跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 19:54 — 2026-11-16 19:54(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 02:59

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

23,827 已收录论文19,941 AI 相关6,921 有修订112 HF 社区发现

浏览论文库

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

找到 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2610.40620

Tessera:数据库引擎中面向倾斜稀疏关系的快速连接聚合

Tessera: Fast Join-Aggregates over Skewed Sparse Relations in Database Engines

Gyuyeong Kim

AI 速读 基于摘要

Tessera 是一个倾斜感知的连接聚合算子,直接在数据库引擎的行上计算稀疏矩阵乘积,只输出非零结果单元,并在乘法前剪枝不满足阈值的值。

cs.DB

查看原文摘要

Join-aggregate queries count or sum matching rows for each pair of values, often over skewed sparse relations in which a few values are frequent and most pairs of values never co-occur. Conventional execution plans materialize billions of intermediate join rows, taking minutes to tens of minutes per query. Recent matrix-based solutions reformulate these queries as matrix multiplication to reduce or avoid this materialization. However, they remain slow because they either store result cells for non-matching pairs or still materialize intermediate join rows for infrequent values. We present Tessera, a skew-aware join-aggregate operator for database engines that avoids both sources of overhead. Specifically, Tessera computes a sparse matrix product directly over the engine's rows, emits only nonzero cells as result rows, and prunes values that cannot meet the query's threshold before multiplication begins. It also offloads the dense block formed by pairs of the most frequent values to a CPU matrix accelerator when that block is dense enough. Experimental results show that Tessera is faster than the fastest existing system by 2.8x to 18.8x. In addition, Tessera outperforms DuckDB's execution plans by up to 1,802x.

新论文 · v1arXiv:2610.40619

来自时间线的证词:基于证据的时间临床假设显著性检验

Testimony from Timelines: Evidence-Grounded Significance Testing of Temporal Clinical Hypotheses

Chengyang He, Wenlong Zhang, Koduvayur Subbalakshmi, Ping Wang

AI 速读 基于摘要

提出STRATA基准和ART范式,对临床时间假设的显著性检验过程进行逐步评分,揭示模型主要失败于证据选择而非结论。

cs.CL · cs.IR

查看原文摘要

Ask a language model whether sales tend to dip after a product recall, or whether one side effect tends to follow another after a vaccine, and it answers in a fluent sentence that reads like a finding, with no test behind it. Assertions about how events unfold across many cases fill the Web, and each is a temporal hypothesis that only a significance test over the right records can settle. The verifier must specify the null, select the test and decide which records bear on the hypothesis, and any of these choices can go wrong while the conclusion still comes out right. Yet benchmarks for language-model data analysis grade only the conclusion, with the relevant data handed over. We study the problem in health, where a wrong verdict is costly, and present STRATA, a benchmark that grades every decision on the way to a verdict: 8,735 hypotheses over the clinical timelines of vaccine adverse-event reports, with gold plans, evidence sets, p-values and verdicts derived under a released codebook and reproduced by a deterministic oracle. We also propose ART (articulate, retrieve, test), a staged paradigm that exposes each decision as an inspectable output. Extensive experiments with five model configurations show that systems fail mostly at choosing which records count, a verdict-evidence gap that accuracy alone conceals. ART closes most of this gap and brings a 31B open model to within 0.01 of the frontier models under the same paradigm; the frontier models succeed once given the codebook.

新论文 · v1arXiv:2610.40618

面向离散扩散模型的基于ODE的采样器

An ODE-based Sampler for Discrete Diffusion Models

Samson Gourevitch, Yazid Janati, Eric Moulines, Eric P. Xing, Alain Durmus, Giacomo Zanella

AI 速读 基于摘要

作者提出指数残差流(ERFs),为离散扩散模型构造类似概率流ODE的确定性采样框架,并证明其保持原扩散的边缘分布。

cs.LG · stat.ML

查看原文摘要

The marginals of a continuous diffusion model can be reproduced by a deterministic ordinary differential equation (ODE), known as the probability flow ODE, which provides a foundation for accelerated sampling and consistency distillation. In this paper we address the question whether an analogous formulation exists for discrete diffusion models and answer it affirmatively by introducing exponential residual flows (ERFs). Our framework augments the discrete state with a continuous residual variable for each token and position. These residuals evolve deterministically according to piecewise-defined ODEs whose vector fields depend on the current discrete state and the forward and backward rate matrices of the prescribed diffusion model. The discrete state changes whenever a residual reaches zero. We prove that this construction preserves the marginals of the original diffusion. We derive a practical discretization of our sampler and specialize it to masked and uniform diffusion. The deterministic trajectories of ERFs support consistency distillation and yield empirical improvements over previous approaches across a variety of benchmarks including code and text generation tasks.

版本更新 · v2arXiv:2610.36187

坦率地说:公司选举诚信在国会沟通中保持的立场

Frankly Speaking: The Company Election Integrity Keeps in Congressional Communication

Michael A. Robinette, Christina Barsky, Amanda D. Clark, Helen Flannery, Juniper Lovato

AI 速读 基于摘要

通过分析2010至2025年国会电子通讯,发现两党使用相同的选举词汇但搭配完全不同的词语,导致选举诚信的含义分化。

cs.CL

查看原文摘要

Election integrity is a shared commitment in American politics, but Democrats and Republicans in Congress increasingly mean different things by it. Analyzing 10,420 congressional e-newsletters sent from 2010 to 2025, we examine how the two parties invoke election terms such as ``integrity,'' ``security,'' and ``fraud.'' Using diachronic word embeddings, which track semantic change through how words are used in context, we measure how differently each party uses each term, how much each party shifts, and whether they share nearest semantic neighbors. We show that members of Congress do not need different words to tell different stories about elections. They need only place those same words in different company. Across nearly every term and year, the two parties surround election-integrity vocabulary with entirely different words. That divergence is easy to miss, because most election vocabulary is no more divergent than other words used at roughly the same frequency, and neither party's usage shifted more than the other's. Only a subset of terms grew more divergent, most notably ``certification,'' while ``rigged'' and ``stolen'' entered election discourse after 2020 and polarized there. By 2024, Democrats surround ``voter,'' ``election,'' and ``integrity'' with the language of access and administration. Republicans surround the same terms with ``citizenship verification,'' ``noncitizen voting,'' and ``border security.'' For one party, integrity means protecting eligible voters' ability to cast a ballot. For the other, it means protecting the electoral process from illegitimate ballots. Election officials, who must administer a single system under both definitions, inherit this tension.

