跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 00:58 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 01:15 — 2026-11-09 01:15（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：2026-11-09 00:58最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 00:56（北京时间）
版本更新 · v2arXiv:2610.32794

Consommé: Conditioned Token Merging for Split Inference

Man Ngo, Jan S. Rellermeyer

原文摘要

Split inference partitions a Vision Transformer between a resource-constrained edge device and a server. However, transmitting intermediate tokens across the communication channel is costly. Deploying fine-tuned backbones to every endpoint becomes expensive as well. We study token reduction for split inference under a frozen backbone, where only a small adapter is shipped. We observe that the CLS token plays a dual role: it acts as the global summary the receiver needs for classification, and it serves as a signal on which patches to keep. We propose Consommé, a method utilizing both characteristics. There, an information bottleneck compresses the CLS token into a compact latent which is transmitted in place of the full CLS token and conditions a learned patch gate merging patches into exactly $k$ tokens via soft assignment. It reaches any budget in a single step, thus escaping the per-layer cap of bipartite matching (BPM). On DeiT-S/T, it leads all methods at aggressive token budgets and remains operable at shallow splits where BPM cannot operate, while matching fine-tuned methods at gentle budgets at a fraction of their deployment cost.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39754

Toward Complete Speaker Anonymization: a Streaming Cascaded System for Voice Privacy and PII Removal

Stanisław Kacprzak, Thomas Thebaud, Najim Dehak

原文摘要

We present a cascade streaming voice privacy system, consisting of ASR, NLP, and TTS modules. By leveraging recent improvements in all three aspects of speech and language processing, we show that such a system is capable of achieving a result comparable to state-of-the-art offline voice privacy systems, while providing controllable capabilities of content protection beyond voice. With an estimated utterance-onset end-to-end latency of 717 ms, the presented system preserves speech content with 11% WER on Librispeech, while detecting PII with a 69% SLU F1 score and achieving up to 47.66% EER against a semi-informed attacker.

cs.SD · eess.AS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39753

Four-Coloring Planar Graphs in Linear Time

Yuta Inoue, Ken-ichi Kawarabayashi, Atsuyuki Miyashita, Bojan Mohar, Carsten Thomassen, Mikkel Thorup

原文摘要

The famous Four Color Theorem (4CT) states that any planar graph can be colored with four colors, but how do we find a 4-coloring? In our previous paper [FOCS'26], we presented a simple combinatorial algorithm to 4-color planar graphs in $O(n\log n)$ time. We improve it here to $O(n)$ time, which is optimal. The algorithm from our previous paper is based on proving that every planar triangulation has a linear number of reducible configurations or obstructing cycles. The bottleneck for the algorithm is that we need $O(\log n)$ Kempe changes to extend a recursive 4-coloring to the reducible configurations. Each Kempe change can involve a constant fraction of the graph and takes linear time. Here we show that all $O(\log n)$ Kempe changes can be identified and implemented in $O(n)$ time. The idea is to spend $O(n)$ time to preprocess the graph so that we can identify and simulate each good Kempe change in $O(n/\log n)$ amortized time. Thus, we implement all $O(\log n)$ Kempe changes in $O(n)$ total time. Based on this, we implement the whole 4-coloring in linear time. We note that creating such a representation for fast identification and simulation of the right Kempe changes is a challenge of data structures, unlike the previous paper that builds on a new graph theoretic understanding of reducible configurations.

cs.DS · cs.CG · cs.DM · math.CO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39751

Parameterized Approximation of Max k-Weight CSP: A Dichotomy for Boolean Languages

Rudranarayan Kar, Souvik Saha, Abhishek Sahu

原文摘要

We study \textsc{Max $k$-Weight CSP}: maximize the satisfied weight of Boolean constraints with nonnegative rational weights by setting at most $k$ variables to $1$. Each constraint uses at most $d$ distinct variables and a relation from a finite Boolean language $Γ$. This includes \textsc{Partial Vertex Cover}, \textsc{Densest $k$-Subgraph}, bounded-frequency \textsc{Maximum Coverage}, and cardinality-constrained \textsc{Max-SAT}. We completely classify the fixed finite languages admitting an efficient parameterized approximation scheme (EPAS) with parameter $k+d$. Only nonempty relations excluding the all-zero tuple matter. For such a relation, a coordinate is a \emph{unit witness} if the tuple with a single $1$ in that coordinate is accepted, and a \emph{control} otherwise. A relation is \emph{Direct} if setting any selected control to $0$, with all other coordinates unchanged, preserves satisfaction. It is \emph{Rooted} if every satisfying tuple has a selected unit witness such that keeping it, setting all other unit witnesses to $0$, and setting any subset of selected controls to $0$ preserves satisfaction. If all such relations are Direct, or all are Rooted, we give a deterministic $(1-\varepsilon)$-approximation for every rational $\varepsilon\in(0,1)$ in time $2^{O(d+k\log(1+dk/\varepsilon))}\ell_{\mathrm{in}}^{O(1)}$, where $\ell_{\mathrm{in}}$ is the total input length. The algorithms are uniform in $d$ and give an EPAS parameterized by $k+d$ whenever relation membership is polynomial-time decidable. If neither condition holds, no EPAS exists unless $\mathsf{FPT}=\mathsf{W[1]}$, even for unweighted instances where no two constraints involve the same set of variables.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.24005

