each language. Capabilities also do not improve together: once we partial out overall model quality, per-task scores are largely uncorrelated, and transcription ability in particular trades off against semantic extraction.

cs.CL · cs.AI

新论文 · v1arXiv:2611.14755

A Sublogarithmic Competitive Algorithm for Online Graph Exploration

Max Klimm

原文摘要

In online graph exploration, an agent must visit every vertex of an unknown weighted graph and return to its start, learning the incident edges at each vertex it visits. On $n$-vertex graphs, the best known competitive ratio has been $O(\log n)$, achieved by several algorithms, among them the hierarchical depth-first search of Megow, Mehlhorn, and Schweitzer. We give an algorithm with competitive ratio ${(2+o(1))}\ln n/\ln\ln n$ for known~$n$. Like hierarchical depth-first search, it groups the edges into geometric weight classes and searches depth-first between components of lighter edges. Unlike it, the agent tours each component along a minimum spanning tree for the original weights, so only crossings between components pay for rounding, and the base $b$ of the weight class can grow with~$n$. The leading constant $2$ is tight for our choice of base. Without knowing $n$, restarts with increasing size guesses give upper bounds with leading constant $4$ for a fixed schedule and $2$ in expectation for a randomly shifted schedule. If the weights lie in a known range $[1,2^k]$ with $k\ge4$, choosing $b=k/\log_2 k$ gives a competitive ratio of $O(k/\log k)$ without knowing $n$.

cs.DS

版本更新 · v2arXiv:2610.03391

Native Action-Prior Learning from Videos for World Action Models

Zhaochong An, Fei Zhang, Menglin Jia, Duncan Frost, Zijian Zhou, Yikai Wang, Xudong Wang, Aditya Patel 等 13 位作者

原文摘要

World action models integrate future visual dynamics with robot action prediction, but their scalability remains limited by the need for action-annotated robot trajectories. Observation-only videos contain rich evidence about interaction dynamics, but existing approaches typically use them either to pretrain visual representations that must later be adapted for control, or to infer latent actions that are subsequently grounded to robot commands. We present NAVA-WAM, which introduces native action-prior learning by directly pretraining the action policy from observation-only videos, avoiding indirect representation-to-control transfer or a separate latent-action model. Our training consists of two stages. First, we pretrain on observation-only videos, where future-video flow-matching supervision over visual transitions is propagated through transition-structured joint attention to optimize the Action-DiT and learn action-relevant priors. Second, we use action-labeled demonstrations to post-train the Action-DiT for robot control through joint video--action flow matching, while asymmetric attention decouples the visual branch from iterative action denoising and enables efficient action-only inference. Extensive experiments show that NAVA-WAM consistently outperforms prior approaches under both in-distribution and out-of-distribution settings, while demonstrating strong action-label efficiency and effective real-robot generalization. These results establish native action-prior learning as an effective approach to directly pretrain action policies from observation-only videos, providing a scalable path beyond action-labeled robot data.

cs.CV · cs.RO

新论文 · v1arXiv:2611.14750

From Nodes to Pixels: Topological and Structural Two-View Graph Imaging

Md Joshem Uddin, Soham Changani, Sai Karthik Navuluru, Cuneyt Gurcan Akcora, Baris Coskunuzer

原文摘要

Graph learning still lacks a broadly reusable input interface comparable to patches in vision or tokens in language. Unlike images or text, graphs are irregular, vary in size and density, and are invariant under many equivalent node labelings, making it difficult to standardize inputs across tasks and architectures. We introduce G2Image, a fixed-budget graph imaging framework that converts each graph into two complementary image-like views. TopoGrid provides a stable topological view by encoding an intrinsic bifiltration as a compact multipersistence surface grid, while GraphGrid provides a higher-bandwidth structural view by aggregating edge densities between groups defined by intrinsic node scores. Both views are permutation-invariant and come with resolution-controlled stability guarantees. Because the resulting representations are fixed-size tensors, they can be processed by lightweight 2D encoders and aligned through a supervised cross-view contrastive objective. Across graph classification and molecular prediction benchmarks, G2Image achieves strong average performance among the compared methods, improves over single-view and standard fusion variants, and extends to attribute-rich molecular graphs without changing the overall architecture. These results suggest that fixed-budget graph images offer a practical and reusable interface for graph representation learning.

cs.LG · cs.AI

新论文 · v1arXiv:2611.14749

Don't Match the Noise: Distribution Matching under Unknown Measurement Error with an Audit Sample

