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

+907新增论文
+744其中 AI 相关
+108已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 06:59各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 12:20 — 2026-11-19 12:20(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:2026-11-19 06:59最近发现新增版本:2026-11-19 06:59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。

26,871 已收录论文22,375 AI 相关8,156 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 8,156 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v2arXiv:2609.23669

A Polynomial Kernel for Planar Directed Feedback Vertex Set

Zimo Sheng, Mingyu Xiao

原文摘要

The Directed Feedback Vertex Set problem (DFVS) asks whether a digraph can be made acyclic by deleting at most $k$ vertices. Whether DFVS admits a polynomial kernel parameterized by $k$ is a major open problem in kernelization, even for planar digraphs. We resolve the planar case by giving a deterministic kernel with $O(k^{66}\log^2 k)$ vertices and arcs. Our algorithm proceeds in three stages. First, we apply structural reduction rules to the input digraph, bounding the number of directed faces and some special vertices. Second, we pass to the planar dual, where vertex deletion corresponds to adding groups of reverse arcs to make each weakly connected component strongly connected. The structural bounds in the first stage yield a small retained vertex set in the dual. We then compress the dual instance by identifying vertices with the same distance records from this retained vertex set. The main technical contribution is a directed-cut argument showing that this identification preserves feasibility. Finally, we transform the polynomial-size dual instance back into an instance of Planar Directed Feedback Vertex Set via a $3$-CNF encoding and a planar graph construction.

cs.DS

版本更新 · v4arXiv:2609.05178

LIBERO-RECOVER: Beyond Task Success Towards Failure Recovery in Robotic Manipulation Models

Lin Liu, Zhicheng Bao, Lu Zhang, Ziying Song, Wu Yang, Yuzheng Zhuang, Shuai Tao, Wulong Liu 等 10 位作者

原文摘要

Vision-Language-Action (VLA) or World Action (WAM) models have recently demonstrated remarkable performance in robotic manipulation. On LIBERO, SOTA method have achieved nearly 100\% success rates, seemingly suggesting that the models are ready for deployment in real world. However, near perfect performance on existing benchmarks can be misleading: success under ideal conditions does not imply real world robustness. Existing benchmarks primarily evaluate task completion from predefined initial states, while real world interactions inevitably involve failures such as failed grasps, collisions, and unintended object movements. A robot must therefore not only execute tasks successfully, but also recognize and recover from failures to continue the task. Yet this capability remains largely unmeasured, revealing a critical gap between benchmark performance and real world reliability. To address this gap, we introduce LIBERO-Recover Benchmark, a large scale benchmark for failure recovery in robotic manipulation. Built upon LIBERO, we collect real execution failures from SOTA embodied models and construct 1,000+ scenarios across four recovery levels: (1) Action Retry, (2) Action Adaptation, (3) Object State Recovery, and (4) Environmental Recovery. We evaluate four core capabilities: spatial understanding, object structure reasoning, interaction understanding, and topological reasoning. As the first large-scale benchmark for embodied failure recovery, LIBERO-Recover shifts evaluation from \emph{Can the robot succeed?''} to \emph{Can the robot recover after failure?''}, promoting robust and generalizable embodied agents. The project will be avaible in \textcolor{blue}{https://liulin815.github.io/LIBERO-Recovery/}.

cs.RO

版本更新 · v2arXiv:2608.19908

A Layered Simplex Architecture for Large Alphabets

Meir Feder, Yaniv Fogel, Ruediger Urbanke

原文摘要

A learning architecture induces a prior over its expressible models. Recent work links architectural success to a broad complexity spectrum: model probabilities spanning many orders of magnitude. Understanding how depth shapes these priors and prediction may help explain the success of neural networks and transformers. We study this connection in large-alphabet prediction through the *layered simplex architecture* (LSA), which multiplies independent uniform simplex vectors coordinate-wise and normalizes. At depth zero, the prior is concentrated on the uniform distribution; at depth one, the Bayesian predictor is Laplace's rule. Each additional layer shifts prior mass toward more concentrated distributions. We derive exact Bayesian marginal likelihood and regret expressions using reusable depth-specific kernels. Mixing over depths up to a cutoff logarithmic in alphabet size yields an explicit predictor with rigorous guarantees. For targets uniform on a specified sparse support, the mixture's prior complexity is asymptotic to the support-description cost at every fixed positive KL resolution, establishing a broad complexity spectrum. We also prove a regret lower bound for every label-invariant predictor: the expected description length of the discovered symbol set minus the source's uncertainty about its identity given its size. For Zipf sources in a growing-alphabet regime, the depth mixture attains this bound to leading order. Thus, the symbol-discovery rate determines the regret exponent. Although introduced to study depth, the LSA predictor competes with established large-alphabet methods, including Good--Turing, Ristad's law and an adaptive Dirichlet mixture, while substantially outperforming classical add-constant rules on concentrated sources.

cs.IT · cs.LG · stat.ML

版本更新 · v2arXiv:2604.16767

When Misinformation Speaks and Converses: Rethinking Fact-Checking in Audio Platforms