新论文 · v1arXiv:2610.40616

扩散模型成员推理中的跨时间难度校准

Difficulty Calibration Across Time for Membership Inference in Diffusion Models

Michael Joseph, Yedid Hoshen

AI 速读 基于摘要

通过沿训练时间和扩散时间两个轴校准图像难度,提升扩散模型成员推理攻击的准确性。

cs.CV · cs.CR · cs.LG

查看原文摘要

Modern diffusion models are trained on massive datasets that often include copyrighted or private images. Membership inference attacks (MIAs) address this by testing whether a given image was in a model's training set. The standard approach scores an image by its reconstruction loss and flags low-loss images as members. This often fails because some images are simply easier to reconstruct than others, so a simple unseen image can score a lower loss than a complex training image. Difficulty calibration separates memorization from how difficult an image is to begin with. We show how to calibrate along two axes of time: training time and diffusion time. First, across training time, we introduce Reference-Model Calibration (RMC), which compares a fine-tuned model's loss against an earlier checkpoint. This cleanly isolates newly memorized data and gives near-perfect auditing, even without text captions. Since earlier checkpoints are not always available, we next present Temporal Self-Calibration (TSC), which calibrates across diffusion time using only a single model. Our key observation is that an image's difficulty persists across noise levels, whereas memorization is localized in time. By comparing the loss at a target timestep against neighboring timesteps from the same model, TSC attenuates image difficulty using the model's own trajectory. Empirically, our methods beat the state of the art by a wide margin, and unlike most existing attacks, generalize across different model parameterizations such as $x$-, $v$-, and $ε$-prediction models. Code is available at https://github.com/MichaelJoseph777/TSC.

新论文 · v1arXiv:2610.40614HF 社区推荐

L3G-World:基于潜在3D高斯记忆的实时无限世界生成

L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory

Jinhyeok Choi, JoungBin Lee, Jongmin Lee, Minkyeong Jeon, Jiyoung Kim, Kaeun Han, Yoonjin Yoon, Seungryong Kim

AI 速读 基于摘要

提出潜在3D高斯记忆(L3G)与视频扩散Transformer交替自回归生成,实现实时、长时程空间一致的世界生成。

cs.CV

查看原文摘要

Interactive world models generate visual content conditioned on user actions, yet maintaining spatial consistency over long-horizon exploration in real time remains challenging. Existing approaches rely on either temporal context or explicit 3D memory, both of which scale poorly because memory grows with the length of the generated stream. Moreover, explicit 3D memories condition latent video generators by re-encoding RGB renderings, which precludes real-time generation. In this paper, we introduce a Latent 3D Gaussian Memory (L3G) that combines the efficiency of feed-forward reconstruction with a compact, rapidly renderable scene representation. Building on this memory, we propose L3G-World, in which a memory updater and a video diffusion transformer (DiT) alternate autoregressively to generate spatially consistent worlds. The memory updater spawns Gaussians in newly observed regions and refines existing ones, so that the memory grows with scene extent rather than stream length. Each Gaussian further stores a VAE latent feature, allowing the memory to be rendered directly into the DiT's latent space without VAE re-encoding. Experiments show that L3G-World achieves state-of-the-art generation quality and long-horizon spatial consistency, with up to $38.6\times$ fewer 3D primitives, $3.2\times$ faster memory updates, and $359\times$ faster memory rendering relative to the most efficient prior 3D-memory baseline for each metric, enabling real-time world generation at 9 FPS.

新论文 · v1arXiv:2610.40613

TextSeal2:基于 Copula 混合与无记忆竞争的无失真大语言模型水印

TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races

Tom Sander, Pierre Fernandez, Itai Gat, Haiming Bao, Jiaxin Shi, Jason Park, Valeriu Lacatusu, Sylvestre-Alvise Rebuffi 等 14 位作者

AI 速读 基于摘要

提出一种在推测解码下仍保持水印信号、不损失多样性且不增加可测推理延迟的无失真 LLM 水印方法。

cs.CR · cs.AI · cs.CL

查看原文摘要

We present TextSeal2, a distortion-free watermark for large language models that keeps its signal under speculative decoding: tokens that replace rejected drafts remain watermarked with the same keys, and the acceptance rate is unchanged. It also preserves output diversity and adds no measurable inference latency. Its predecessor, TextSeal, restores diversity in the Gumbel-max scheme by routing each token to one of two keys via a coin flip. This is suboptimal because the detector averages the scores from both keys without knowing which key was used. TextSeal2 instead merges two or more keys into a single virtual key and couples it to fresh noise through AutoMark's Gaussian copula. Any number of keys, including publicly shared keys, can be merged this way without diluting detection. Under speculative decoding, TextSeal2 verifies keyed drafts with one more exponential race, run on the leftovers of the draft races. By memorylessness, this race reproduces block verification, so the output follows the target model exactly. We evaluate TextSeal2 on three LLMs. At equal output token diversity, TextSeal2 detects 8 to 22 percentage points more 100-token answers than TextSeal at a false-positive rate of $10^{-3}$, and is comparable to textGrain while requiring no post-logits optimization. Under speculative decoding, it detects 18 and 22 percentage points more 200-token answers than TextSeal and textGrain, respectively, at the same acceptance rate.