PACE: Pareto-Adaptive Compression for Efficient Native MLLMs

Lei Tian, Chunzheng Zhu, Kai Wu, Yifan Zhang, Haihua Yang

原文摘要

Native multimodal large language models (native MLLMs) jointly encode visual and linguistic sequences within a unified autoregressive Transformer, emerging as a promising paradigm for multimodal understanding. Unlike conventional ViT-based MLLMs relying on external vision encoders, ViT-free native MLLMs tokenize pixel patches directly, potentially suffering severe visual token redundancy. A pilot study confirms this: unlike ViT-based models that degrade under compression, ViT-free MLLMs tolerate aggressive compression with near-lossless or even improved performance. Yet existing compression methods target ViT-based settings, leaving native MLLMs, which stand to gain the most, unexplored. To close this gap, we introduce an analysis pipeline centered on token discriminability and cross-dimensional heterogeneous redundancy, revealing that (i) redundancy is distributed independently and heterogeneously along height and width axes, and (ii) early-layer visual tokens are indiscriminable and uniformly redundant. Guided by these findings, we propose PACE (Pareto-Adaptive Compression for Efficient Native MLLMs), the first visual token compression framework tailored for native MLLMs with Multimodal-RoPE. Leveraging dimensional decoupling of positional encoding, PACE decomposes attention into two orthogonal spatial saliency estimates along height and width, gated by a positional attention signal, yielding direction-aware importance with negligible overhead. It further casts token budget allocation as Pareto optimization over performance preservation, inference efficiency, and spatial coverage, jointly identifying optimal compression depths and retention ratios. Experiments show PACE maintains near-lossless performance at only 25%-50% visual token retention, even improving several benchmarks, while delivering over 2x FLOPs reduction.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2411.04852

Conformalized Credal Regions for Classification with Ambiguous Ground Truth

Michele Caprio, David Stutz, Shuo Li, Arnaud Doucet

原文摘要

An open question in \emph{Imprecise Probabilistic Machine Learning} is how to empirically derive a credal region (i.e., a closed and convex family of probabilities on the output space) from the available data, without any prior knowledge or assumption. In classification problems, credal regions are a tool that is able to provide provable guarantees under realistic assumptions by characterizing the uncertainty about the distribution of the labels. Building on previous work, we show that credal regions can be directly constructed using conformal methods. This allows us to provide a novel extension of classical conformal prediction to problems with ambiguous ground truth, that is, when the exact labels for given inputs are not exactly known. The resulting construction enjoys desirable practical and theoretical properties: (i) conformal coverage guarantees, (ii) smaller prediction sets (compared to classical conformal prediction regions) and (iii) disentanglement of uncertainty sources (epistemic, aleatoric). We empirically verify our findings on both synthetic and real datasets.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39747

When the Top Answer Decides: Gender Bias in Decision Models

Yeb Havinga

原文摘要

Decision models are language models built to route, classify and triage: they return option probabilities from one forward pass, and an application acts on the top answer. They are offered off the shelf, trained for the decision format rather than for fairness or any one application, and we found no bias measurement in their cards. We test TypeSafe's closed Jev and five open decision models on gender-swapped yes/no decisions about people (Tamkin et al., 2023), BBQ, StereoSet and the gender-bias studies of Fulgu and Capraro (2024). Five of the six give women significantly more favourable answers than men (+0.05 to +0.10 in log-odds), and a gender swap changes 1-3.5% of top answers (Jev's partly through its call-to-call variation). The makers' recommended confidence gate removes many biased commitments but raises the stereotyped share of those it keeps in ambiguous BBQ gender questions (granite-switch 0.76 to 0.85, pplx 0.81 to 1.00). Probes show gender preferences in the same models: all six rate violence for a greater good as more acceptable against a man than against a woman, and two default to "girl" when forced to guess a child's gender without a cue. Decision-level and probability-level measures differ, so audits should read a model as its application does.