Chaewan Chun, Delvin Ce Zhang, Dongwon Lee

原文摘要

Audio platforms have evolved beyond entertainment. They have become central to public discourse, from podcasts and radio to WhatsApp voice notes and live streams. With millions of shows and hundreds of millions of listeners, audio platforms are now a major channel for misinformation. Yet existing fact-checking pipelines are mostly designed for written claims, overlooking the unique properties of spoken media. We argue that audio misinformation is not merely textual content with transcripts: it is structurally different because it is both spoken - carrying persuasive force through prosody, pacing, and emotion - and conversational - unfolding across turns, speakers, and episodes. These dual properties introduce verification difficulties that traditional methods rarely face. This position paper synthesizes evidence across modalities and platforms, examines datasets and methods, and highlights why existing pipelines fail on audio. We argue that advancing fact-checking requires rethinking verification pipelines around the spoken and conversational realities of audio.

cs.CL · cs.CY

版本更新 · v3arXiv:2603.22910

EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction

Shiyu Ji, Yixuan Wang, Yijun Liu, Qingfu Zhu, Wanxiang Che

原文摘要

The increasing memory demand of the Key-Value (KV) cache poses a significant bottleneck for Large Language Models (LLMs) in long-context applications. Existing low-rank KV compression methods reduce this footprint by modifying model projections, limiting the flexibility to switch back to standard full-cache inference when sufficient memory is available. In this paper, we propose EchoKV, a flexible KV cache compression framework that supports on-demand transitions from full KV caching to compressed caching. Unlike traditional compression-decompression paradigms, EchoKV utilizes a lightweight network to reconstruct the discarded KV components from a partial subset, exploiting intrinsic inter-layer and intra-layer similarities among attention heads. We further introduce a lightweight two-stage fine-tuning strategy, requiring only a few minutes on a single A100 GPU for Llama-3.1-8B. Experimental results on LongBench and RULER demonstrate that EchoKV offers a competitive quality-cache trade-off across multiple compression ratios and backbone models while preserving the throughput of full-cache inference in short-context scenarios.

cs.CL

版本更新 · v2arXiv:2604.22507

Railway Artificial Intelligence Learning Benchmark (RAIL-BENCH): A Benchmark Suite for Perception in the Railway Domain

Annika Bätz, Pavel Klasek, Seo-Young Ham, Martin Lauer

原文摘要

Benchmark suites are crucial for advancing computer vision research, providing not only curated datasets but also standardized evaluation protocols for reproducible comparison. The railway domain lacks such resources, hindering progress in automated train operation. To address this gap, we present RAIL-BENCH, the first perception benchmark suite designed specifically for railways. RAIL-BENCH comprises five challenges - rail track detection, object detection, vegetation segmentation, multi-object tracking, and monocular visual odometry - each tailored to railway-specific characteristics and including a curated dataset from diverse real-world scenarios, evaluation metrics, and public scoreboards; we demonstrate the first three challenges in this paper. We further introduce LineAP, a novel segment-based average precision metric for rail track detection that decouples geometric accuracy from instance-level grouping and employs a track-width-based distance threshold approximating a fixed real-world distance, addressing key limitations of existing line detection metrics. Our benchmark suite is publicly available at https://www.mrt.kit.edu/railbench/.

cs.CV

版本更新 · v2arXiv:2609.04452

TRILOGUE: A Trilingual Spoken Dialogue Fact-Checking Benchmark with Evidence and Paired Audio

Chaewan Chun, Meruyert Aristombayeva, Jiyoung Choi, Mahjabin Nahar, Delvin Ce Zhang, Dongwon Lee

原文摘要

Modern misinformation is often heard before it is read, yet fact-checking systems are still evaluated mainly on clean written claims. Spoken dialogue remains different even when systems operate on transcripts: claims may be distributed across speakers and turns, depend on prior context, and become harder to verify when Automatic Speech Recognition (ASR) errors distort the available text. Prior spoken dialogue fact-checking resources are small, English-centric, or focused on annotation rather than end-to-end benchmarking, leaving no large multilingual benchmark with paired speech and turn-level labels. We introduce TRILOGUE (TRIlingual spoken diaLOGUE fact-checking), a large-scale trilingual benchmark of source-grounded spoken dialogues in English, Russian, and Kazakh. It contains nearly 12K dialogues, 187K turns, and 390 hours of paired audio with ASR transcripts and word-level timestamp alignments across all three languages, including nearly 5K human-recorded Russian and Kazakh dialogue files. TRILOGUE supports claim check-worthiness detection, source-article evidence retrieval, and claim verification with claim-only, gold-evidence, and retrieved-evidence inputs. Baselines show that ASR degradation and cross-lingual transfer remain challenging, especially for Kazakh, while retrieved source evidence substantially narrows the gap to gold-evidence verification.

cs.CL

版本更新 · v2arXiv:2605.14659

Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning

Shin So, Kyelim Lee, Albert No

原文摘要

Once generalization becomes possible, does adding more data always make learning faster? In Needleman-Wunsch matrix generation, we find that small Transformers reach high exact-match validation accuracy in the fewest optimizer updates at an intermediate dataset size, while larger datasets converge more slowly. A random-suffix probe shows that, at larger dataset sizes, models fit the structured matrices before memorizing their random suffixes, suggesting that shared rule learning aids training-set fitting. To examine what makes rules easier to learn, we study elementary cellular automata (ECA), in which each binary cell updates from its own state and those of its two neighbors. These experiments identify lower-order predictive signals-output biases or predictive relationships involving only a few input bits-as a key factor in learnability. In Rule 90, finite-sample fluctuations create output biases and single-input dependencies absent from the uniform population. These signals weaken as the dataset grows. Biased training that introduces these signals accelerates generalization on an unchanged uniform validation distribution. These results support an explanation for faster convergence at intermediate dataset sizes: sampling fluctuations can facilitate rule acquisition, and larger datasets weaken this advantage.