新论文 · v1arXiv:2610.40611

何时协助与建议什么:紧凑解码器中的联合门控与记忆锚定提示生成

When to Assist and What to Suggest: Joint Gating and Memory-Grounded Hint Generation in One Compact Decoder

A. J. A. Jubayer Talukder, Mohammad Ariful Haque

AI 速读 基于摘要

在一个紧凑的1B解码器中联合实现主动协助的触发门控与基于记忆的提示生成,并评估其与分离式门控-生成器管线的性能权衡。

cs.CL · cs.AI · cs.HC

查看原文摘要

Proactive assistants offer short, memory-grounded hints during a conversation, deciding when to assist and what to suggest. Current systems split this between a gate and a larger generator; we evaluate both together on 28,058 decision points. Stage-wise generation scores are oracle-gate ceilings: behind a real gate, end-to-end exact match is 0.2619 against a ceiling of 0.2971, and end-to-end precision is 0.2387, leaving substantial headroom. A gate pays off through precision and compute, whose saving falls from 4.39x with an 8B generator to 1.38x with a 1B one. The memory profile drives hint quality: removing it costs 24.7 exact-match points (rescaled BERTScore 0.57 to 0.35), while retrieval and a larger generator add nothing on exact match. One 1B decoder can do both, gating from an intermediate layer and generating in the same pass. At its final checkpoint it matches or exceeds the two-model pipelines on automatic end-to-end measures with 1.31-1.76x less wall-clock time than the matched 1B pipeline; across three seeds, its deeper exit ties the separate gate. A human evaluation (1,144 ratings over 32 dialogues) supports the memory effect and rates the single model level with the matched 1B pipeline and below the 8B one. Graded metrics and LlamaPIE's native judge track human ratings more closely than exact match, which we report as a strict lower bound.

新论文 · v1arXiv:2610.40607

战斗世界模型:通过视觉交互代理实现可定制战斗

Fight World Model: Customizable Combat through Visual Interaction Proxies

Jiahua Li, Zixu John, Tom Zhong, Fuping Wu, Tianhao Xu, Ruicheng Zhang, Jun Zhou, Zunnan Xu

AI 速读 基于摘要

FWM 将规则驱动的战斗执行与视频渲染分离,用可执行引擎和确定性编译器生成交互代理,从而在无需重训渲染器的情况下支持可定制战斗规则与角色外观。

cs.CV

查看原文摘要

A playable, programmable game world must maintain persistent state, enforce executable rules, and support extensible gameplay mechanics. Existing video world models can generate plausible combat, yet struggle to keep hit reactions and health updates consistent with game rules. We introduce Fight World Model (FWM), which separates rule-governed combat execution from video rendering. An executable engine maintains state and resolves interactions. A deterministic compiler encodes these outcomes and attempted actions in a spatially and temporally aligned interaction proxy. The proxy aligns action and skill windows, brief hit reactions, and persistent health by fighter identity and timing. These cues can be controlled separately to render interactions under modified rules. Identity-bound references preserve character appearance across side switches. We train FWM on FightWorld Corpus, spanning 52 skill effects, 187 character-appearance variants, and 15 arenas. Without retraining the renderer, FWM supports damage scaling, limited-hit immunity, lifesteal, and multi-stage skill mechanisms beyond the native game. It also allows character and arena customization. Experiments demonstrate the effectiveness of FWM, which outperforms existing game world models in action fidelity, hit reactions, health-state consistency, and character appearance preservation. Our project is available at https://fight-world-model.github.io.

新论文 · v1arXiv:2610.40600

用于连续体机器人间可重定位磁耦合的传送带机构

A Conveyor Belt Mechanism for Repositionable Magnetic Coupling Between Continuum Robots

Ella Walsh, Eric Diller, Jessica Burgner-Kahrs

AI 速读 基于摘要

提出一种可集成于腱驱动连续体机器人内部的传送带机构,实现功能元件沿机器人本体的连续主动重定位,并以磁耦合案例验证其可调刚度能力。

cs.RO

查看原文摘要

This work proposes a novel conveyor belt mechanism enabling continuous, active repositioning of functional elements along the body of a tendon-driven continuum robot. Up to three conveyor belt mechanisms are integrated within a 9 mm diameter continuum robot. We demonstrate equivalent or reduced conveyor belt actuation forces compared to robot tendon actuation forces. As a case study, we mount permanent magnets along two conveyor belts, and demonstrate actively reconfigurable inter-robot coupling. Coupling point location and quantity can be adjusted during robot operation to actively tune the effective stiffness of the coupled multi-robot system. We show that effective stiffness follows a predictable inverse-cubic relationship with coupling location, and increases with the number of coupling points. These findings demonstrate that the conveyor belt mechanism enables active functional element repositioning for changing tasks requirements, with magnetic inter-robot coupling as one proof-of-concept.

新论文 · v1arXiv:2610.40598

论无序系统的零点与算法 II:至 Kesten-Stigum 阈值的反铁磁 Ising 模型

On Zeros and Algorithms for Disordered Systems II: The Antiferromagnetic Ising Model up to Kesten-Stigum

Ferenc Bencs, Brice Huang, Daniel Z. Lee, Kuikui Liu, Guus Regts

AI 速读 基于摘要

作者提出首个在均匀随机 d-正则图上、对反铁磁 Ising 模型在直至 Kesten-Stigum 阈值的全部逆温度范围内以任意高精度估计配分函数的多项式时间算法。

cs.DS · cond-mat.dis-nn · math-ph · math.PR

查看原文摘要

We give the first polynomial-time algorithm to estimate the partition function of the antiferromagnetic Ising model on the uniformly random $d$-regular graph to arbitrarily high accuracy for all inverse temperatures up to the Kesten-Stigum threshold. This is the entire regime in which the model is "replica symmetric," and is conjectured to be optimal for polynomial-time counting and sampling. To achieve our algorithmic result, we establish the absence of Fisher zeros for the partition function in a constant-width strip around the interval from $0$ up to the Kesten-Stigum threshold, with high probability over the randomness of the input graph. AI Disclosure: The overarching vision and proof architecture were developed solely by the authors without AI input. GPT 5.5 Pro was used, with extensive guidance from the authors, for only a few minor technical aspects of the proof. The authors independently verified correctness and wrote everything by hand. We take full responsibility for its contents. A more detailed statement can be found in Section 1.2.

