跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+547新增论文
+436其中 AI 相关
+87已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-18 16:38各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 17:12 — 2026-11-18 17:12(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:2026-11-18 04:28最近发现新增版本:2026-11-18 16:38库内论文最新更新时间:2026-11-18 08:00

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

26,239 已收录论文21,850 AI 相关7,895 有修订112 HF 社区发现

论文修订列表

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 7,895 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v2arXiv:2507.00725

PL Morse-Cerf Theory for Topological Analysis of Time-Varying Scalar Fields

Amritendu Dhar, Apratim Chakraborty, Vijay Natarajan

原文摘要

Morse-Cerf theory studies the evolution of critical points in one-parameter families of smooth functions defined on a manifold. This paper describes an adaptation of Morse-Cerf theory of smooth functions to one-parameter families of piecewise-linear (PL) functions. The vertex diagram and Cerf diagram are introduced as topological descriptors that represent evolution of the PL function. The characterization of a crossing in the vertex diagram based on the homology of the lower links of vertices leads to the definition of a topological descriptor for time-varying scalar fields. Algorithms and methods for computing, querying, and comparing Cerf diagrams support its application towards the analysis of time-varying scalar fields. Stability theorems on the comparison measure provide a guarantee of robustness. Experimental results on multiple scientific datasets demonstrate its practical utility.

cs.GR · cs.CG

版本更新 · v3arXiv:2606.30995

Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again

Zakk Heile, Hayden McTavish, Margo Seltzer, Cynthia Rudin

原文摘要

Recent work has shown that well-optimized individual decision trees can match complex black box models in some settings, primarily in noisy domains. For the remaining settings, however, complex ensembled compositions of trees often achieve higher accuracy at the cost of interpretability, leaving practitioners with difficult modeling decisions along an accuracy-interpretability tradeoff. Ideally, we would like to classify as much of the data as possible with one or a small number of trees, achieving interpretability for most samples while maintaining state-of-the-art accuracy. We introduce Multistage Defer Trees: a sequence of sparse decision trees that each make predictions for most samples, while deferring a small proportion to the next tree in the sequence or, ultimately, to a black box. We demonstrate that we can train this model class to match the performance of complex tree-based ensembles while routing most samples through only one or a small number of sparse decision trees. We discuss a range of techniques for training these models while maintaining simplicity. Our method expands the accuracy--interpretability frontier in settings where single-tree methods remain insufficient, demonstrating that even when complex models are necessary, they need not be fully opaque.

cs.LG · stat.ML

版本更新 · v5arXiv:2410.03897

Generative AI, Managerial Expectations, and Economic Activity

Manish Jha, Jialin Qian, Michael Weber, Baozhong Yang

原文摘要

Using generative AI, we extract managers' economic expectations from over 120,000 corporate conference call transcripts. The resulting AI Economy Score predicts GDP growth, production, employment, and wages five or more quarters ahead, beyond survey forecasts and other existing measures. Industry- and firm-level scores capture sector- and firm-specific activity, and a composite of firm, industry, and macroeconomic expectations further improves forecasting power and horizon. Predictability concentrates among historically more accurate, less biased managers, consistent with an information rather than a noise channel. Managerial expectations thus offer incremental insights into economic activity, with implications for macro- and microeconomic decision-making.

q-fin.CP · cs.LG · econ.GN

版本更新 · v2arXiv:2605.07270

bispectrum: Selective G-Bispectra Made Practical

Johan Mathe, Adele Myers, Simon Mataigne, Nina Miolane

原文摘要

Many machine learning tasks are invariant under transformations such as translations and rotations. The $G$-bispectrum is a complete invariant that determines a signal up to a group action, but its computation is costly and existing implementations each cover a single group. We present bispectrum, an open-source, fully unit-tested PyTorch library providing efficient, differentiable selective $G$-bispectra for seven group actions. Selectivity reduces the number of coefficients from $O(|G|^2)$ to $O(|G|)$ for finite groups, from $O(m^{5/2})$ to $O(m)$ for planar rotations on the disk with $m$ harmonics, and from $Θ(L^3)$ to $Θ(L^2)$ for spherical 3D rotations using our augmented selective spherical bispectrum at band limit $L$. The library is invariant up to floating-point error and computes selective $G$-bispectra in sub-millisecond time on GPU. We evaluate them as pooling layers on PatchCamelyon and OrganMNIST3D against five baselines. Across 46 comparisons, bispectral pooling remains competitive, matching all baselines on PCam and improving on max pooling by 5.0 percentage points on OrganMNIST3D. On Spherical MNIST, our method with an MLP head reaches 95.8% on rotated test digits, matching a spherical CNN at $4\times$ lower latency and coming within 0.3 percentage points of a tensor-product network at $364\times$ lower latency. Selective $G$-bispectra provide fast, competitive invariant layers for finite and continuous groups.