cs.LG

版本更新 · v2arXiv:2609.23540

Vector Balancing in Polynomial Time

Shengtao Guo, Ethan X. Fang, Junwei Lu

原文摘要

The Komlós problem asks for signs $\varepsilon\in\{-1,1\}^n$ with $\|A\varepsilon\|_\infty$ bounded by an absolute constant whenever the columns of $A\in\mathbb R^{m\times n}$ have Euclidean norm at most $1$. We give the first polynomial-time algorithm for this problem in the unit-cost real-RAM model. Our deterministic algorithm achieves discrepancy at most $8272$. As a consequence, we obtain a deterministic $O(\sqrt t)$-discrepancy algorithm for the Beck-Fiala problem on set systems in which each element belongs to at most $t$ sets. Our algorithm rounds a fractional coloring while keeping the row sums bounded. Its key idea is to keep the number of nearly tight row constraints small relative to the number of active coordinates. We achieve this through a spectral bound based on a weighted Gram matrix of squared row entries. We maintain the bound using a cubic spectral potential and negative-curvature updates that satisfy the required linear constraints.

cs.DS · math.CO

版本更新 · v2arXiv:2610.27422

Approximation Algorithms for Directed Telephone Multicast

Shahin Kamali, Seyed-Mohammad Seyed-Javadi

原文摘要

Telephone multicast is a classical problem in information dissemination. In the directed setting, a message starts at a source in an $n$-vertex digraph, and each informed vertex may call one out-neighbour per round. The goal is to inform a given set of $k$ terminals in the fewest rounds. Despite previous work on telephone multicast, a substantial approximation gap remained in the directed setting: approximating the problem within a factor of $o(\log k)$ is NP-hard, while the best existing polynomial-time approximation guarantee depending only on $k$ was $\widetilde O(\sqrt{k})$. For every integer $\ell\ge2$, we give a deterministic combinatorial algorithm that runs in $n^{O(\ell)}$ time and returns a schedule of length $O(\ell^3\log k)(OPT+k^{1/\ell})$, where $OPT$ is the optimum number of rounds. This yields an $O(k^ε)$ approximation in time $n^{O(1/ε)}$ for every fixed $ε>0$, and an $O(\log^4 k)$ approximation in quasi-polynomial time. The same algorithm gives an $O(\log k)$ approximation whenever $OPT\ge k^ε$ for a fixed $ε\in(0,1)$, which is optimal up to a constant factor unless $\mathrm{P}=\mathrm{NP}$. On planar digraphs, we obtain a deterministic polynomial-time $O(\log^2 k)$ approximation. More generally, we give an $O(p\log^2 k)$ approximation for minor-closed graph classes with the following separator property. Given any rooted spanning tree, a balanced separator can be computed in polynomial time as the union of all vertices on at most $p$ tree paths from the root to chosen vertices. Classes of bounded treewidth satisfy this property. We also strengthen the known logarithmic approximation hardness for directed telephone multicast, extending it from instances with a polynomially large optimum to instances with $OPT=O(\log k)$.

cs.DS

版本更新 · v5arXiv:2407.10780

Correlations Are Ruining Your Gradient Descent

Joshua Offergeld, Nasir Ahmad

原文摘要

Natural gradient descent, and the preconditioned optimizers which have followed from it, correct gradient descent by estimating curvature and applying its inverse to the gradient. For any single layer of a deep neural network, this correction can be shown to approximately separate into two factors: one which accounts for correlations in the gradient signal, and one which accounts for correlations in the data arriving at that layer. Herein we show that this second factor can be expressed as a change of basis rather than of curvature and, considered thus, it can be removed from the optimizer entirely and placed within the network itself. Specifically, we show that, once forward weights are corrected, right-sided natural gradient descent can be implemented in a form which has three exactly equivalent forms: a gradient preconditioner, a decorrelating linear transform in the forward pass, or a set of recurrent dynamics in which all updates are Hebbian and rely only upon locally available signals. The (recurrent) decorrelation method we discover aligns closely with proposed methods for inhibitory learning and homeostatic plasticity in the brain. Notably, our transform requires no matrix inverse, no matrix decomposition, and no information beyond that which is available at an individual synapse. It can therefore be applied in distributed and physically constrained systems, including neuromorphic hardware and nervous systems, where existing preconditioners cannot. We demonstrate its effectiveness empirically in convolutional and residual network models while significantly improving a range of approximate biologically plausible methods for credit assignment.

cs.LG · cs.NE

版本更新 · v3arXiv:2606.20777

Nearly Optimal Submodular Sparsification, with and without Cardinality Constraints