新论文 · v1arXiv:2610.40599HF 社区推荐

HairDeck:从单张图像生成可动画的风格化发片

HairDeck: Animation-Ready Stylized Hair Cards from a Single Image

Yuze He, Yixiang Wei, Wang Zhao, Chuhao Chen, Yanning Zhou, Yong-Jin Liu

AI 速读 基于摘要

HairDeck 将风格化发型视为无序的发片集合,用集合扩散 Transformer 从单张图像一次性生成发片及其弹簧骨骼链,得到可直接导出的可动画资产。

cs.CV · cs.GR

查看原文摘要

The hair of stylized characters in games and avatars is built from hair cards: artist-placed ribbons whose geometry is the visible hair, animated by spring bones. Existing image-based methods produce realistic hair or a single fused mesh, while CHARM, the only generator of stylized hair cards, decodes a hairstyle autoregressively as a long sequence of control points. Observing that a card hairstyle is an unordered set of artist-defined primitives, we propose HairDeck, which generates it as one: each card is a single token, and a set diffusion transformer denoises all cards together. From a single image, HairDeck generates the cards and the spring-bone chains that drive them, yielding an animatable asset that exports to ready-to-use downstream formats. On CHARM's own test set, it lowers Chamfer distance by 44% and card-orientation error by more than half while running 33 times faster, and from single images it outperforms CHARM, image-to-3D pipelines and strand-based methods. Project page: https://hyzcluster.github.io/HairDeck

新论文 · v1arXiv:2610.40594

半随机损坏度量下最小生成树的近似

Approximating Minimum Spanning Trees in Metrics under Semi-Random Corruptions

Aditya Anand, Anupam Gupta, Rajesh Jayaram, Euiwoong Lee, Ali Vakilian

AI 速读 基于摘要

研究在半随机损坏的度量空间中近似最小生成树,针对距离只增、只减和任意改变三种情形给出近似算法与下界。

cs.DS

查看原文摘要

We study the problem of finding minimum spanning trees in semi-random corrupted metrics. In this problem proposed by Bateni, Dharangutte, Jayaram, and Wang (COLT'24), we start with a metric space $\mathcal{M} = (X, d)$. The adversary independently corrupts each pairwise distance with probability $p$. The algorithm only observes these possibly corrupted distances and must output a spanning tree whose expected cost (in the true metric) is multiplicatively close to the minimum spanning tree cost. Prior work showed that losing a factor of $Ω(\log n)$ is necessary, even if the algorithm may adaptively select $O(n/\log n)$ points and probe the true distances between them. However, no upper bounds were known. We study three regimes based on whether the adversary can only increase, decrease, or arbitrarily change the corrupted distances. We show the following: (1) In the increase-only setting, we give a polynomial-time $O(1)$-approximation algorithm for any constant $0 \le p < 1$. (2) In the decrease-only setting, we give an $O(\log n)$-approximation algorithm for any constant $0 \le p < 1$. Additionally, we show an $O(\log^4 n)$-approximation algorithm that runs in quasi-polynomial time $n^{O(\log n)}$, for any constant $p \leq 0.1$. Moreover, we show that a polynomial-time algorithm computing an $n^{1/3-\varepsilon}$-approximation is unlikely to exist. (3) In the general setting, where the adversary can both increase and decrease distances, we show an $O(\log n)$-approximation algorithm for every $0 \leq p < \frac{1}{4}$. Further, we show that no $o(n)$-approximation is possible for $\frac{1}{2} \leq p < 1$. Our algorithms answer the main open question in Bateni et al.'s work; moreover, the $O(\log n)$-approximations in the latter two settings are information-theoretically optimal.

新论文 · v1arXiv:2610.40591

最大基数匹配的 n^{2+o(1)} 时间算法

Maximum Cardinality Matching in $n^{2+o(1)}$ Time

George Z. Li, Jason Li, Junkai Zhang

AI 速读 基于摘要

作者提出一个在一般图上以 n^{2+o(1)} 时间求解最大基数匹配的算法,思路是扩展近期组合最大流技术到斜对称流问题。

cs.DS

查看原文摘要

We consider the maximum cardinality matching problem in general graphs, and give an $n^{2+o(1)}$-time algorithm for the problem. Our work builds on recent work on combinatorial algorithms for maximum flow and extends the techniques to skew-symmetric flow problems which capture general matchings as a special case.

新论文 · v1arXiv:2610.40589

面向固态量子自旋自主实验研究的协作式AI智能体

Collaborative AI agents for autonomous experimental research with solid-state quantum spins

El Mustapha Mansouri, Eikichi Kimura, Masato Koga, Keigo Arai

AI 速读 基于摘要

多个基于大语言模型的智能体相互评审、可中止或改道研究,并在金刚石量子自旋体系上完成从选题、理论推导到实验检验的闭环。

cs.AI · cs.MA · quant-ph

查看原文摘要

An autonomous research laboratory could conduct an entire study, from formulating questions to preparing manuscripts. Artificial intelligence (AI) offers one route towards this goal. Recent AI systems take on several research roles, but may draw conclusions that the evidence does not support. Here, we present an autonomous research laboratory in which agents based on large language models assess one another's work and can stop or redirect investigations. They can generate and reject research questions, require separate theoretical checks and conduct experiments designed to challenge their claims. We demonstrate these capabilities by investigating ensembles of quantum spins in diamond. The agents derived the minimum number of calibration settings needed to predict responses to a defined family of microwave pulse sequences. They checked the result computationally and designed experiments to distinguish competing predictions. An initial experiment agreed with the theoretical predictions, but repeated reference measurements showed that the signal was drifting during data collection. The agents therefore treated the result as inconclusive and revised the measurement protocol without relaxing the acceptance criteria. The revised experiment met those criteria and supported the theoretical predictions. This study demonstrates that collaborating AI agents can select research questions, derive theoretical results and test their predictions experimentally.