cs.LG

版本更新 · v2arXiv:2605.26399

OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following

Qiaomu Miao, Haoyu Wu, Jingyi Xu, Minh Hoai, Dimitris Samaras

原文摘要

Understanding human gaze behavior is essential for complex scene comprehension and human-computer interaction. Traditional gaze following models are typically restricted to pure spatial localization, lacking the high-level capacity to reason about semantic targets or complex social contexts. Furthermore, these models often process individuals sequentially, requiring redundant computations over the same scene image for multi-person inference. While recent Vision-Language Models (VLMs) offer the exceptional semantic reasoning needed to address gaze-related semantic tasks, their reliance on discrete text generation inherently limits precision in continuous spatial tasks like gaze localization. To bridge this gap, we propose OmniGF, a unified vision-language framework that adapts foundational VLMs for highly scalable multi-person gaze reasoning. The model adopts a dual-branch decoding strategy: a structured language branch generates discrete reasoning states, while a continuous spatial branch directly taps into the VLM's dense hidden states. Supervising these extracted representations with high-resolution gaze target heatmaps effectively overcomes the spatial bottleneck of text-only coordinate generation. Furthermore, to explicitly ground the model in multi-person scenes, we augment the input with head embeddings encoded from cropped head images, providing fine-grained appearance and orientation cues for all individuals simultaneously. By modeling all individuals and leveraging the strong semantic capability of VLMs, OmniGF seamlessly integrates precise spatial gaze target estimation, semantic gaze prediction, and complex social gaze reasoning. Extensive experiments demonstrate that our framework establishes new state-of-the-art performance across multiple standard benchmarks. Code is available at https://github.com/cvlab-stonybrook/omnigf.

cs.CV

版本更新 · v2arXiv:2602.14917

BFS-PO: Best-First Search for Large Reasoning Models

Fiorenzo Parascandolo, Wenhui Tan, Enver Sangineto, Xiaoyi Yu, Ruihua Song, Rita Cucchiara

原文摘要

Large Reasoning Models (LRMs) have shown excellent performance in reasoning tasks using long Chains of Thought (CoTs). However, this has also led to a significant increase of computational costs and the generation of verbose output, a phenomenon known as overthinking. The tendency to overthink is often exacerbated by Reinforcement Learning (RL) algorithms such as GRPO/DAPO. In this paper, we propose BFS-PO, an RL algorithm which alleviates this problem using a Best-First Search exploration strategy. Specifically, the reasoning chains generated at training time by BFS-PO are organized into a search tree, within which the shortest correct sequence is selected as the best and expanded using a backtracking mechanism based on maximum entropy nodes. In this way, we bias the exploration of the solution space towards the search for increasingly shorter solutions, training the LRM to generate progressively more concise answers. Using different benchmarks and base LRMs, we show that BFS-PO can simultaneously increase the LRM accuracy and shorten its reasoning chains.

cs.CL · cs.AI

版本更新 · v2arXiv:2608.16347

Architecture-Dependent Causal Transfer of Activation States Across Large Language Models

Fernando Cardenas Piepereit

原文摘要

Direct communication between AI systems relies on natural language as an intermediate layer, incurring encoding/decoding overhead, token cost, and latency. We ask whether internal activation states can instead be transferred causally between different large language model (LLM) architectures via a learned projection, evaluated at three levels: representational similarity, cross-model retrieval from projected states, and end-to-end causal transfer via activation injection during generation. Using four architecturally diverse open-weight models (Qwen2-0.5B, Phi-3-mini, Mistral-7B, FLAN-T5-base), we find that representational alignment in trained models exceeds a random-initialization null baseline and is best captured by a rank-based metric (mutual k-nearest-neighbour alignment), more robust to activation-magnitude outliers than centered kernel alignment (CKA) or Procrustes analysis. A learned projection network retrieves the correct target-model representation from a held-out set well above chance for the three causal decoder-only model pairs (45-50% top-1 accuracy vs. 5% chance) but at chance level for the encoder-based FLAN-T5. Injecting projected activations into a target model during generation produces a statistically significant, pre-registered causal effect on retrieval-based output similarity for only one of the three decoder-only pairs (Qwen2-0.5B to Phi-3-mini: 23.3% vs. 0.0% under negative control, p=0.047, FDR-corrected); the two pairs targeting Mistral-7B show no such effect despite comparable representational alignment at the hidden-state level. We interpret these results as evidence for causal transfer of the representational vehicle, not of meaning, and conclude that end-to-end activation-state transfer between LLMs, as currently implemented, is architecture-dependent rather than universal.