cs.CL · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39746

Step Recursion: Rational Strides and Exact Inclusion Orders over the Reals

Kirill Osipov

原文摘要

We study finite-terminating, address-only step recursion on the nonnegative reals, from zero, unit successor and projections. For reduced positive rational strides $s=a/q$ and $t=b/v$, we prove $\mathcal{C}s\subseteq\mathcal{C}t$ if and only if $q$ divides $v$, for both the bounded and unbounded algebras $\mathcal{C}\in{\mathcal{B},\mathcal{U}}$. The bounded compiler preserves earlier global majorants on every auxiliary input. Mixed rational stride sets are classified by least common denominators and supernatural denominators. Primitive-recursive translated-coordinate grid codes characterize the unbounded algebras and yield $\mathcal{U}{1/q}\cap\mathcal{U}{1/v}=\mathcal{U}{1/\gcd(q,v)}$. For bounded intersections, we prove an exact reduction: all corresponding identities hold if and only if the single identity $\mathcal{B}{1/2}\cap\mathcal{B}_{1/3}=\mathcal{B}_1$ holds, equivalently if the Boolean parts of the integer successor and addition algebras under scalar bounded recursion coincide. A Boolean reconstruction reduces general functions to predicates; a clipped fine-grid simulation with a frozen global resource bound identifies the union of predicate precision classes with the addition level. These reductions do not decide the resulting predicate equality, so literal bounded intersections remain unresolved. We also prove that unbounded-program equality is $Π^0_1$-complete and extensional bounded-algebra membership is $Σ^0_2$-complete. The model has no free real arithmetic or Zeno limits; semantic majorant validity is distinguished from syntax transformation.

cs.LO · math.LO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.27392

Handling Complex Interference Compositionally: A Concurrent Garbage Collector Case Study

Nisansala P. Yatapanage

原文摘要

Rely/Guarantee is a well-known verification technique for reasoning about concurrent programs. However, for some algorithms, devising suitable rely and guarantee conditions is challenging, due to the strong interference exhibited in these algorithms. The Ben-Ari concurrent garbage collector is an algorithm where the complex interactions between the components prevent the construction of compositional rely and guarantee conditions. This paper investigates an approach for verifying the Ben-Ari algorithm, which enables reasoning to be performed in a more compositional manner in cases where compositional reasoning would not otherwise be possible. This is accomplished by reasoning that a given property holds for all instances of a particular variable and then instantiating the variable to the local variable required. As well as providing a reasoning approach which is more compositional, the result is the identification of the core property required of a component, thus enabling a deeper understanding about the reasons why the algorithm works correctly. This helps to reveal the reasons why the rely/guarantee approach does not work directly for some problems.

cs.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39745

UniffordInteractor: Reasoning the Unified Affordance for Human and Multi-Object Interaction

Chen Su, Xingqun Qi, Xurui Hu, Bingkun Yang, Muyi Sun, Man Zhang, Zhenan Sun

原文摘要

Deriving plausible and dynamic Human Object Interaction (HOI) has gained tremendous progress in Embodied AI and Immersive AR/VR. While existing HOI methods have effectively explored human interaction with individual or fixed objects, they still show limitations in complex multi-object interaction scenes. Meanwhile, previous approaches focus more on the contact information held by human-object relation, overlooking the significance of the contact situation of various entities (i.e., object-object). To address these limitations, we propose UniffordInteractor, a Reasoning-then-Interacting framework that leverages unified affordance for realistic and long-horizon human and multi-object interaction modeling. At the reasoning stage, we devise a Unified Affordance Reasoner (UAR) that employs a fine-tuned 3D Multimodal Large Language Model for unified object-centric affordance prediction. At the interacting stage, we propose Hierarchical Interaction Generator (HIG), which formulates the interaction generation as a hierarchical (e.g., root to body to hand to objects) autoregressive prediction, conditioned on the obtained unified affordance. Extensive experiments demonstrate that UniffordInteractor surpasses SOTA counterparts in human and multi-object interaction generation.

cs.GR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39744

PAPERBENCHX: Can AI Reproduce Science Across Disciplines?