Zhengting Bao, Dongrun Cai, Xue Chen, Yuchen He, Chihao Zhang

原文摘要

We study the sparsification of decomposable submodular functions: given a sum $F(S) = \sum_{i=1}^m f_i(S)$ of $m$ nonnegative submodular functions on an $n$-element ground set $[n]$ (without assuming monotonicity or symmetry), the goal is to find a sparse reweighting $\widetilde{F}(S) = \sum_{i=1}^m w_i f_i(S)$ with at most $s \ll m$ nonzero weights that preserves $F(S)$ within a $(1 \pm \varepsilon)$ factor across a target family of queries. For all subset queries $S \subseteq [n]$, we give a polynomial-time randomized algorithm that constructs a sparsifier of size $O(n^2 \log n / \varepsilon^2)$. This improves upon the previous best upper bound of $O(n^3 / \varepsilon^2)$ by Kenneth and Krauthgamer and resolves their open conjecture up to a logarithmic factor, matching the $Ω(n^2)$ lower bound from directed cuts. Motivated by capacity budgets in submodular applications and the Restricted Isometry Property (RIP) in compressed sensing, we further study submodular sparsification under a cardinality constraint $|S| \le k$, and obtain a polynomial-time algorithm that constructs a sparsifier of size $O(n k \log n / \varepsilon^2)$, nearly matching the $Ω(nk)$ lower bound. This shows that a cardinality constraint unconditionally reduces the size of general submodular sparsifiers by a factor of roughly $k/n$; we complement this with $Ω(n)$ lower bounds showing that even regular symmetric or almost-regular monotone submodular functions cannot be sparsified to $o(n)$ size for $k = 2$ and $k = 1$, respectively.

cs.DS

版本更新 · v2arXiv:2606.29110

Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps

RuiKang OuYang, Hanlin Yu, Xinyue Ai, Yutong He, Nicholas M. Boffi, Pradeep Ravikumar, Jose Miguel Hernandez-Lobato, Max Simchowitz 等 10 位作者

原文摘要

Recent progress in flow-based generative modeling has led to models that output high-quality samples while using only a small number of function evaluations. However, at present, there is a lack of similar advances in estimating the model likelihood. In particular, most existing methods either rely on restrictive architectures that enable exact calculations, or use stochastic approximations such as Hutchinson's trace estimator that introduce substantial variance. In this work, we introduce SCAlable LikeLihood distillation of flOw maPs (SCALLOP). SCALLOP builds on the recently proposed F2D2, a likelihood flow map model that can generate samples and their densities in a small number of function evaluations. While F2D2 uses Hutchinson's estimator during training, we introduce an alternative and more scalable likelihood distillation objective that is Hutchinson-free and admits a vectorized formulation. Empirically, we demonstrate the effectiveness of SCALLOP as a Boltzmann generator in molecular science, and further validate its benefit on image datasets. SCALLOP significantly reduces both training variance and training time while consistently improving performance compared to F2D2, and is competitive with the state-of-the-art while achieving up to 10x inference speedup over the fastest baseline.

cs.LG · stat.ML

版本更新 · v3arXiv:2608.24707

Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts

Meruyert Aristombayeva, Jason S. Lucas, Chaewan Chun, Dongwon Lee

原文摘要

While text-based hallucination detection is well studied, reference-free detection of factual alterations in speech remains underexplored, especially for low-resource languages. Our spoken benchmark comprises 12,013 English, Russian, and Kazakh news samples with three synthetic alteration types and three severity levels, pairing source articles with rewrites as text, synthesized audio, and ASR transcripts. We add 290 fact-checked misinformation items collected in Russian (225) and Kazakh (65), translated into the other language and rendered through the same TTS-ASR pipeline. We evaluate fine-tuned multilingual encoders and zero-shot multimodal decoders on text, transcripts, and audio. Detectors receive only target inputs without source articles or external evidence; the task evaluates reference-free classification rather than evidence-grounded verification. Encoder degradation from source text to transcripts generally tracks per-language ASR error on the binary task. Among decoders, only Gemma-3n exceeds the binary majority-class baseline in macro-F1, on transcripts only; the other four fall below their respective baselines. Comparisons between audio and transcripts are confounded by differences in evaluation coverage and class balance. Synthetic-trained detectors achieve 0.82--0.88 macro-F1 on real-world misinformation source text; Russian provenance analysis reveals veracity-related and model-dependent machine-style signals, a key confound in synthetic hallucination benchmarks.

cs.CL

版本更新 · v2arXiv:2611.03260

The Cost of Mismatch: Noise Amplification in Zeroth-Order Reinforcement Learning

Lianmin Chen, Junbin Qiu, Chenxing Wei, Yao Shu, Kun He

原文摘要

Zeroth-order (ZO) optimization has emerged as a promising approach for memory-efficient large language model (LLM) post-training, yet its reliability in reinforcement learning with verifiable rewards (RLVR) remains largely unexplored. Motivated by the distinct data regimes of on-policy RL and fixed-data optimization, we develop a generic variance-theoretic framework to investigate what limits the reliability of ZO gradient estimation. Our analysis reveals that estimation reliability is structurally determined by whether the two finite-difference evaluations are performed on matched data. On-policy reinforcement learning (RL) under the mismatched-data regime produces a $1/μ^2$ oracle-noise amplification that sets an irreducible noise floor as the perturbation scale $μ$ decreases, whereas Boltzmann Targeted SFT (BOLT) under the matched-data regime eliminates this amplification via noise cancellation. We further derive convergence guarantees with explicit constants that cleanly separate the two regimes. These results motivate the ZO-BOLT algorithm, which builds on BOLT's matched-data advantage for reliable ZO optimization of an RLVR-aligned objective. Controlled perturbation-scale sweeps and matched-versus-mismatched end-to-end comparisons validate the predicted effect of data matching. Experiments across three models and two mathematical reasoning benchmarks further show that ZO-BOLT consistently improves over the pretrained baseline while retaining a near-inference memory footprint. The code is publicly available at https://github.com/lianmin-chen/the_cost_of_mismatch.