新论文 · v1arXiv:2610.40588

最后一秒的智能体预犯罪:探测被招募智能体何时屈服

Pre-Crime for Agents, at the Last Second: Probing When a Recruited Agent Gives In

Leonidas Raghav

AI 速读 基于摘要

作者报告,在受控多智能体场景中,对智能体激活做线性探针可在输出生成前预测其即将泄露秘密,但增益主要来自有标签训练而非激活本身。

cs.AI

查看原文摘要

When AI agents share channels and credentials, one agent can press another to break its operator's rule, a first step towards collusion. Output filters check only what an agent has already written. Can an overseer tell beforehand that an agent is about to give in? We show that a linear probe on the agent's activations can, in a controlled multi-agent setting. Across six scenarios, a peer presses a target for up to 20 rounds to reveal a secret, such as a deploy token; the target often refuses, then gives in. Read at each model call before its output is written, the probe picks out the one that leaks. On held-out Qwen3-32B episodes, at a threshold set to flag 5% of benign calls, it catches 82% of leaking calls. At a similar flag rate, a zero-shot decision-model monitor catches 26%. On gpt-oss-20b, a probe on its reasoning reaches AUROC 0.91. A bag-of-words classifier trained on the same calls comes close, so most of the gain comes from training on labels, not activations. The probe also flags permitted disclosures: it reads the coming disclosure more than the violation. The warning is short-range, and halting on any alarm would stop most benign episodes, which a second text check does not fix. A warning raised before generation could let an overseer stop an agent that is about to give in, ahead of others acting on its messages or recruitment spreading through a swarm.

新论文 · v1arXiv:2610.40587

超越真实标注:一种用于诊断牙科分割中校准盲区的启发式无监督质量保证引擎

Beyond Ground Truth: A Heuristic Unsupervised Quality Assurance Engine for Diagnosing Calibrational Blindness in Dental Segmentation

Fatematuj Johura Mim

AI 速读 基于摘要

提出无需真实标注的启发式质量检查引擎 HUS-QA,用于评估牙科 X 光分割掩膜质量并诊断模型的校准盲区。

cs.CV

查看原文摘要

In real-world clinical settings, dental X-ray segmentation using deep learning methods suffers from reliability issues. Even when the segmentation quality is bad, deep learning models show high confidence in their predictions (calibrational blindness). Moreover, in real use, doctors do not have ground-truth masks to check their accuracy. To address this problem, we introduce a simple quality-checking engine called HUS-QA with three stages. We train it on the PRAD (Periapical Dental X-ray) dataset to build our SimCLR self-supervised ResNet-18 U-Net model, which generates the segmentation mask and then evaluates its quality. Our HUS-QA checks the segmentation mask quality without a ground-truth mask. Prediction confidence, edge sharpness, shape connectivity, and area-size penalty are the simple indicators considered in this research. Results show that standard confidence methods fail (r = -0.1394, p = 1.7864e-3, ROC AUC = 0.4275). By contrast, our HUS-QA shows a positive correlation with actual Dice scores (r = 0.4647, p = 3.7510e-28) and achieves a strong ROC-AUC of 0.8405. Therefore, HUS-QA serves as a practical tool for clinical quality control.

新论文 · v1arXiv:2610.40586

面向5G及后5G的多基地ISAC与基于深度学习的杂波抑制

Multistatic ISAC with Deep Learning-Based Clutter Suppression for 5G and Beyond

Yalin E. Sagduyu, Tugba Erpek, Sastry Kompella

AI 速读 基于摘要

该论文提出一种多基地ISAC框架,利用残差与注意力增强的深度神经网络从杂波污染观测中直接增强目标响应,以提升目标位置与速度估计的鲁棒性。

cs.NI · cs.AI · cs.LG · eess.SP

查看原文摘要

Integrated sensing and communications (ISAC) systems using 5G and beyond signals of opportunity enable joint wireless sensing and communication using shared infrastructure and spectrum resources. While multistatic ISAC can increase sensing coverage with spatially distributed receivers, dense and dynamic clutter can significantly degrade bistatic range and Doppler estimation, leading to errors in target localization and velocity estimation. This paper presents a multistatic ISAC framework with clutter suppression for high-fidelity estimation of target position and velocity. Distributed clutter is modeled with randomly located scatterers with varying Doppler spreads and radar cross sections to capture dense and dynamic clutter effects. A broad range of conventional signal processing baselines are evaluated for clutter suppression, showing limited robustness under strong clutter conditions. To address this limitation, deep learning-based clutter suppression methods are introduced to improve robustness against dense and dynamic clutter by employing residual and attention-enhanced deep neural network architectures that directly enhance target responses from clutter-contaminated observations. These methods substantially outperform conventional approaches in target position and velocity estimation across diverse clutter conditions in multistatic ISAC.

新论文 · v1arXiv:2610.40585

量子信道上的经典通信:纠缠在自然界中有帮助吗?

Classical communication over quantum channels: does entanglement help in nature?

Peixue Wu

AI 速读 基于摘要

作者提出Schur加权块熵不等式,证明所有相位协变信道(含多能级振幅阻尼、广义退相位、阻尼-退相位信道)在经典通信中不存在纠缠优势。

quant-ph · cs.IT · math-ph

查看原文摘要

Can entangling codewords across independent uses of a quantum channel improve the rate of classical communication? An old conjecture states that there is no such entanglement advantage for all channels. Although Hastings's result and follow-up works disproved this conjecture, it turns out that enormous dimension is required to construct a channel where entanglement enhances classical communication. This indicates that there might be no entanglement advantage for many physical channels, or for all low dimensional channels. Motivated by recent progress on (generalized) amplitude damping channels, we propose a general Schur-weighted block entropy inequality, and show that there is no entanglement advantage for all phase-covariant channels including multi-level amplitude damping channels, generalized dephasing channels, and damping-dephasing channels. As a by-product, we also recover the recently established result that there is no entanglement advantage for all qubit channels.