Ruoyu Wu, Zengji Tu, Aolong Sun, Tianyi Ma, Junren Li, Xinbo Xu, Li Fu, Ziyan Zhang 等 17 位作者

原文摘要

Before AI can be trusted to discover new science, it should be able to reproduce what science already knows. Reproduction provides a rigorous checkpoint for an AI scientist: the target claim is known, yet recovering it still requires translating an incomplete scientific description into an executable experiment and producing evidence that can be independently verified. Existing research-reproduction benchmarks largely focus on AI and machine learning, where experiments share relatively homogeneous software stacks. Extending this capability across scientific disciplines introduces a different challenge: agents must operate domain-specific scientific software, make physical and numerical choices, diagnose long-running computations, and distinguish valid evidence from merely plausible outputs. We introduce PAPERBENCHX, a benchmark of 93 expert-constructed paper-reproduction tasks spanning 12 research areas across electromagnetics, photonics, chemistry, materials science, biology, and robotics. Each task provides the source paper, a public task specification, and a domain-native scientific environment involving specialized scientific software. Agents must reconstruct a key experiment, execute and diagnose it, and deliver a runnable workflow that supports the target scientific claim. To evaluate scientific validity rather than surface-level agreement, we replay every submission from scratch and score only regenerated evidence against expert-validated criteria. Across 10 frontier agent configurations, the best configuration fully reproduces only 14% tasks under the 90% threshold. Meanwhile, mean rubric scores range from 27.53% to 59.08%, indicating that substantial partial progress rarely translates into complete scientific reproduction. These results reveal a large gap between paper understanding and reliably producing reproducible scientific evidence.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.04310

Latent Anchor-Driven Test Generation for Deep Neural Networks

Bin Duan, Matthew B. Dwyer, Guowei Yang

原文摘要

Deep Neural Networks (DNNs) are increasingly being deployed in security-critical and safety-sensitive applications, which makes rigorous testing essential to identify and mitigate model weaknesses. Existing DNN testing approaches explore either the input space or a learned latent space. While latent-space generation can better maintain plausibility than direct input-space mutation, current methods still face a trade-off among exploration controllability, failure diversity, and seed-relative semantic drift. To overcome these limitations, we propose Latte, a black-box testing framework that generates semantically proximate, diverse, and fault-revealing test cases by leveraging the latent space. Specifically, Latte encodes each input seed with a pre-trained VQ-VAE and performs a seed-centered, one-step latent mutation along directions defined by anchors sampled from alternative classes, followed by quantization and decoding back to the input space. This explores local neighborhoods around each seed within the learned latent manifold, resulting in a larger number and broader diversity of oracle-triggering prediction discrepancies under the same budget. We evaluated Latte on 5 datasets and 10 DNN models in single-model and multi-model testing scenarios. Across the evaluated datasets and models, Latte improves fault exposure and behavioral diversity under matched testing budgets. Under the single-model setting, it also maintains low seed-relative semantic drift with respect to the source seeds.

cs.LG · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39742

The Importance of Speech Genre for End-of-Turn Detector Training

Rini Sharon, Kadri Hacioglu, Jeena Prakash, Andreas Stolcke

原文摘要

End-of-turn (EoT) detection has been studied mostly through features, models, and modalities, while the speech genre of the training data has drawn far less attention. We isolate this factor. Using one reproducible annotation pipeline, we build a matched pair of corpora, multi-turn human-human conversational and single-turn human-machine, and train the same streaming ConvLSTM EoT detector on each. Across four test sets the conversational model reaches up to +0.45 higher F1, driven by fewer false alarms on the mid-turn pauses and hesitations that are rare in single-turn corpora. This conversational-training effect is not specific to frame-level decoding. Under a matched complete-or-not test it also appears at the utterance level, across two encoders, but only on conversational test data. Testing only on single-turn speech, as most prior work does, therefore hides the benefit of conversational training data. Against open-source baselines, our 1.8M-parameter model attains the highest F1 on every test set.

eess.AS · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2608.27906

Design the Feedback, Not Just the Reward: Environments for Open-Ended Reinforcement Learning

Rui Jin, Jikai Chen, Chengyue Yu, Yihan Chen, Hao Zhou, Demin Zhu, Kaichen Yang, Dong Wang 等 10 位作者

原文摘要

Reinforcement learning has advanced large language models on tasks with reliable verifiers, where checking an outcome provides a clear basis for reward. Extending this approach to open-ended tasks requires environments that can both evaluate complex, partially successful outputs and turn these judgments into effective learning guidance. We propose a reinforcement learning framework built around a training environment that integrates human domain knowledge with model reasoning. Human domain knowledge, encoded in rubrics, anchors evaluation to task intent, while model reasoning combined with hierarchical rewards distinguishes complex open-ended outputs and links diagnosed failures to likely responsible output regions. Furthermore, these diagnostic attributions guide token-level weights in the GRPO objective, thereby translating the ambiguous notion of success in open-ended tasks into concrete guidance for policy optimization. We instantiate this framework in interactive web application generation, a representative open-ended generation task. The resulting model achieves an average pass rate of 41.25\% on MiniAppBench and 76.19\% on ArtifactsBench. Ablation studies show the contributions of individual components, while additional out-of-distribution evaluations support transferable gains without degrading performance on other evaluated tasks.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39735