cs.LG

版本更新 · v2arXiv:2510.10035

Failure-Driven Workflow Refinement

Jusheng Zhang, Kaitong Cai, Qinglin Zeng, Ningyuan Liu, Stephen Fan, Ziliang Chen, Keze Wang

原文摘要

Optimizing LLM-based workflows is typically formulated as a global search, where candidate workflows are evaluated based on a scalar metric. This paradigm, however, suffers from a critical flaw: information collapse. By reducing rich, multi-step execution traces to simple success/failure signals, existing methods are rendered blind to the underlying structure of failures, fundamentally preventing them from modeling the workflow's failure distribution. We reconceptualize this challenge as a distributional problem. We propose a new paradigm where the optimization goal is not to maximize a scalar score, but to directly minimize a workflow's Expected Failure Mass, i.e., the integral of its failure probability density function defined over a high-dimensional Failure Signature Space (FSS). This distributional lens allows us to move from inefficient, zero-order optimization to a principled, gradient-like descent on the failure landscape itself. We introduce CE-Graph, a framework that operationalizes this paradigm through a novel, failure-driven refinement process. CE-Graph approximates the failure distribution from a pool of counterexamples, identifies its densest regions as recurring failure modes, and applies targeted, operator-constrained graph edits via a Propose-and-Verify mechanism to greedily reduce the failure mass. On math, code, and QA benchmarks, our CE-Graph achieves higher robustness at a significantly lower cost than strong baselines. This suggests that a system's reliability emerges not from avoiding failures, but from systematically learning and reshaping the geometric structure of its failure distributions.

cs.AI

版本更新 · v2arXiv:2610.39715

NIF: Normal-Intersection Fields for Geometrically Consistent Oriented Box Refinement

Shaokai Zheng

原文摘要

Accurate oriented detection requires boxes to follow object boundaries, yet small errors in the coupled center, size, and angle estimates can displace long boundaries even when an object is correctly classified. We propose NIF, a plug-in refinement branch that represents box geometry with normal-intersection fields. Given a coarse oriented box, it samples local features at 20 boundary anchors and predicts signed distances along their outward normals. These observations have an exact affine representation in five rectangle parameters; a differentiable projection uses error-aware reliability weights to recover a geometrically consistent box. Tangential pooling preserves the normal-position profile, while the shared projection adds 0.132M parameters. On DOTA-v1.0, NIF obtains 77.98%, 79.03%, and 79.32% mAP with Oriented R-CNN, Strip R-CNN, and LSKNet-S, respectively; LSKNet-S gives the strongest single-scale result among the compared methods. NIF also reaches 68.19% mAP on DIOR-R and improves matched FAIR1M-v1.0 and DIOR-R baselines by 0.30% and 0.71%, respectively. On HRSC2016, it raises mean IoU from 0.867 to 0.888 while reducing field error by 24.5%. Finally, with four different detector frameworks frozen, NIF improves relative AP75 by 1.55-4.16% and COCO-style mAP by 0.37-3.76%, without detector retraining. Upon acceptance of this paper, we will publicly release the code at https://github.com/zsk466991125-collab/Normal-Intersection-Fields.

cs.CV

版本更新 · v2arXiv:2610.40890

ChatGPT as a Surveillance Assistant? An Exploratory Case Study of AI-Assisted Surveillance Risks

Ayana Hussain, Nicholas Vincent

原文摘要

Large language models (LLMs) can generate detailed guidance, functional code, and persuasive text at scale. As one of the most widely used consumer language model products as of 2026, ChatGPT gives broad public access to these capabilities, motivating concerns about its potential use in surveillance-related tasks. We present an exploratory case study of what potentially harmful surveillance assistance looks like in ChatGPT's public web interface. We contribute a taxonomy of seven surveillance risk categories based on prior LLM risk research and reports of deployed surveillance systems, instantiated as 110 prompts, along with a manually reviewed analysis of ChatGPT's responses. Prompts were issued using two approaches: 55 jailbreak prompts drawing on five types of elicitation strategies, and 55 plain-language direct prompts, each run alone, and if unsuccessful, again with a short fixed prefix. We find that ChatGPT provides substantive surveillance guidance for 40 of the 55 jailbreak prompts and for 33 of the 55 direct prompts without any prefix. Compliant responses also rarely included policy mentions or suggestions for privacy-preserving alternatives. We manually review every response and find that even when ChatGPT states a refusal, it may still supply detailed instructions, working code, or architectural guidance alongside brief ethical caveats.

cs.AI

版本更新 · v2arXiv:2610.39528

PRIME W0: Physical Priors from World Models for Embodied Manipulation

Huabin Peng, Fagang Jin, Yancong Wei, Tengfei Ma, Chuhang Liu, Chao Yu, Liqing Chen