Arya Farahi, Ritwik Vashistha

原文摘要

Real-world machine learning systems often operate on imperfect measurements: sensors are noisy, annotations are produced by non-experts, and scientific observations are often indirect. In these settings, classic distribution comparison tools such as maximum mean discrepancy (MMD) can be systematically biased, matching artifacts of the measurement process rather than the underlying mechanisms of interest. We study a practical regime in which noisy observations are abundant, but only a small audited subset contains ground-truth measurements. We propose measurement-error-corrected MMD (MEC-MMD), an audit-based estimator that debiases kernel evaluations without requiring a noise model. MEC-MMD is exactly unbiased for the oracle MMD under simple random auditing, admits an explicit variance decomposition, and is consistent for the population MMD, achieving the standard $O_p(N^{-1/2})$ rate when the audit size scales with the dataset. We demonstrate the utility of distributional matching with MEC-MMD loss for both parameter estimation and unsupervised applications, showing that MEC-MMD consistently outperforms MMD and alternative methods. These results provide a principled foundation for robust distribution comparison, simulation-based inference, and learning in noisy real-world machine learning pipelines.

stat.ML · cs.LG · stat.ME

新论文 · v1arXiv:2611.14748

UniPipe: Unified Inference Serving and Fine-Tuning for Deadline-Constrained DNN Surrogate Workflows

Jaiaid Mobin, Avinash Maurya, M. Mustafa Rafique, Bogdan Nicolae

原文摘要

DNN surrogates are increasingly used to accelerate scientific workflows that must process high-rate sensor streams in near real time, exemplified by Ptychographic imaging at next-generation X-ray light sources. Such surrogates deliver 100-1000x higher throughput than iterative solvers, enabling faster steering of experiments. To preserve surrogate accuracy during an experiment, as the input distribution evolves, state-of-the-art deployments freeze the pretrained surrogate or run a separate CUDA context that fine-tunes concurrently with serving. However, multi-context concurrency causes significant contention on the GPU, inflating both the mean and the variance of inference latency, triggering deadline misses in workflows where sensor data has to be processed within a hard per-unit deadline. To address this challenge, we propose UniPipe, a single-context system that unifies inference serving and fine-tuning of a DNN surrogate on a single edge GPU. UniPipe is driven by three key insights: both serving and fine-tuning require a forward pass and can be fused into one; the per-sample latency of modern GPUs is non-linear in batch size; and the workload is repetitive across intervals, enabling offline scheduling. Specifically, UniPipe fuses training and inference data in a single forward pass with a selective backward pass on the training subset, and uses a polynomial-time scheduler that exploits the latency curve to compute the batch composition. We evaluate UniPipe on a real-world Ptychographic reconstruction workflow with sensor rates up to 5000 patterns/sec.; UniPipe lowers reconstruction MSE by up to 30% and inference MSE by up to 50% over a pretrained baseline, and reduces the deadline-miss rate by 13%-22% over a multi-context baseline. UniPipe's unified deployment reduces the latency spread from 106% to 57% of the mean, and increases total throughput compared to multi-context baseline.

cs.LG · cs.PF · eess.SY

版本更新 · v4arXiv:2601.20154

Spectral Ghost in Representation Learning: A Unified View from Component Analysis to Self-Supervised Learning

Bo Dai, Na Li, Dale Schuurmans

原文摘要

Self-supervised learning (SSL) extracts representations from massive unlabeled data that transfer to a variety of downstream tasks. Its empirical success has produced a dizzying array of objectives and procedures, yet a clear understanding of what representation is desired, and why these seemingly different methods work, is still missing. In this paper, we develop a unified spectral framework for representation learning. We first show that a representation is sufficient for arbitrary downstream prediction with a linear head if it spans the spectral decomposition of the pointwise mutual information, which can be extracted purely from unlabeled data. This view organizes representation learning along two axes, the parametrization of the spectral representation (linear, energy-based, denoising, nonlinear, latent-variable, and multi-modal) and the learning objective for fitting it, under which a broad range of existing methods, including SimCLR, MoCo, BYOL, Barlow Twins, VICReg, DINO, MAE, JEPA, BERT, GPT, and CLIP, as well as classic PCA, CCA, Laplacian eigenmaps, LLE, and SNE, are recovered as particular combinations. The framework also clarifies optimization behaviors: the batch-size requirement is determined by whether the objective is unbiased, a consistent surrogate, or biased, rather than by contrastive vs. non-contrastive losses. Finally, the framework inspires new scalable algorithms and extends spectral representations to causal inference and reinforcement learning.