From the Transformer to a Formal Semantics of Coordinated Transformations

Marco Giunti, Fabrizia Giulia Garavaglia

原文摘要

We develop a formal semantics for a general class of coordinated systems of parameterized transformations, taking the Transformer as a paradigmatic starting point but abstracting from its particular mathematical instantiation. Representational vectors receive both extensional reference and ordered intensional interpretations, while parameter structures acquire relative, second-level interpretations that determine how argument properties are preserved, replaced, or combined. This yields the notion of a transforming concept: a parameterized transformation whose numerical action is coordinated with a corresponding property-level map. We then distinguish the common algebraic-semantic core of these systems from their architecture-specific functional organization, allowing different mathematical instantiations and mechanical realizations of the same abstract system type. The framework is applied to attention heads and residual connections, providing semantic explanations that depend only on the shared algebraic-semantic core and their local functional organization and therefore generalize beyond the standard Transformer. These analyses also reveal the modularity of the framework: complex architectures can be decomposed into simpler semantically coordinated subsystems whose organization may recur across different abstract system types.

cs.AI · cs.CL · cs.LO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.11886

Testing Deep Learning Library APIs via Cross-Framework Differential Fuzzing

Bin Duan, Ruican Dong, Naipeng Dong, Dan Dongseong Kim, Guowei Yang

原文摘要

Deep learning libraries underpin many safety- and reliability-critical applications, yet existing API-level testing techniques often rely on intra-library properties or CPU--GPU differential oracles and may miss defects that behave consistently across hardware backends. We present Xamt, a cross-framework differential fuzzing approach for deep learning library APIs. Xamt constructs and tests execution-validated groups of APIs intended to implement equivalent operations across seven libraries. It uses explicit API aliases and parameter-role normalization to construct candidate correspondences and validates them through pairwise execution and a group-level behavioral check on canonical ordinary inputs. The resulting groups are explored using variance-guided differential fuzzing with ordinary, boundary, and non-finite inputs. Crash and inconsistency oracles flag executions exhibiting abnormal termination or inconsistent outputs for subsequent reproduction and analysis. Across the seven libraries, Xamt constructs 676 execution-validated groups containing 2,563 matched APIs. Among these, Xamt identifies 72 independently reproduced discrepancy cases, including 4 crash cases and 68 output inconsistencies. Among the 72 developer reports, 25 have been confirmed, including 23 that have been fixed.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.11345

Symmetry-Aware Steering of Equivariant Diffusion Policies: Benefits and Limits

Minwoo Park, Junwoo Chang, Jongeun Choi, Roberto Horowitz

原文摘要

Equivariant diffusion policies (EDPs) combine the expressivity of diffusion models with the generalization and sample efficiency afforded by geometric symmetries. While steering these policies with reinforcement learning (RL) offers a promising fine-tuning mechanism beyond demonstration data, directly applying standard (non-equivariant) RL ignores the symmetries that EDPs are designed to exploit, leading to sample inefficiency and instability. We theoretically establish that the diffusion process of an EDP is equivariant, inducing a group-invariant latent-noise MDP which is well-suited for equivariant diffusion steering. Building on this, we introduce a principled symmetry-aware steering framework and compare standard, equivariant, and approximately equivariant RL strategies across tasks with varying degrees of symmetry. While we identify the practical boundaries of strict equivariance under symmetry breaking, exploiting symmetry during the steering yields substantial benefits---enhancing sample efficiency, preventing value divergence, and achieving strong policy improvements even when EDPs are trained from extremely limited demonstrations.

cs.LG · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39733

Bank-World: A Benchmark for Evaluating Agents on Banking Workflows

Daniel Rupawalla

原文摘要

Bank-World is a benchmark of 50 banking tasks across two simulated institutions. Completing banking work requires more than producing the right calculation: agents must reconcile records, obtain permission, execute transactions, and keep instructions and status reports consistent as circumstances change. Bank-World tests these requirements through single-turn assignments and multi-turn interactions with simulated employees who supply information, approve actions, and revise instructions. Grading combines executable checks of recorded actions and state with model judgments of task requirements, including whether valid alternative solutions satisfy them. Across 1,600 attempts by four models, we find that correct decisions often fail to become completed work. Agents charge fees twice, distribute the correct total in incorrect amounts among the recipients, and execute payments while approval is pending. Their strengths also differ: Sol leads single-turn completion, Opus has the highest observed multi-turn completion rate, and Grok succeeds across more multi-turn tasks but less consistently. Bank-World makes these differences inspectable through task-level results and worked examples connecting source evidence, agent decisions, and simulated consequences. We retain the task environments, executable graders, and full trajectories privately to reduce contamination and preserve the benchmark for future evaluations.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39731

Going deep, reaching further: What can Boltzmann machines efficiently represent?