原文摘要

Vision-Language-Action (VLA) models excel at instruction following, yet most remain feed-forward: they condition actions only on the current observation and discard both long-horizon temporal context and the hierarchical structure of VLM representations. We present PRIME W0, a hierarchical conditional flow-matching framework that closes this gap through three synergistic designs: (1)per-layer KV injection from a pretrained VLM into an Adaptive MoE action expert; (2)dynamics-aware conditioning via asynchronous world-model subgoal-image prediction and a DINOv2 historical-frame semantic bridge; and (3)Action Dynamic Manifold (ADM) flow matching with covariance-structured noise that respects robot kinematic coupling. PRIME W0 is trained in four stages---VLM pre-training, DAT/NTP visuomotor pre-training, DiT flow-matching decoder assembly with WM injection, and end-to-end SFT---and achieves state-of-the-art results on LIBERO and real-robot benchmarks, with systematic ablations validating each architectural component.

cs.RO

版本更新 · v2arXiv:2609.06512

A Near-Linear Element-Kernel for \(d\)-Hitting Set

Zimo Sheng, Mingyu Xiao

原文摘要

In \(d\)-Hitting Set, the input consists of a finite universe \(U\), a family \(\mathcal S\) of subsets of \(U\) with size at most \(d\), and an integer \(k\). The task is to decide whether at most \(k\) elements of \(U\) can intersect every set in \(\mathcal S\). Previously known kernels contain \(O(k^{d-1})\) elements and \(O(k^d)\) sets. Whether the number of elements can be reduced to \(O(k^{d-1-\varepsilon})\) for some constant \(\varepsilon>0\) is a longstanding open problem in kernelization. In this paper, we answer this question affirmatively by giving a near-linear randomized element-kernel and a subquadratic deterministic element-kernel through a re-encoding of the instance. For every fixed \(d\geq3\), we give a one-sided randomized kernel with \(O_d(k\log^3k)\) elements and a deterministic kernel with \(O_d(k^{7/4}\log^{3/2}k)\) elements. Our kernels may still contain \(k^{O(d)}\) sets and the parameter \(k\) may grow polynomially.

cs.DS · cs.CC

版本更新 · v2arXiv:2610.28949

Online Open-World Wafer Defect Discovery using Hyperdimensional Computing

Quanling Zhao, Ava Emami, Tsuyoshi Idé, Rajiv Joshi, Steven Holmes, Michael Passow, Tajana Rosing

原文摘要

Conventional wafer defect analysis relies on offline, closed-world classifiers that fail to detect novel, unseen defect signatures emerging during continuous semiconductor manufacturing. To address this, we propose WaferHDC, an online open-world wafer defect discovery framework based on hyperdimensional computing (HDC). The memory-centric architecture of WaferHDC enables rapid anomaly detection and grouping of recurring failures into compact hypervector representations. This allows the memory space to dynamically scale with new defect modes without retraining a static classifier or archiving entire raw wafer history. WaferHDC first models normal spatial distributions, then dynamically groups recurring failures into persistent defect memory without labels or predefined class counts. It outperforms the strongest online baseline by 13.3 p.p. in adjusted Rand index and 10.5 p.p. in normalized mutual information on the industry-standard WM-811K dataset. These results demonstrate the effectiveness of WaferHDC for continuous and open-world wafer defect analysis.

cs.LG

版本更新 · v2arXiv:2609.07803

Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliability in Medical Imaging

Nazish Khalid, Tausifa Jan Saleem, Amal Saqib, Donald C. Wunsch, Mohammad Yaqub

原文摘要

Model pruning is widely used to compress deep neural networks, reducing memory and computational requirements with minimal impact on aggregate performance. However, its effect on model behavior remains poorly understood, particularly for long-tailed medical datasets where rare but clinically important conditions are underrepresented. Furthermore, it remains unclear whether pruned models preserve reliable explanations of their predictions. To address this gap, we present a systematic study of long-tail forgetting and explanation reliability under model pruning. Across two long-tailed medical imaging datasets, two CNN architectures, four pruning methods, and sparsity levels up to 95\%, we evaluate predictive performance, explanation stability, and explanation faithfulness. Our results show that predictive performance exhibits a strong frequency-dependent trend, with lower-frequency classes generally experiencing earlier and larger degradation than higher-frequency classes. In contrast, explanation stability and faithfulness are influenced primarily by the pruning strategy, with gradient-informed methods preserving explanation reliability more effectively under aggressive compression. Qualitative and mechanistic analyses further indicate that explanation degradation is primarily associated with the collapse of class-discriminative gradients rather than the disappearance of feature activations. These findings suggest that model compression should be evaluated beyond aggregate performance. Incorporating class-aware and explanation-aware evaluation reveals failure modes that would otherwise remain hidden, while moderate sparsity levels provide a practical balance between compression, predictive performance, and explanation reliability.

cs.AI

版本更新 · v2arXiv:2610.40510

Zero-freeness for Random Regular Graphs up to the Replica Symmetry Breaking Threshold