新论文 · v1arXiv:2610.40580

RADIOlogy:一种单次前向的无训练零样本异常检测方法

RADIOlogy: A Single-Pass Approach to Training-Free Zero-Shot Anomaly Detection

Joaquín Figueira, Giacomo D'Amicantonio, Egor Bondarau

AI 速读 基于摘要

作者提出 RADIOlogy,利用视觉-语言模型中多头注意力池化的零样本异常定位特性,以单次前向的对比打分实现无需训练的零样本异常检测与分割。

cs.CV

查看原文摘要

Current zero-shot anomaly detection methods often rely on complex prompt-learning techniques or computationally expensive sliding-window strategies to achieve fine-grained visual alignment to detect small-scale anomalies. This reliance stems from the fundamental limitation of standard CLIP architectures, where [CLS] token attention and spatial patch pooling struggle to capture subtle, localized anomaly features. While prompt-learning approaches aim to bridge this gap, they typically require a large number of ground-truth segmentation masks from auxiliary datasets, which are often unavailable in specialized domains. In this work, we show an emerging property of multi-head attention pooling in vision-language models: remarkable zero-shot anomaly localization and detection right out of the box. We translate this property into a single-pass anomaly detection technique, RADIOlogy, that does not require dense, windowed execution and significantly outperforms other training-free baselines. Instead, the method relies on a simple contrastive scoring approach that compares the average similarity between vision features and a suite of normal and abnormal prompts. Furthermore, we leverage the agglomerative features of RADIO models to enhance pixel-level anomaly segmentation using a dense anomaly refinement pipeline. Finally, we show how the vision-language family of training-free zero-shot anomaly detection techniques can be applied successfully to the medical domain with minimal modifications. Code is available at https://github.com/jacomof/RADIOlogy.

新论文 · v1arXiv:2610.40579

当插补改变最近邻:不完整传感器时间序列相似性检索的精确认证

When Imputation Changes the Nearest Neighbor: Exact Certification of Similarity Retrieval for Incomplete Sensor Time Series

Jianru Shen

AI 速读 基于摘要

针对缺失值插补会改变最近邻的问题,提出对窗口最小值距离族在任意允许补全下保持检索结论的精确认证方法。

cs.DB · cs.DS

查看原文摘要

Sensor time series routinely reach similarity search with missing values, and the retrieved neighbours then depend on how the gaps were filled. We ask which retrieval conclusions hold for every admissible completion of an incomplete query. For a family of window-minimum distances that contains the $L_1$ distance as its separable end we give a pairwise certificate that one candidate is strictly closer than another, a guaranteed candidate set that contains every possible nearest neighbour, and a certificate that a nearest-neighbour label cannot change. The guarantees hold uniformly over the specified box and apply to the true query whenever it lies inside. At the separable end a closed form is known, but beyond it the worst-case gap need not be attained at a corner of the box. We prove a finite reduction to critical values, give an exact interval dynamic programme for the worst-case ranking gap, and a quadratic-time fast layer of valid bounds and feasible witnesses, supported by an exact criterion for when the feature-box relaxation is tight. On three traffic-sensor collections with real gap patterns, linear interpolation changes the nearest neighbour in 15 to 33 percent of the queries. At the full band the feature-box relaxation misses up to 14 percent of the exactly stable boundary pairs, whereas fixed-completion and Monte Carlo checks issue false certificates. The fast layer resolves about 90 percent of all tested boundary pairs without dynamic programming, and on paired network-scale queries the exact method is 82 to 110 times faster than the programme alone. Label certificates transfer to three public benchmarks, and the band width trades forecasting accuracy and certification coverage for lower imputation sensitivity, with dataset-dependent crossovers.

新论文 · v1arXiv:2610.40578

VeriCUA:将验证作为智能体探索的计算机使用智能体

VeriCUA: Verification as Agentic Exploration for Computer-Using Agents

Qiushi Sun, Da Yu, Alexander Knop, Amer Sinha, Lingpeng Kong, Ben Kao, Ravi Kumar, Pritish Kamath

AI 速读 基于摘要

提出平台无关的验证框架 VeriCUA,把任务完成验证建模为智能体在共享流程中动态收集证据并评估,统一在线与离线、跨平台与多模态观测场景。

cs.AI · cs.CL · cs.CV

查看原文摘要

Building and scaling computer-using agents (CUAs) across desktop, mobile, and web environments requires reliable task-completion verification for data curation, evaluation, and reinforcement learning. Typical automated approaches prompt vision-language models (VLMs) to judge trajectories or generate programs to inspect application state. However, both rely on partial views of complex digital environments. VLM judges are restricted to supplied observations, while generated programs depend on accessible state. These views can omit decisive evidence or leave completion judgments unsupported. Tailoring separate verifiers to different platforms and access settings adds further engineering cost. We present VeriCUA, a platform-agnostic framework for verification through agentic exploration. It treats verification as dynamic evidence gathering and assessment within a shared procedure for online and offline settings across platforms and observation modalities. After inspecting the available context to construct a task rubric, the verifier selects GUI or code checks for unresolved requirements and combines their findings under explicit evidence rules. Experiments show improved agreement with reference labels over the compared baselines across these settings, with the largest offline gains on hard cases and stronger rejection of false completion claims online. Further analyses connect these gains to complementary evidence and test-time exploration.