Tobias Reinhart, Gemma De les Coves

原文摘要

While universal approximation theorems theoretically underpin the representation capabilities of machine learning models, they have two shortcomings: They do not focus on efficient representations and they tend to be insensitive to depth and other heuristically important properties. In this work we show that these two shortcomings are intertwined. We prove that machine learning models which are deeper or have higher-order interactions can efficiently represent a larger set of functions, i.e. have larger efficient reach. It follows that deep Boltzmann machines (DBMs) have maximal efficient reach, restricted Boltzmann machines (RBMs) sub-maximal, and k-body generalizations of RBMs form a hierarchy between the two, even though all are universal. More generally, (i) we provide a full characterization of machine learning models with maximal efficient reach; (ii) we derive separations between deep and shallow models for three representation tasks; and (iii) we prove that the efficient reach of shallow models constitutes an infinite hierarchy indexed by the interaction order. The proofs draw on different methodologies, namely on (i) a recent characterization of universal spin models; (ii) computational complexity bounds for spin models; and (iii) communication complexity bounds applied to shallow models. This work shows that universal machine learning models can strongly differ in their efficient representation capabilities, and provides a theoretical foundation for heuristic observations.

cs.LG · cond-mat.dis-nn · math-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39730

Investigating Data Flows from Android Games

Judit Borcsiczky, Lukas Moog, Boel Nelson

原文摘要

Online applications can share data with arbitrary parties, without users noticing. In practice, these data flows could constitute privacy violations to individual users, with the lack of transparency leaving users unaware of the unwanted data flows. To understand the spread and scale of this privacy threat, we investigate what data is collected and where it is sent in popular free-to-play Android games. As part of our investigation, we conduct a measurement study where we collect and analyze over 16 GB of network traffic from 50 puzzle games. Additionally, we explore the effectiveness of user-side countermeasures for a selection of the apps. We find that while most countermeasures, such as ad-blocking DNS services, decrease data flows, withholding consent and opting out of data collection can produce inconsistent behavior including increased outgoing traffic. To encourage further analysis, we release our measurements as an open dataset.

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.10726

CacheSolidarity: Preventing Prefix Caching Side Channels in Multi-Tenant LLM Serving Systems

Panagiotis Georgios Pennas, Konstantinos Papaioannou, Marco Guarnieri, Thaleia Dimitra Doudali

原文摘要

Large Language Models (LLMs) rely on optimizations like Automatic Prefix Caching (APC) to accelerate inference. APC works by reusing previously computed states for the beginning part of a request (prefix), when another request starts with the same text. While APC improves throughput, it introduces timing side channels: cache hits are faster than misses, creating observable latency differences. In multi-tenant systems, attackers can exploit these differences to infer sensitive information, e.g., by incrementally reconstructing another user's request by observing hit/miss patterns. Current defenses take a sledgehammer approach: they disable APC and cache sharing, isolating users, and sacrificing efficiency for regular users. This paper presents CacheSolidarity, a system that secures multi-tenant LLM serving systems against APC side channels without sacrificing performance and efficiency. CacheSolidarity monitors cache reuse across users, flags suspicious sharing, and selectively isolates prefixes, restricting their reuse only when necessary. Evaluation shows that CacheSolidarity enables up to 70% higher cache reuse and 30% lower inference latency compared to existing user-isolation defenses. CacheSolidarity's lightweight design demonstrates how LLM serving can be secured without sacrificing performance or incurring unbearable overheads.

cs.CR · cs.DC · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.01671

Self-Referential $K$-SAT and the Finite Analogue of Gödel's Incompleteness Theorem