cs.CL · cs.LG

版本更新 · v2arXiv:2606.29623

SCARCE: Scalable Cascade Analysis for Rare-event Characterisation via Embeddings

Yingjie Wang, Yi Dong, Edmund Lau, Jie Meng, Taylor T Johnson, Xiaowei Huang

原文摘要

Rare events govern the safety profile of modern AI systems, yet their probabilities are extremely difficult to estimate: direct Monte Carlo requires prohibitive sample budgets. Subset Simulation (SS) addresses this by decomposing a rare-event probability into moderate conditional probabilities over nested intermediate events. However, classical SS requires a handcrafted scalar performance function whose sublevel sets define those events, demanding detailed knowledge of the failure geometry and limiting transfer to new domains. We propose SCARCE (Scalable Cascade Analysis for Rare-event Characterisation via Embeddings), which replaces the performance function with learned latent representations and geometric rulers that score proximity to failure regions. Adaptive thresholding constructs nested intermediate events directly from data. We formalise SCARCE through a non-negative supermartingale, yielding a high-probability upper envelope that remains valid under early stopping. On MNIST misclassification, where dense Monte Carlo provides ground truth, SCARCE achieves approximately 400--500 times lower mean absolute error than grid-searched traditional SS while eliminating systematic over-counting. We then study PAIR-style LLM jailbreaks under a fleet-level threat model with adversarial fraction $η$. On Llama-Guard-3-8B hidden states, a PCA-based ruler attains 2.6% mean relative error for $η\geq 10^{-3}$ against finite-sample references whose average bootstrap relative half-width is 27.9%, and transfers to a GCG-style corpus with 2.93% relative error after recalibration. A directional criterion $\mathrm{KL}(p_{\mathrm{good}}\,\|\,p_{\mathrm{bad}})$ ranks rulers consistently with estimation error (Spearman $ρ=0.83$).

cs.AI · cs.LG

版本更新 · v2arXiv:2609.12980

Transpilation-Aware Runtime Prediction for Noisy Quantum Circuit Simulation

Davud Azizov, Javier Vela-Tambo, Tian Guo

原文摘要

Predicting the runtime of noisy quantum circuit simulations is important for scheduling, resource allocation, and performance optimization. However, accurate prediction is challenging because backend-aware transpilation can substantially alter the original circuit structure, while the backend-derived noise model and simulator execution behavior can introduce additional runtime variation. We study the effectiveness of graph neural networks (GNNs) and conventional regression methods in predicting Qiskit Aer simulation runtime measured after transpilation. We construct a dataset from a benchmark pool of 1,402 unique circuits spanning 22 circuit families, two Qiskit fake-backend configurations, and four transpiler optimization levels. Specifically, we compare a source GNN using original circuit information, hybrid GNN combining source-level graph with post-transpilation features, and transpiled GNN using only transpiled circuit information, along with five regression models. In the overall-model setting, the transpiled GNN achieves the strongest performance among the graph-based representations at all four optimization levels, obtaining $R^2$ values of 0.974, 0.713, 0.745, and 0.605 for optimization levels 0 through 3, respectively. However, under backend-specific evaluation, the advantage of GNN decreases, with conventional regression models matching or outperforming the GNNs in several settings. These results indicate that post-transpilation information is useful, while the value of explicit graph modeling depends on the backend and optimization level.

quant-ph · cs.PF

版本更新 · v2arXiv:2610.26507

Learn the Task, Not the Schedule: Reducing Spurious Cross-Arm Coupling in Bimanual Imitation Learning

Shuyuan Hu, Deng-Ke Wu, Yifan Jin, Qianhang Luo, Mingchen Ju, Kai Ye, Bo Zhao

原文摘要

A bimanual demonstration specifies both what the robot should do and one particular schedule for when each arm should act. Standard imitation learning does not distinguish task-required cross-arm constraints from incidental scheduling choices, and may therefore exploit opposite-arm progress as a shortcut cue, creating spurious cross-arm coupling even where relative timing is irrelevant for the current task phase. We introduce Constraint-preserving Temporal Recombination (CTR), a training-time data intervention that preserves recorded arm-local sensorimotor content while retiming the corresponding segments to realize admissible schedules that preserve task-required cross-arm constraints. We use CTR to train Diffusion Policy, Action Chunking with Transformers, and $π_{0.5}$, and evaluate them on four simulated and four real-robot tasks. Across six real-robot bimanual progress-state initializations, CTR raises worst-state success from 56% for the strongest non-CTR schedule mixture to 76%. With $π_{0.5}$ on an Independent task, a 4 s pause transfers 2.56 s of delay to the opposite arm under the Concurrent schedule distribution, but only 0.25 s with CTR. On real robots, CTR violates task constraints in only 0--4% of trials, versus 36--98% for narrow-schedule baselines. Code will be released at https://github.com/MINT-SJTU/CTR.

cs.RO · cs.AI · cs.LG

版本更新 · v2arXiv:2607.17147

SlotGuard: Stop Oversharing Private Local Context in LLM Agent Transcripts

Haocheng Xia, Yongjoo Park

原文摘要

LLM agents can expose private local context (e.g., paths, emails) and credentials (e.g., API keys) as agent observations (e.g., tool outputs, shell logs, and file reads) are appended to provider-bound transcripts. Existing placeholder redaction is brittle: it can miss embedded or cross-turn references, over-redact benign lookalikes, and destroy the structure useful for reasoning. We present SlotGuard, a local transcript boundary that can hide sensitive data while retaining agents' performance. SlotGuard rewrites structural bindings as typed, suffix-aware slots, replaces secrets with format-preserving synthetic values, links cross-turn references with a lightweight session graph, and restores raw values only inside the trusted runtime. On controlled repository-oriented agent transcripts, SlotGuard removes all 20,814 annotated structurally sensitive characters across 9,229 paths and reduces credential leakage to 0.0% across 852 planted values. It remains close to raw-transcript task success across four upstream models, while generic redaction drops to 2.5%. Deterministic transcript rewriting takes a median of 14.424 microseconds per agent turn, excluding the optional semantic detector. The code is publicly accessible at https://github.com/illinoisdata/SlotGuard.