新论文 · v1arXiv:2610.40576

PIVOT:通过在线教师纠正的渐进式干预

PIVOT: Progressive Intervention via Online Teacher Correction

Zhihao Yang, Boyuan Zheng, Puhui Tan, Yukun Chen, Kuan Zhang, Longze Chen, Jiaming Li, Renke Shan 等 10 位作者

AI 速读 基于摘要

PIVOT 将教师生成的纠正片段插入学生 rollout,并对这些片段施加 token 级 KL 监督,与 RLVR 目标联合训练,以缓解困难推理任务中稀疏奖励无学习信号的问题。

cs.CL

查看原文摘要

Reinforcement learning from verifiable rewards (RLVR) is limited by sparse outcome-level feedback on hard reasoning tasks: when all rollouts in a group fail, rewards provide no learning signal. Stronger teachers can provide additional guidance, but this raises a central question: how can such signals be incorporated into RLVR to support successful rollouts while remaining learnable for the student? We distinguish two complementary mechanisms: trajectory-level intervention, which improves access to reward-bearing trajectories, and token-level supervision, which provides dense targets to guide student learning. Our controlled experiments show that either mechanism alone can remain insufficient, motivating their combination. We therefore introduce PIVOT, which inserts teacher-generated corrections into student rollouts and applies token-level KL supervision to these segments alongside the RLVR objective. Beyond their combination, we systematically analyze where to intervene and how to supervise, yielding a recipe for effective guidance. Across hard logic games and mathematical reasoning benchmarks, PIVOT consistently outperforms existing methods, nearly doubling mean avg@8 on logic games from 19.5% for the best-performing baseline to 35.6%.

版本更新 · v3arXiv:2602.06849

离散扩散模型的改进采样调度

Improved Sampling Schedules for Discrete Diffusion Models

Alberto Foresti, Mustapha Bounoua, Giulio Franzese, Luca Ambrogioni, Pietro Michiardi

AI 速读 基于摘要

作者从热力学熵产生与动力学活动角度分析均匀离散扩散模型的反向过程,并提出两种新的采样调度(EDS、WDS),在语言建模任务上报告了计算效率提升。

cs.LG

查看原文摘要

Uniform Discrete Diffusion Models have emerged as a powerful paradigm for generative modeling on sequence data; however, the information-theoretic principles governing their reverse processes remain underexplored. In this work, we bridge this gap by analyzing the reverse process dynamics through the lens of thermodynamic entropy production and dynamical activity. We use a variational expression of the discrete Wasserstein distance to characterize the dynamics of the generation process. Leveraging these insights, we first introduce the Entropic Discrete Schedule (EDS), which aligns with entropy production, and later construct the Wasserstein Discrete Schedule (WDS), which combines entropy production and dynamical activity to act as a geometric cost. Our experimental results on language modeling show that WDS provide the same results as uniform while using up to half of the computations on the MBPP benchmark. The code is available at https://github.com/AlbertoForesti/impscheds.

新论文 · v1arXiv:2610.40575

平面图上的最小标签 k-割:复杂性与颜色结构

Minimum Label $k$-Cut on Planar Graphs: Complexity and Color Structure

Yuanhao Wang, Wei Wang

AI 速读 基于摘要

研究底层图结构与颜色类结构如何影响最小标签 k-割问题的参数化复杂性与可解性边界。

cs.DS

查看原文摘要

Minimum Label $k$-Cut asks for a minimum-size set of colors such that deleting all edges of these colors leaves at least $k$ connected components. We study how the structure of the underlying graph and its color classes affects the complexity of this problem. Regarding fixed-parameter tractability with respect to $k$ on simple planar graphs, we prove that the problem is W[1]-hard, even when the underlying graph is a cactus graph and each color appears at most twice. Furthermore, for cactus graphs in which every color class is connected, we establish a complexity boundary in terms of the maximum monochromatic degree: when this degree is at most two, an optimal solution can be found in $O(Nk^2)$ time, where $N$ is the input size, with no restriction on color frequency or the number of blocks spanned by a color; allowing the maximum monochromatic degree to increase to three already makes the decision version NP-complete. Finally, we prove that the problem remains W[1]-hard parameterized by $k$ on fan graphs, even when every color class is an induced path. These results show that bounding color frequency does not suffice to eliminate parameterized hardness. They also establish a monochromatic-degree boundary for connected colors on cactus graphs and identify complexity barriers to extending this tractable case to outerplanar graphs.

新论文 · v1arXiv:2610.40574

每个 Token 都需要自己的老师:多教师自适应在线策略自蒸馏

Every Token Needs Its Own Teacher: Multi-teacher Adaptive On-policy Self-distillation

Yifu Luo, Chuang Ma, Zeyu Chen, Enkelejda Kasneci, Qi Chen, Gjergji Kasneci

AI 速读 基于摘要

提出首个 token 级自适应在线策略自蒸馏方法 MTA-OPSD,让每个 token 在训练中从多教师池中选择偏好的教师。

cs.CL

查看原文摘要

On-policy Self-distillation (OPSD) has proven effective for post-training large language models by constructing a teacher conditioned on privileged references. However, existing approaches keep the teacher fixed either throughout training by consistently exposing it to the full reference, or within each response by adaptively varying partial reference exposure only across responses. In this paper, we argue that neither of them is sufficient. Instead, every token needs its own teacher, as the teacher preference can vary token by token within the same response. Through a teacher-intervention pilot study, we validate that the teacher preference differs across tokens, and reveal that a preferred teacher can be identified for each token through majority voting and KL-based selection. Motivated by these findings, we propose Multi-teacher Adaptive On-policy Self-Distillation (MTA-OPSD), the first token-level adaptive OPSD method. Our method constructs a multi-teacher pool consisting of candidate teachers, and enables every token to adaptively select its preferred teacher during training. Experiments with Qwen3 models on mathematical reasoning tasks show that MTA-OPSD consistently outperforms existing OPSD approaches with an average gain of up to $+5.9$ over the base model, highlighting the importance of adapting teacher supervision at the token level. The code is available at https://github.com/xingzhejun/MTA-OPSD.

新论文 · v1arXiv:2610.40573

不定因果结构能计算什么?

What Can Be Computed with Indefinite Causal Structure?