Wen Fang, Xianxian Li, Jun Liu, Jie Luo, Yongxin Tong, Ke Xu

原文摘要

We study self-reference and solution independence in Boolean $K$-SAT as a finite analogue of Gödel incompleteness. Independence is defined through factorial moments of the solution count. Constant-width random formulas fail this criterion due to correlations among overlapping assignments. At a covering threshold, logarithmic-width random CNFs have a Poisson solution count, with positive probabilities of unsatisfiability and unique satisfiability. Replacing a redundant clause by one falsified by the unique solution yields an unsatisfiable companion preserving the unsigned incidence graph. For every permitted local view of a good uniquely satisfiable formula, an unsatisfiable companion preserves that view. Irreducibility defeats deterministic and bounded-error evaluators using $N^c$ clause queries, for fixed $0<c<1$. It establishes a local information obstruction, not an unrestricted time lower bound. For fixed $δ>0$, transcripts of $N^{1-δ}$ queries leave $N-o(N)$ bits of witness entropy. On typical support graphs, expansion yields linear Resolution width, linear PC/PCR and SOS degree, and exponential proof size. Bounds hold for semantic Cutting Planes under a partition condition and for Positivstellensatz with bounded product width, uniformly over unsatisfiable support-preserving signings. Structural evidence and the limits of acceleration strategies motivate the self-referential $K$-SAT exhaustive-search hypothesis (SRK-ESH): no uniform deterministic algorithm deciding the promise family achieves a fixed proportional saving in the exponent. This dual-evidence criterion combines intrinsic hardness mechanisms with algorithmic evidence. We interpret this hypothesis as a quantitative projection of the Gödel-style local--global gap. The information obstruction constrains quantum local observation and statistical learning from bounded local information.

cs.CC · cs.DS · cs.IT · cs.LO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.13309

NovaSplat: Model-Free 6D Object Pose Estimation via 3D Gaussian Splatting Onboarding and Refinement

Georgios Floros, Evangelos Sartinas, Orestis Vaggelis, Maria Pateraki

原文摘要

6D pose estimation of novel objects without CAD models remains an open challenge: model-free methods must build the object representation from scratch during onboarding and have long trailed their model-based counterparts. We present NovaSplat, a model-free pipeline that closes this gap. From a short smartphone video captured at onboarding, we train a 3D Gaussian Splatting (3DGS) model that serves both as a template source for detection and coarse pose estimation and as a differentiable backbone for pose refinement. Our refiner optimizes the object-to-camera pose with combined photometric and geometric losses under a continuous rotation parametrization free of gradient singularities. On a household-object benchmark, NovaSplat surpasses all model-based methods. On a challenging industrial benchmark with textureless and specular surfaces, it outperforms all model-free competitors while substantially narrowing the gap to model-based ones. We further introduce NovaSplat-Lite, an inference variant that is $3.1\times$ faster at negligible accuracy cost. Code will be made available at https://github.com/POSE-Lab/novasplat .

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39728

Grounding Predictive Reliability through Masked Observability

Shang Gao, Bernhard Sick, Franz Götz-Hahn

原文摘要

An uncertainty estimate is meaningful only if its semantics can be tied to observable predictive behavior. Normal-Inverse-Gamma (NIG) evidential regression provides a structured decomposition of predictive variability into data-scale and predictive-mean components, but marginal likelihood does not identify their allocation. We address this semantic ambiguity in masked representation learning. MORSE (Masked Observability for Reliable Structured Encoding) predicts the same hidden target under controlled changes in visible context and uses normalized cross-context variation to ground predictive-mean uncertainty, while a Gaussian objective learns the conditional mean and data scale. The normalized variation plays the role of the NIG factor $1/ν$, which the marginal leaves unidentified; this yields a policy-relative observability variance that measures dependence on visible evidence, distinct from variation induced by resampling the training set. On a Gaussian-process benchmark with a contextual reference built from analytic Bayes conditional means, MORSE has the lowest log-variance error among compared evidential, ensemble, and dropout estimators in all nine tested settings, while the estimator closest to training-set variation perturbs the model rather than its context in every setting, so the two references separate the estimators empirically. MORSE amortizes observability estimation into one forward pass per observation state. On a heteroscedastic pulse benchmark, its predictor's cross-context variance approaches a large-sample reference as training data increase. MORSE also improves low-label transfer on PTB-XL and in-distribution trajectory prediction on IMPTC.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39727