cs.LG

新论文 · v1arXiv:2611.14744

Beyond Ground States: Learning Many-Body Hamiltonians for p-Bit Invertible Arithmetic

Tian Feng, Xutang Fan, Yiyun Chen

原文摘要

Probabilistic-bit (p-bit) invertible logic encodes a Boolean relation as an energy whose ground states are its legal assignments, computing in any direction by sampling. Traditional constructions target ground-state membership and a wide minimum energy gap, yet finite-time samplers traverse excited states. We cast Hamiltonian design as inverse statistical mechanics: fit an energy with interactions up to order four whose Gibbs law approaches uniformity on each clamp case's legal states, under a gap floor keeping every legal state below every illegal one. Constrained maximum likelihood with pruning and refitting fits terms from a fixed pool, and every delivered energy is audited exactly on all cases. Each energy is scored by time to a verified solution under restarts with its best of nine tuned samplers. In underdetermined modes, learned multipliers factor in 0.55, 0.44, 0.52 and 0.46 [0.38, 0.56] of the hand-written encodings' updates from 4x4 to 7x7, faster within every family below 7x7 at no resolved work penalty; learned adders solve the reverse mode in 0.71 of the updates at 8 bits and about a quarter at 24 and 32 bits, at 0.55 of the work at 32 bits. At 5x5 under equal pool, budget and floor, a gap-maximizing fit reaches 0.79 [0.73, 0.88] in updates and 1.26 in work against the hand-written encoding, while likelihood fitting takes 0.55 [0.46, 0.58] and 0.58 [0.48, 0.61] of the gap fit's updates and work. Rounding coefficients to the narrowest exact integer words tested, we run both energies at each pair's common word on one FPGA color-sweep SSA core, bit-exact with software: learned multipliers take 0.41 of the hand-written encoding's cycles at 4x4 and 0.057 [0.045, 0.068] at 7x7, at up to 2.4 times its lookup tables. The method requires only a circuit's legal assignments; in determined modes, hand-written encodings take less work, and from 12 bits on the adder fewer updates.

cond-mat.dis-nn · cs.ET · physics.app-ph

版本更新 · v3arXiv:2605.10919

Random Access Expectation in DNA Data Storage: Asymptotic Analysis Through Fountain Codes

Christoph Hofmeister, Rawad Bitar, Eitan Yaakobi

原文摘要

The expected number of coded symbols drawn from a linear code until a desired information symbol can be decoded is studied. This quantity is of interest in DNA data storage, where it is called the random access expectation. If the generator matrix of the code is binary and fully symmetric, the process of sampling symbols from the code is equivalent to the encoder of an LT code. Based on this observation, the random access expectation of binary fully symmetric codes under a peeling decoder is analyzed in the large blocklength limit. Asymptotically, a random access expectation, normalized by the number of information symbols, of $0.7869$ is achievable, while for a binary fully symmetric code under a peeling decoder it cannot be below $π/4\approx 0.7854$. The analysis is extended to the case where a set of information symbols needs to be decoded.

cs.IT

新论文 · v1arXiv:2611.14741

Reconstructing Fine-grained Memory Reuse Structure in GPU Kernels

Yanbo Zhao, Yueming Hao, Zecheng Li, Mao Lin, Shuyin Jiao, Keren Zhou, Xu Liu, Jiajia Li

原文摘要

Optimizing GPU data movement requires knowing which instructions access the same data and across which execution scopes reuse occurs. Existing profilers can attribute memory behavior to individual instructions but do not expose the reuse relations among them, while aliasing, dynamic indexing, and runtime parameters prevent static analysis from establishing these relations in general. Cycle-level simulation can reconstruct such relations, but at costs prohibitive for production workloads. We introduce two abstractions for representing this structure: Topological Distance, which labels each dynamic memory access with the smallest execution scope (thread, warp, block, or grid) containing its most recent reuse, and PCDepGraph, which organizes these labels into a PC-level graph of the kernel's memory reuse structure. Defined over logical execution scopes rather than transient hardware state, the representation remains stable across runs and GPU targets while directly indicating the sharing scope that candidate optimization mechanisms must cover. Our tool, cuVein, reconstructs PCDepGraph directly from optimized binaries, without sampling, at generally under 10x overhead. Across HPC and AI workloads on NVIDIA RTX 4090 and H100, optimizations guided by PCDepGraph eliminate up to 90.18% of memory instructions and yield up to 2.84x kernel speedup; reuse-scope distributions remain consistent across platforms, supporting that the representation captures program structure rather than transient hardware behavior.

cs.DC · cs.PF · cs.PL