cs.CR · cs.CL

版本更新 · v6arXiv:2507.06565

A Mathematical Theory of Discursive Networks

Juan B. Gutiérrez

原文摘要

Large language models (LLMs) turn writing into a live exchange between humans and software. We characterize this new medium as a discursive network that treats people and LLMs as equal nodes and tracks how their statements circulate. We define the generation of erroneous information as invalidation (any factual, logical, or structural breach) and show it follows four hazards: drift from truth, self-repair, fresh fabrication, and external detection. We develop a general mathematical model of discursive networks that shows that a network governed only by drift and self-repair stabilizes at a modest error rate. Giving each false claim even a small chance of peer review shifts the system to a truth-dominant state. We operationalize peer review with the open-source \emph{Flaws-of-Others (FOO) algorithm}: a configurable loop in which any set of agents critique one another while a harmonizer merges their verdicts. We identify an ethical transgression, epithesis, that occurs when humans fail to engage in the discursive network. The takeaway is practical and cultural: reliability in this new medium comes not from perfecting single models but from connecting imperfect ones into networks that enforce mutual accountability.

cs.CL · cs.LG

版本更新 · v2arXiv:2505.17861

Superplatforms are Strategically Compelled to Counteract AI Agents

Jianghao Lin, Jiachen Zhu, Zheli Zhou, Yunjia Xi, Weiwen Liu, Yong Yu, Weinan Zhang

原文摘要

Over the past decades, superplatforms, digital companies that integrate a vast range of third-party services and applications into a single, unified ecosystem, have built their fortunes on monopolizing user attention through targeted advertising and algorithmic content curation. Yet the emergence of AI agents driven by large language models (LLMs) threatens to upend this business model. Agents can not only free user attention with autonomy across diverse platforms and therefore bypass the user-attention-based monetization, but might also become the new entrance for digital traffic. Hence, we argue that superplatforms have to attack AI agents to defend their centralized control of digital traffic entrance. Specifically, we analyze the fundamental conflict between user-attention-based monetization and agent-driven autonomy through the lens of our gatekeeping theory. We show how AI agents can disintermediate superplatforms and potentially become the next dominant gatekeepers, thereby forming the urgent necessity for superplatforms to proactively constrain and attack AI agents. Moreover, we go through the potential technologies for superplatform-initiated attacks, covering a brand-new, unexplored technical area with unique challenges. We have to emphasize that, despite our position, this paper does not advocate for adversarial attacks by superplatforms on AI agents, but rather offers an envisioned trend to highlight the emerging tensions between superplatforms and AI agents. Our aim is to raise awareness and encourage critical discussion for collaborative solutions, prioritizing user interests and perserving the openness of digital ecosystems in the age of AI agents.

cs.AI · cs.CY · cs.IR

版本更新 · v3arXiv:2604.17958

MINT-Bench: A Comprehensive Multilingual Benchmark for Instruction-Following Text-to-Speech

Huakang Chen, Jingbin Hu, Liumeng Xue, Qirui Zhan, Wenhao Li, Guobin Ma, Hanke Xie, Dake Guo 等 15 位作者

原文摘要

Instruction-following text-to-speech (TTS) has emerged as an important capability for controllable and expressive speech generation, yet its evaluation remains underdeveloped due to limited benchmark coverage, weak diagnostic granularity, and insufficient multilingual support. We present \textbf{MINT-Bench}, a comprehensive multilingual benchmark for instruction-following TTS. MINT-Bench is built upon a hierarchical multi-axis taxonomy, a scalable multi-stage data construction pipeline, and a hierarchical hybrid evaluation protocol that jointly assesses content consistency, instruction following, and perceptual quality. Experiments across ten languages show that current systems remain far from solved: frontier commercial systems lead overall, while leading open-source models become highly competitive and can even outperform commercial counterparts in localized settings such as Chinese. The benchmark further reveals that harder compositional and paralinguistic controls remain major bottlenecks for current systems. We release MINT-Bench together with the data construction and evaluation toolkit to support future research on controllable, multilingual, and diagnostically grounded TTS evaluation. The leaderboard and demo are available at https://aslp-lab.github.io/MINT-Bench-Demo/

eess.AS · cs.SD

版本更新 · v2arXiv:2611.08175

PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers?