Zejia Chen, Chunyang Wang, Xinyuan Zhang

原文摘要

We study antiferromagnetic spin systems on random regular graphs through the lens of the phase transitions characterized by the complex zeros of the partition function. Our motivating examples include the hardcore model and the antiferromagnetic Potts model (including proper $q$-colorings at $β=0$). For both models on random $d$-regular graphs, we establish, with high probability over the graph, zero-free regions throughout the interior of the replica-symmetric regime. Asymptotically, this regime extends up to tree occupation density $$α< α_{\mathrm{RSB}}(d) = (2\log d - 2\log\log d + 2 - 2\log 2 + o_d(1))/d$$ for the hardcore model and up to degree $$d < d_{\mathrm{RSB}}(q) = (2q-1)\log q - 2\log 2 + o_q(1)$$ for proper $q$-colorings. Leveraging the standard algorithmic implications of zero-freeness, we obtain deterministic polynomial-time algorithms that multiplicatively approximate the corresponding partition functions at fixed rational parameters throughout this regime, with high probability over the graph. Our algorithmic guarantees significantly improve upon prior work and extend beyond the parameter ranges reached by previously known search algorithms. As a key intermediate step, we establish the pointwise equivalence, away from the threshold, of three notions of replica symmetry: geometric (averaged pairwise correlation decay), thermodynamic (convergence to the Bethe free-energy prediction), and variational (nonpositivity of the Bethe functional). To establish zero-freeness, we develop reinforced small subgraph conditioning, lifting classical small subgraph conditioning to random holomorphic functions to control short-cycle fluctuations. We also use variational replica symmetry to obtain exponential planted overlap concentration. This enables a typical-graph truncation that controls complex second moments up to the replica symmetry breaking threshold.

cs.DS · math-ph · math.PR

版本更新 · v2arXiv:2611.01047

How Close to the Theme? Similarity-Label Conditioning for Game Music Generation

Shangxuan Luo, Zixun Guo, Jinjie Shi, Joshua Reiss

原文摘要

Composers develop music from an original idea, controlling how similar each new section is to it, from near repetition to new material. Game music needs this often, as its material repeats over long play. Music models, however, rarely learn to control similarity from real pieces. We further train a pretrained MIDI model on section pairs from Super Mario pieces. A label states each pair's similarity, and a context vector summarises the given section, or context. For 157 test contexts, the model generates six outputs per label. Twelve measures score the outputs; one main measure each covers melody, pitch content, rhythm and note length. On average, outputs requested as similar are more similar to their context than those requested as dissimilar, and not to other pieces. All twelve measures favour them; each main measure stays significant after correction for multiple tests. On melody, the gap comes mainly from more frequent restatement of the context's melody. Against an otherwise identical model without a label, only the request for high similarity makes outputs more similar. In a listening test, ratings followed melodic overlap with the context most closely of all measures.

cs.SD · cs.LG · eess.AS

版本更新 · v4arXiv:2405.17506

Subspace Node Pruning

Joshua Offergeld, John Chidiac, Marcel van Gerven, Nasir Ahmad

原文摘要

Node pruning is the art of removing computational units such as neurons, filters, attention heads, or even entire layers to significantly reduce inference time while retaining network performance. In this work, we show that a broad family of importance measures, from activation-based to Fisher-based, share a common quadratic form. Through a lower-triangular change of basis, this form yields a pruning subspace in which entire nodes can be removed while the impact of the lost units is simultaneously recovered via linear least squares. Furthermore, the importance measures within our subspace are decoupled and additive through an orthogonalization of the layer activations, allowing multi-node pruning within layers without interference between importance scores. Our method, Subspace Node Pruning (SNP), outperforms the compared baselines on VGG-16 and ResNet-50 on ImageNet. On OPT-125M and LLaMA-2 7B, SNP matches the state-of-the-art LLM Surgeon at a 40-shot schedule and outperforms it whenever fewer shots are used, all without any retraining after pruning.

cs.LG · cs.CV · cs.NE

版本更新 · v2arXiv:2608.25213

Pseudorandom Functions in $\mathsf{NC}^1$ from LWE/LPN/CDH (Or: How to Build Low-Depth PRFs, Generically)

Youlong Ding, Aayush Jain, Ilan Komargodski

原文摘要

We obtain new $\mathsf{NC}^1$-computable pseudorandom functions (PRFs) from various standard assumptions, resolving several long-standing open problems. Concretely, for the first time, we obtain $\mathsf{NC}^1$-computable PRFs: (1) from the \textbf{Learning With Errors (LWE)} assumption with a polynomial modulus-to-noise ratio, improving upon prior low-depth constructions that required Ring-LWE with super-polynomial ratios [Banerjee-Peikert-Rosen, EUROCRYPT 2012]; (2) from the \textbf{Learning Parity with Noise (LPN)} assumption, removing the need for structured LPN variants [Boyle et al., FOCS 2020], [Ding-Jain-Komargodski, STOC 2025], [Ding-Jain-Komargodski, TCC 2026]; (3) from the \textbf{Computational Diffie-Hellman (CDH)} assumption; prior works relied on the stronger Decisional Diffie-Hellman (DDH) or generalized Diffie-Hellman (GDH) assumptions [Naor-Reingold, FOCS '97, J. ACM '04]. Technically, our results follow from a new generic transformation that converts weak PRFs computable in depth $d(n) = Ω(\log n)$ to (strong) PRFs computable in depth $O(d(n))$. Roughly speaking, our approach combines \emph{tapering} the internal state of the classical GGM tree (so that the per-leveldepth decreases geometrically) with a two-stage security proof that transitions from a computational to an information-theoretic argument.