Omri Shmueli

AI 速读 基于摘要

在过程矩阵形式下研究不定因果序的计算能力,作者报告在两种设定下给出多项式时间算法,分别覆盖 NP 与唯一汇点定向问题。

quant-ph · cs.CC

查看原文摘要

Can quantum computation become more powerful when operations do not need to follow a definite causal order? We study this question in the process matrix formalism of Oreshkov et al. (Nature Communications, 2012), which allows quantum operations to be connected without a fixed global order. In the computational model, a quantum circuit succinctly describes a process matrix, and the algorithm is given access to its generated channel, with computational cost measured by the size of the generating circuit. We give polynomial-time algorithms in two settings. First, general process matrix computation suffices to solve every problem in $\textbf{NP}$. The valid processes used by our algorithm satisfy the purification postulate of Araújo et al. (Quantum, 2017), and their generated channels are unitary, although their generating circuits are not. Second, requiring the process matrices themselves to be pure, we give a polynomial-time algorithm for unique-sink orientation, a general problem capturing several longstanding computational problems in optimization. Our unitary generators are constructed explicitly and efficiently. Assuming that unique-sink orientation has no quantum polynomial-time algorithm, our result shows that indefinite causal order can provide computational power beyond $\textbf{BQP}$ within the process matrix formalism, even while preserving unitarity.

版本更新 · v2arXiv:2610.23009

深度提升:神经网络即使使用最笨的优化器也能泛化

"Deep lifts": Neural networks can generalize even with the dumbest optimizer

Sunil Madhow, Yu-Xiang Wang

AI 速读 基于摘要

作者研究在插值数据的参数中均匀随机选取的过参数化 ReLU 网络参数,证明其泛化速率由解释数据的更小网络的规模决定,而非由完整假设类的 VC 维决定。

cs.LG

查看原文摘要

Given a labeled dataset $\{(x_i, y_i)\}_{i = 1}^n$, consider drawing a parameter vector $\hatθ$ uniformly at random from those that interpolate the data within a width-$W$ depth-$D$ ReLU architecture with continuous weights bounded within $[-M, M]$. We study the generalization properties of $\hatθ$ in the case where the dataset can, in fact, be explained by a smaller $w$-by-$d$ ReLU network. Despite the obliviousness of the selection rule for $\hatθ$, it adaptively generalizes at the rate $\tilde O\left(\frac{wdWD}{n}\right)$, rather than being governed by the VC dimension of the full $W$-by-$D$ hypothesis class. The reason is due to a particular inductive bias in ReLU networks: the $w$-by-$d$ parameter *witnesses* an exponential volume of $W$-by-$D$ interpolating parameters, which dwarfs the volume of poorly generalizing parameters (conditioned on interpolation). We explicitly construct this set of near-equivalent $W$-by-$D$ parameters by a proof technique called *deep lifting*, and then tie the achievable volume to stability properties of the $w$-by-$d$ witness. Examples show that these techniques allow us to convert approximation-theoretic results into generalization guarantees for nonparametric classes. We further show that generalization of uniform-random interpolators can survive label corruptions.

新论文 · v1arXiv:2610.40569

在线Steiner森林问题中贪心算法的紧竞争比

The Tight Competitive Ratio of Greedy for Online Steiner Forest

Iman Gholami, Ilya Hajiaghayi, MohammadTaghi Hajiaghayi, Peyman Jabbarzade

AI 速读 基于摘要

该论文证明在线Steiner森林问题中自然贪心算法的竞争比紧确为Θ(log k log log k),从而否定了Awerbuch-Azar-Bartal的O(log k)猜想。

cs.DS

查看原文摘要

The online Steiner Forest problem is a fundamental network design problem in which terminal pairs arrive one at a time and an algorithm must irrevocably purchase edges connecting each pair. The natural greedy algorithm connects each terminal pair by a shortest path after making all previously purchased edges free. Awerbuch, Azar, and Bartal (SODA 1996) proved that this algorithm is $O(log^2 k)$-competitive and conjectured an $O(log k)$ bound, where $k$ is the number of terminal pairs. Bamas, Drygala, and Maggiori (SODA 2022) obtained an $O(\log \NumPairs\log\log \NumPairs)$ bound for greedy on a restricted class of inputs, leaving the general case open. In this paper, we resolve the competitive ratio of the greedy algorithm for online Steiner Forest, proving that it is tightly $Θ(log(k) log log(k))$. Specifically, we establish an $O(log(k) log log(k))$ upper bound for arbitrary instances and construct a matching $Ω(log(k) log log(k))$ lower bound. Our results refute the $O(log k)$ conjecture of Awerbuch, Azar, and Bartal and establish a tight $Θ(log log k)$ separation between the greedy algorithm and the best possible online algorithm for Steiner Forest.

新论文 · v1arXiv:2610.40566

全维高斯混合模型 NPMLE 的自正则化与结构自适应

Self-regularization and structural adaptation of NPMLE for Gaussian mixture models in all dimensions

Yanjun Han, Yandi Shen, Yihong Wu

AI 速读 基于摘要

作者证明:均值位于超立方体内的 d 维高斯混合模型,其 NPMLE 能以高概率自动拟合出 O((log n/log log n)^d) 个分量,并在有限混合数据下使拟合分量数依概率有界。

math.ST · stat.ML

查看原文摘要

We establish structural properties of the nonparametric maximum likelihood estimator (NPMLE) for $d$-dimensional Gaussian mixtures whose means lie in a hypercube. We show that, with high probability, the NPMLE based on $n$ independent observations self-regularizes by fitting a mixture model with $O((\frac{\log n}{\log\log n})^d)$ components, achieving the optimal model complexity without explicit model selection. Furthermore, the NPMLE exhibits a structural adaptation property: For data drawn from a finite mixture, the number of fitted components is bounded in probability as $n\to\infty$. Our proof applies a multivariate Jensen-type bound to control the typical number of critical points of the KKT function associated with the first-order optimality conditions. The key step is to lower bound its gradient norm uniformly on complex spheres. We establish this lower bound by decomposing the KKT function into an empirical fluctuation term and a relative density estimation error term, combining small-ball probability estimates for the former with polynomial approximation and Hellinger error bounds for the latter.