Yue Zhang, Jilei Sun, Liqiang Jing, Yijie Wei, Ruohan Yang

原文摘要

Automating printed circuit board (PCB) routing requires coordinating board-level connectivity decisions with geometric execution under strict design rules. Although recent agents can interact with native routing tools, reliable routing on complex boards remains challenging. We present PCBRouteAgent, a multimodal PCB routing agent inspired by how human engineers coordinate global strategy with local execution. A Global Routing Planner combines board images and structured electrical and geometric information to specify connection topology, routing order, corridors, and layer transitions. A Detailed Routing Executor realizes these guides through KiCad's native routing engine and performs bounded local recovery. Unresolved failures are returned as structured feedback, enabling targeted guide revisions while preserving accepted routes. We evaluate PCBRouteAgent on 247 synthetic and real-world boards from four PCBWorld-Bench test splits. It achieves clean-pass rates of 100%, 94.9%, 100%, and 40% on D2, D3-A, D3-B, and D3-C, respectively. On the three real-world subsets, PCBRouteAgent outperforms the best evaluated baseline in clean-pass rate by 13.9, 36, and 10 percentage points, respectively.

cs.AI

版本更新 · v2arXiv:2611.08203

Common zeros of homogeneous polynomials and the weight hierarchy of projective Reed-Muller codes

Rodrigo San-José

原文摘要

We determine the maximum number of common zeros in projective space of any set of linearly independent homogeneous polynomials of the same degree, when the degree is smaller than the cardinality of the finite field. This proves the conjecture of Beelen, Datta, and Ghorpade, resolving a longstanding problem on common zeros and determining the complete weight hierarchy of the corresponding projective Reed-Muller codes. The proof uses Green's hyperplane restriction bound, combined with a footprint argument that reduces the problem to the affine case solved by Heijnen and Pellikaan. Wei duality then determines the hierarchy in sufficiently large degrees, recovering the complete hierarchy in every degree for the projective plane. Finally, we prove an upper bound valid in every degree, and conjecture that it is always sharp.

cs.IT · math.AC · math.AG

版本更新 · v4arXiv:2604.24357

DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Discrete Diffusion Models

Dake Bu, Wei Huang, Andi Han, Si Wu, Hau-San Wong, Qingfu Zhang, Taiji Suzuki, Atsushi Nitanda

原文摘要

Discrete diffusion models admit many token orders, yet most systems rely on confidence-based decoding. Confidence is a strong and efficient heuristic, but it can be myopic because local certainty does not measure a position's effect on terminal quality. We introduce DPRM (Doob h-transform Process Reward Model), a plug-in token-ordering module induced by a terminal-reward-tilted trajectory distribution. The Doob transform converts terminal reward into a process reward for each candidate position. A compact estimator indexed by generation progress, confidence, and optional positional or task state makes this correction reusable across partial states. DPRM changes only token order; the host architecture, denoising objective, supervision, and token sampler remain fixed. We derive the exact reward-tilted law and bound its shortlist and online approximations. Across nine recent open-source hosts spanning language, multimodal generation, and scientific sequences, DPRM improves reasoning, numeric VQA, visual-codebook ordering, and preference-conditioned generation. Relative to confidence, it improves PUMA GSM8K by 14.6%, Omni-Diffusion CLIP-L/14 by 13.2%, Prism voted accuracy from 82.41% to 83.85%, and RealWorldQA numeric/count accuracy by 8.97 points. Matched scientific gains include 8.3% in DCM nonzero recovery, 15.0% in GenMol QED, and 53.3% in SDPO-DNA total utility. Entropy and random-order controls show that the gains do not come from favoring uncertain tokens indiscriminately. Token-order traces and shared-state interventions instead show how terminal reward can correct a locally confident but globally poor choice. Code is available at: https://github.com/DakeBU/DPRM-DLLM.

cs.LG · cs.AI

版本更新 · v2arXiv:2611.06320

Conformal Prediction for Distribution-to-Distribution Regression

Trung-Khang Tran, Tuan A. Hoang, Viet-Hoang Tran, Tan M. Nguyen

原文摘要

Conformal Prediction (CP) provides a model-agnostic framework for constructing finite-sample prediction sets with coverage guarantees and has become a tool for reliable decision-making in high-risk settings. Recent advances have extended Split Conformal Prediction to increasingly complex learning problems, including multilabel, high-dimensional, and functional outputs. In this work, we study CP for Distribution-to-Distribution Regression, a setting of growing interest across many application domains. We show that a naive application of Split CP yields prediction sets that, while marginally valid, are non-interpretable, e.g., lacking a well-defined volume or a tractable sampling procedure, and of limited practical value. To overcome this, we propose a new conformal framework that operates in an orthogonal basis space, producing interpretable prediction sets while preserving coverage guarantees. We further develop an adaptive variant with asymptotic conditional coverage under mild assumptions. Empirical results on synthetic and real-world datasets validate the effectiveness of the proposed approach. The code is publicly available at https://github.com/tuanhacs/conformal_d2d.

cs.LG · cs.AI

版本更新 · v2arXiv:2510.25569

A Framework for Bounding Deterministic Risk with PAC-Bayes: Applications to Majority Votes

Benjamin Leblanc, Pascal Germain

原文摘要

PAC-Bayes is a popular and efficient framework for obtaining generalization guarantees in situations involving uncountable hypothesis spaces. Unfortunately, in its classical formulation, it only provides guarantees on the expected risk of a randomly sampled hypothesis. This requires stochastic predictions at test time, making PAC-Bayes unusable in many practical situations where a single deterministic hypothesis must be deployed. We propose a unified framework for extracting guarantees for a single hypothesis from PAC-Bayesian guarantees. We present a general derandomization framework, and derive from it a numerical bound for majority votes and for three different probability distributions over the posterior space. We study the empirical behaviour of our approach, showing that it consistently outperforms popular baselines in terms of generalization bounds for single classifiers (by up to a factor of 2), but sometimes requires a sacrifice in accuracy.