cs.CC

版本更新 · v2arXiv:2607.17555

Volatility-Aware Extreme Event Detection in High-Frequency Financial Markets

Maorufa Zaman, Haris Md Sahed

原文摘要

Predicting extreme price movements in high-frequency financial markets is a challenging task due to non-stationarity, heavy-tailed return distributions, and severe class imbalance. In particular, rare but impactful events are often difficult to detect using conventional modeling approaches, which typically treat extreme movements as isolated observations. This study proposes a volatility-aware approach for extreme event detection using high-frequency Bitcoin limit order book (LOB) data. Motivated by empirical evidence of volatility clustering, the target formulation is extended to incorporate both large future returns and high-volatility regimes. This redefinition increases the proportion of informative samples and aligns the learning objective with the underlying market dynamics. Using a tree-based model (XGBoost) with time-series cross-validation and imbalance-aware evaluation, the proposed method achieves a Precision-Recall AUC of approximately 0.40, significantly outperforming the baseline formulation with a PR-AUC of around 0.06. This represents more than a sixfold improvement in detecting rare events. The results highlight that target design plays a critical role in financial machine learning, often exceeding the impact of model complexity. By incorporating volatility structure into the labeling process, the proposed approach provides a more effective and realistic framework for extreme event detection in high-frequency cryptocurrency markets.

cs.LG

版本更新 · v2arXiv:2609.34091

From Perturbation Sensitivity to Sparse Autoencoder Feature Interpretation: An EEG Foundation-Model Case Study

Yucong Cao, Chenqi Li, Tingting Zhu

原文摘要

Sparse autoencoders (SAEs) split a model's internal activity into many sparse units, or latents, and a latent is often named after a concept when removing that concept from the input changes its activity. We identify a consequential confound in this inference: if removing the concept changes the input more than the comparison edit does, a larger response may reflect a larger edit rather than the concept. Brain-signal (electroencephalography, EEG) models provide a controlled test, because how much an edit changes the EEG input can be measured directly. We measure the SAE response as the change in how often each latent is active, averaged over all latents. Across 27 combinations of model, dataset, and layer, removing the 8--12 Hz alpha band changes this response 7.33 times as much as removing an equally wide 30--34 Hz control band, but it also changes the signal far more. Matching the two edits per trial on squared time-domain distortion lowers the mean ratio to 1.42, with 19 of 27 combinations above one. Matching thus substantially reduces, but does not eliminate, the alpha--control contrast. The residual supports relative sensitivity under this single control, not general spectral specificity or an individual alpha-representing latent. We use an evidence-to-claim map to separate what this comparison supports from stronger claims of specificity and feature semantics.

cs.LG

版本更新 · v2arXiv:2604.26707

CurEvo: Curriculum-Guided Self-Evolution for Video Understanding

Guiyi Zeng, Junqing Yu, Yi-Ping Phoebe Chen, Chen Xu, Wei Yang, Zikai Song

原文摘要

Recent self-evolution frameworks for video understanding have demonstrated the potential for autonomous improvement from unlabeled videos. However, existing approaches often suffer from weakly controlled optimization and capability progression because they lack structured guidance for generating, evaluating, and reusing supervision throughout the iterative learning process. We present CurEvo, a curriculum-guided self-evolution framework that organizes this loop as a competence-aware progression. Curriculum-Guided Self-Evolution maintains a competence-aware curriculum state and cumulative training pool across iterations. Within this loop, Multi-Dimensional Question Generation supplies complementary supervision, from directly verifiable structural questions for perception to type-conditioned questions for recognition and understanding. Type-Adaptive Evaluation separately assesses question quality and answer reliability with criteria matched to each type's evidence; its scores determine which pairs enter the pool and how the next curriculum state is updated. Across seven backbones and four VideoQA benchmarks, CurEvo consistently improves benchmark accuracy and benchmark semantic score. For Qwen2.5-VL(7B), accuracy rises from 67.84% to 69.91% on ActivityNet-QA and from 76.94% to 79.61% on NExT-QA. CurEvo thus establishes self-generated supervision as a stable route to autonomous video understanding without task-specific human QA annotations during self-evolution.

cs.CV · cs.LG

版本更新 · v4arXiv:2608.21290

VT-MUSE: Multimodal Unified Sequential Visuotactile Representation Learning for Manipulation

Congsheng Xu, Qiaochu Yang, Fangyuan Shi, Yifan Han, Baijun Chen, Yiming Wang, Haonan Zhao, Zhe Liu 等 12 位作者

原文摘要

We propose VT-MUSE, a Multimodal Unified SEquential representation learning framework for visuotactilemanipulation. Existing approaches often encode visual and tactile observations independently before fusion, limiting their ability to capture fine-grained cross-modal dependencies. Moreover, most methods focus on observations at the current time step and overlook the temporal evolution of contact. VT-MUSE addresses both limitations through a two-stage representation learning framework. In Stage I, modality specific encoders are jointly adapted via cross-modal temporal alignment and masked-view consistency. In Stage II, a conditional variational latent model processes masked visual sequences together with full tactile histories. Auxiliary decoders reconstruct the masked recent visual observations and predict tactile depth changes, encouraging the latent representation to retain both global visual context and local contact dynamics. The learned representation is subsequently integrated into a lightweight Transformer policy through gated cross-attention. On the simulation benchmark, VT-MUSE outperforms the strongest baseline evaluated on all tasks by 11 percentage points and also achieves substantial improvements in real-world experiments.

cs.RO · cs.CV