cs.LG

版本更新 · v2arXiv:2610.36143

Program-Level Adversarial Co-Adaptive Self-Play for Robotic Security

Leo Benaharon, Chi Zhang, Wei Zheng, Weifan Zhang, Yifan Wei, Yong Sun

原文摘要

Coding agents can adapt robotic software by revising executable programs, but successful responses to an evolving opponent may not remain effective. We present a framework for program-level adversarial co-adaptive self-play in which coding agents generate attacks and defenses from tested opponent code and mission feedback, without model fine-tuning. Environment-specific interfaces support external programs for autonomous driving and SDK-level defenses for humanoid locomotion. Two eight-generation case studies reveal concrete software responses: a driving defender introduces direct-actuation recovery, while a humanoid defender revises incoming-state validation. These responses provide local task recovery but do not establish sustained robustness. The framework makes such adaptation and limitations observable through executable artifacts and task-level evidence.

cs.RO

版本更新 · v2arXiv:2603.12300

Internet-Scale Measurement of React2Shell Exploitation Using an Active Network Telescope

Aakash Singh, Kuldeep Singh Yadav, Md Talib Hasan Ansari, V. Anil Kumar

原文摘要

The increasing adoption of server-side component-based web frameworks has introduced new application-layer attack surfaces that remain insufficiently understood at Internet scale. On 3 December 2025, a critical remote code execution vulnerability (CVE-2025-55182) in React Server Components, referred to as React2Shell, was publicly disclosed and subsequently observed being exploited in the wild. Despite its critical severity and a CVSS base score of 10.0, there is limited empirical understanding of how this vulnerability is exploited across the Internet. This paper presents the first Internet-scale measurement study of React2Shell exploitation activity using traffic collected from an Active Network Telescope. We developed a deterministic detection methodology that identifies exploitation attempts targeting endpoints implementing React Server components. It helped analyze exploitation traffic to characterize its temporal evolution, geographic and autonomous system-level distribution, and behavioral properties of the observed scanning activity. In addition, exploit payloads are examined to understand the attacker infrastructure and delivery mechanisms. The analysis reported rapid post-disclosure exploitation activity exhibiting patterns consistent with automated scanning campaigns, geographically distributed scanners, and concentrated backend infrastructure. To the best of our knowledge, this work provides the first quantitative characterization of React2Shell-triggered scanning activity, including the number of distinct scanners, their geographic and autonomous system distribution, and the scale of backend infrastructure involved in exploitation attempts.

cs.CR · cs.NI

版本更新 · v2arXiv:2602.04736

Conditional Counterfactual Mean Embeddings: Doubly Robust Estimation and Learning Rates

Thatchanon Anancharoenkij, Donlapark Ponnoprat

原文摘要

A complete understanding of heterogeneous treatment effects requires fully capturing the conditional distribution of the counterfactual outcomes. To this end, we propose the Conditional Counterfactual Mean Embeddings (CCME), a framework that embeds conditional distributions of counterfactual outcomes into a reproducing kernel Hilbert space (RKHS). Under this framework, we develop a two-stage meta-estimator for CCME that accommodates any RKHS-valued regression in each stage. Based on this meta-estimator, we develop three practical CCME estimators: (1) Ridge Regression estimator, (2) Deep Feature estimator that parameterizes the feature map by a neural network, and (3) Neural-Kernel estimator that performs RKHS-valued regression, with the coefficients parameterized by a neural network. We provide finite-sample convergence rates for all estimators, establishing that they possess the double robustness property. Our experiments demonstrate that our estimators accurately recover distributional features including multimodal structure of conditional counterfactual distributions. Our code is available at https://github.com/donlap/Conditional-Counterfactual-Mean-Embeddings.

stat.ML · cs.LG

版本更新 · v2arXiv:2607.26515

HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models

Hei Yi Mak, Shadan Golestan, Hoang Le, Mehran Taghian Jazi, Yunke Peng, Yaoyuan Wang, Yao Wang, Junsong Wang 等 13 位作者

原文摘要

We present, to our knowledge, the first end-to-end FP4 RL post-training, in which both the rollout and training policies, including their forward and backward passes, operate at 4-bit precision. A systematic study reveals that the dominant source of degradation in FP4 RL is not training-side quantization error but rollout activation quantization: outliers stretch the dynamic range so far that a large number of activation values underflow to zero under FP4. Counterintuitively, restoring the training policy to higher precision while keeping the rollout in FP4 makes accuracy worse than full FP4 baseline, exposing rollout--training mismatch as the principal failure mode and ruling out standard pretraining-style fixes. We address this with Rollout Residual Quantization (Rollout-ResQ): a single residual correction term constrained to a hardware-friendly sparsity pattern, added only to the FP4 rollout matmul -- a lightweight correction that recovers most of the precision lost to outlier-driven underflow without inflating the rollout's compute footprint. On Qwen2.5-3B, Rollout-ResQ paired with the HiFloat4 (HiF4) format -- whose three-level hierarchical scaling preserves resolution under FP4's tight 4-bit budget -- closes the accuracy gap to BF16 from 3.59% to 1.39%, bringing fully quantized FP4 RL within close reach of full precision. Applied to the open-standard MXFP4, the same recipe narrows the gap from 13.6% to 5.3%, revealing that FP4 format choice is a key factor that determines the ceiling on recoverable accuracy. The experimental results on Qwen2.5-Math-7B further confirm the recovery benefits of Rollout-ResQ with HiF4. Together, these results establish HiF4 as the enabling format for end-to-end FP4 RL post-training, and Rollout-ResQ as the activation-side mechanism that makes the gap to BF16 closable.

cs.LG · cs.AI

版本更新 · v3arXiv:2607.09489

Ceci n'est pas une pipe: A semantics of justified reliance for AI systems

Jade Alglave, Patrick Cousot

原文摘要

An AI agent may keep a successful check in context after an edit has invalidated its evidence. We give a semantics for specifying when a system may rely on a message and act on it. Reliability checks an asserted claim against accepted domain knowledge, sources, and messages in the selected context. Justified reliance additionally checks current evidence, authority, and the proposed world change. Relational component semantics and event traces represent nondeterministic outputs, iteration, and external changes. We characterise when merging claims preserves derivable conclusion classes, then construct the coarsest permitted quotient whose rules preserve the exact statuses of designated concrete claims. Construction is polynomial for unary rules; deciding even one permitted merge is coNP-complete for acyclic binary rules. This applies completeness and strong-preservation methods to the execution of quotiented rules. We also relate transition safeguards to runtime enforcement. Relative to a supplied set of possible worlds, a sound guard accepts an observation only when every matching world passes the checks. Exact acceptance requires observations that distinguish opposite-decision worlds; choosing sufficient services is NP-complete on explicit finite tables. A complete finite passport-renewal instance, Lean theorem encodings, Z3 instance checks, and an OCaml harness exercise the semantics. Domain knowledge, interpretation, source licenses, and policy remain application inputs.

cs.AI · cs.PL

版本更新 · v2arXiv:2610.11288

Memorization and Malign Generalization in Conditional Diffusion Models with Random Features

Gwangho Kim, Sungyoon Lee

原文摘要

Conditional diffusion models generate diverse, novel, and high-quality samples under prescribed conditions. However, theoretical understanding of their memorization and generalization remains limited, while recent works have characterized these behaviors primarily in unconditional settings. In this work, we analyze a random-feature conditional score model in the high-dimensional proportional limit, deriving asymptotic expressions for training and test losses. By decomposing the test loss, we show that in the overparameterized regime, increasing model width improves prediction of the condition-dependent mean while reducing within-condition prediction variance, a phenomenon we term "malign generalization." We further show that in the infinite-width limit, the model predicts the conditional mean as accurately as ridge regression of the data on the condition, while its within-condition variance vanishes. Finally, analyzing the training loss reveals that more informative conditions lead to memorization of training samples at smaller widths. These theoretical findings are supported by experiments with U-Net architectures on realistic data.

cs.LG

版本更新 · v3arXiv:2607.10103

LLM Watermarking as Big Data Provenance: A Deployment-Oriented Systematization

Huy Phan, Kieu Dang, Ojaswi Dulal, Aiham AL Shukairi, Abby Shine, Chase Garner, Phung Lai

原文摘要

As large language models (LLMs) generate and transform content at scale, reliable attribution becomes an increasingly important requirement for big data provenance. Although numerous watermarking methods have been proposed, existing evaluations predominantly emphasize sample-level detectability and robustness, leaving deployment requirements such as serving efficiency, population-scale false positives, multi-key attribution, and long-term verification less systematically examined. This paper presents a deployment-oriented systematization of LLM watermarking through the five Vs of big data: Volume, Velocity, Variety, Veracity, and Value. We classify representative watermarking methods across four dimensions: insertion point, verification authority, operational state, and adversarial threat model. We further map these methods to four deployment workloads: online generation, streaming detection, transformation pipelines, and ecosystem governance. Our synthesis identifies recurring limitations, including dependencies on generation-time access, additional inference overhead, sensitivity to downstream transformations, and incomplete reporting of calibration and lifecycle compatibility. Based on these findings, we propose workload-specific evaluation requirements covering statistical reliability, throughput, utility, robustness, and governance. This framework connects watermark design choices to practical deployment constraints and provides guidance for selecting and evaluating provenance mechanisms in large-scale data ecosystems.

cs.CR · cs.CL

版本更新 · v2arXiv:2605.26379

When Does LeJEPA Learn a World Model?

David Klindt, Yann LeCun, Randall Balestriero

原文摘要

A representation that scrambles the true degrees of freedom of the world cannot support reliable planning or compositional generalization. We prove that LeJEPA (alignment plus Gaussian regularization) linearly recovers the world's latent variables from nonlinear observations, a property known as linear identifiability, in a class of worlds where latents evolve under stationary, additive-noise transitions. Our main result is that among all such worlds, the Gaussian is the unique latent distribution for which this guarantee holds. The forward direction rests on a spectral decomposition in which each degree of nonlinearity is strictly penalized by alignment, making the linear map the optimum; the converse rules out every non-Gaussian alternative. We further prove an approximate identifiability result where the guarantee degrades gracefully, and show that linear, orthogonal identifiability enables optimal latent-space planning. We validate the theory with experiments ranging from 2D examples to 4096-dimensional latents, including ablations, pixel-based robotic control, and natural images from ImageNet-X. Our theory turns an empirically successful recipe into a mathematical guarantee, providing the foundation for building World Models that provably recover the structure of the world.

stat.ML · cs.LG

版本更新 · v2arXiv:2611.00162

Beyond Typical Strings: Sampling the Complexity Landscape

Abdurrahman Hadi Erturk, Joshua Sharkey, Nora S Martin, Kamal Dingle, Ard A Louis

原文摘要

Uniform random sampling of strings is overwhelmingly dominated by high-complexity strings, leaving the much smaller set of low- and intermediate-complexity strings largely unexplored. Here, we adapt the nested neutral set estimator (NNSE), a Monte Carlo rare-event sampling method, to estimate the distribution P(K) of complexity values for binary strings of fixed length. NNSE allows us to explore the full complexity landscape, including exponentially rare low-complexity regions that are inaccessible to direct sampling, for string lengths up to several hundred. We apply the method to several widely used complexity measures: Lempel-Ziv 76 (LZ76), Lempel-Ziv 78 (LZ78), context tree weighting (CTW), the block decomposition method (BDM), and block entropy. We further introduce uniform complexity weighting (UCW), which gives equal weight to different complexity levels rather than to individual strings. Using NNSE to perform UCW sampling allows us to compare complexity measures across their full range in a dataset-independent way. This reveals differences in their behavior for low- and intermediate-complexity strings that are practically inaccessible to conventional uniform sampling.

cs.IT

版本更新 · v3arXiv:2609.27710

FFM-CP: Cross-Backbone Fusion of Vision-Language Foundation Models for Few-Shot Computational Pathology

Anh-Tien Nguyen, Trung Dang, Nghiem Tuong Diep, Bui Ngoc Han Nguyen, Tan-Ha Mai, Miriam Cindy Maurer, Phuong Hoa Nguyen, Thi Thuy Uyen Nguyen 等 12 位作者

原文摘要

Pathology vision-language foundation models vary in performance across diseases and tasks, with no single model consistently performing best. The high cost of expert pathology annotation can also limit the labeled data available for task-specific adaptation. Combining complementary pretrained representations is a potential approach to these limitations, yet learning an effective fusion from few labeled examples remains challenging. We introduce Few-shot Fusion Foundation Models of Computational Pathology (FFM-CP), which is a framework that combines multiple pathology vision-language models in the few-shot learning setting. The framework first aligns heterogeneous representations using a closed-form Orthogonal Procrustes transformation estimated from corresponding support images. This alignment preserves within-model feature geometry without training an additional alignment network. Within the aligned space, a unified graph enables information exchange across backbones by jointly refining support-image features and visual and textual class prototypes. These refined representations support complementary text-prototype and case-retrieval branches that capture semantic class knowledge and within-class visual variation, respectively. Each branch learns to combine predictions from all ordered backbone pairs, allowing queries encoded by one model to draw on evidence represented by another. We evaluate three backbone combinations on six histopathology datasets at 4, 8, and 16 shots per class. FFM-CP achieves higher mean macro-F1 than the strongest individually adapted member of each fused set in 50 of 54 comparisons. These findings suggest that combining complementary pretrained representations can improve histopathological classification when annotations are limited.

cs.CV · cs.LG

版本更新 · v2arXiv:2510.20708

ALICE-LRI: A General Method for Lossless Range Image Generation for Spinning LiDAR Sensors without Calibration Metadata

Samuel Soutullo, Miguel Yermo, David L. Vilariño, Óscar G. Lorenzo, José C. Cabaleiro, Francisco F. Rivera

原文摘要

3D LiDAR sensors are widely used in autonomous navigation, environmental monitoring, and precision mapping. Their point clouds are often projected into 2D range images for efficient processing, but conventional projection methods can lose points because of geometric inconsistencies. We present ALICE-LRI (Automatic LiDAR Intrinsic Calibration Estimation for Lossless Range Images), a metadata-free method for lossless range-image generation from calibrated spinning multi-beam LiDAR point clouds. It requires neither factory calibration files, packet-level data, nor beam identifiers, and targets operating regimes where scanlines contain enough returns for reliable parameter estimation. The method estimates the intrinsic calibration parameters relevant to projection, including beam configuration, angular distributions, and per-beam geometric corrections. Evaluation on the complete KITTI and DurLAR datasets yielded zero lost points across all point clouds. Reconstruction deviations remain below manufacturer-reported range-performance specifications, while the method runs in real time. A compression case study also shows improved reconstruction quality and a better quality-compression trade-off for a downstream application. These results enable range-image-based LiDAR processing in applications that require high measurement fidelity and preservation of acquired geometric information.

cs.CV · cs.RO