Cross-Encoder Anchor Refinement for Zero-Shot Anomaly Detection

Kaisong Ji, Ziyang Xu, Chang Bian, Yu Zhou, Wenyu Liu, Xinggang Wang

原文摘要

Zero-shot anomaly detection aims to transfer anomaly discrimination from auxiliary training domains to unseen categories while localizing subtle defects. A key challenge is to construct discriminative references that combine contextual representations with complementary local evidence. We present Cross-Encoder Anchor Refinement (CEAR), which connects two visual encoding paths for the same image at the anchor stage, before normal and anomalous prototypes are constructed. An independent convolutional encoder pretrained for industrial product recognition builds an image-specific memory shared across selected vision transformer (ViT) layers. Spatial anchors read from ViT patch features query this memory through cross-attention and undergo residual refinement. Image-conditioned normal and anomalous queries then gate anchor aggregation to construct prototypes for anomaly scoring. Across 13 industrial and medical datasets, CEAR achieves the best performance in 57 of 68 evaluations spanning image-level detection and pixel-level localization. Notably, CEAR surpasses all other state-of-the-art methods in 41 of 44 pixel-level comparisons. Across 11 localization datasets, mean gains in pixel-level maximum F1 score and average precision are 4.45 and 3.79 percentage points, respectively. This study shows how cross-encoder interaction at the anchor stage can integrate complementary visual representations for fine-grained anomaly localization across domains.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.11472

BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registration

Qianliang Wu, Yaqing Ding, Guangwei Gao, Weiping Ding, Jin Xie, Jian Yang

原文摘要

Non-rigid point cloud registration depends on accurate correspondences under deformation and partial visibility. Existing coarse-to-fine methods use coarse matches to select regions for fine matching, but incorrect selection can remove valid correspondences before refinement. We introduce \paper, a conditional transport framework that connects coarse correspondence estimation to high-resolution matching. A diffusion model first estimates a coarse matching matrix. We lift the complete estimate to a fine-level source matrix and refine its scores with a geometry-conditioned bridge. We consider two bridge formulations: a deterministic endpoint-parameterized flow and a stochastic paired Brownian bridge with endpoint and noise prediction. At each step, the current matrix provides an alignment for the next prediction. Both models reuse backbone features throughout inference. Experiments on 4DMatch and 4DLoMatch show improved correspondence and non-rigid registration accuracy. The models also transfer to CAPE and DeepDeform without target-domain training. Ablations examine the roles of candidate coverage, source initialization, and refinement budget.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39723

Countable Nondeterminism in Weighted Programming with an Application to Mechanized Foundations for Probabilistic Program Verification

Sebastian Körner, Oliver Emil Bøving, Christoph Matheja

原文摘要

Weighted programming is a framework by Batz et al. for describing mathematical models or optimization problems as imperative programs parametrized over semirings and then analyzing them with program verification techniques like weakest precondition calculi. Applications include reasoning about expected outcomes of probabilistic programs and competitive analysis of online algorithms. We extend weighted programming with (1) countable nondeterminism and (2) user-defined additive rewards, where programs are parametrized over modules instead of semirings. The resulting framework enables reasoning about expected resource consumption of probabilistic programs and about optimal scores of combinatorial games. A technical challenge is that wp-calculi for weighted programs with (1) and (2) over arbitrary modules can be unsound, because it is well-known that continuity properties commonly used in program semantics break in the presence of countable nondeterminism. We study conditions under which a wp-style transformer for reasoning about weighted programs is sound with respect to an operational ground truth defined in terms of weighted decision processes (WDPs) - transition systems that generalize Markov decision processes by drawing transition weights and state rewards from a module. Based on those conditions, we show that a range of concrete instances of the weighted programming framework enjoy sound weakest precondition reasoning. We demonstrate the usefulness of our wp-semantics through case studies for different modules. We mechanized our extended weighted programming framework and our main soundness results in the interactive theorem prover Lean. Instantiating these results for probabilistic programming yields, to the best of our knowledge, the first mechanized proof of a fixed point characterization of minimal expected rewards in Markov decision processes with countable nondeterminism.

cs.PL · cs.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39721

WorldProbe: When Video World Models Fall Apart under Long-Horizon Spatial Exploration

Minqi Wang, Jie Peng, Hejun Dong, Ruchang Yao, Puyi Wang, Siyuan Huang, Jihai Zhang, Yafu Li 等 11 位作者

原文摘要

Video world models generate future visual observations from camera or action inputs, with the goal of synthesizing persistent 3D worlds that can be explored across time and space. Existing benchmarks typically evaluate short interactions or rely on camera trajectories fixed before generation. The performance of video world models under long-horizon exploration with extensive camera motion remains under-explored. We introduce WorldProbe, a diagnostic benchmark that uses a goal-conditioned multimodal agent to adapt camera actions online during generation. WorldProbe comprises 164 test cases across four probing families. Across 10 state-of-the-art models, we generate more than 1,600 rollouts totaling approximately 800 minutes, with horizons up to 180 seconds. Our evaluation across four dimensions reveals both the degradation of local measures and the emergence of long-range inconsistencies. We find that recent models sustain visual and content quality for longer, while long-range memory and evolution remain weak. These results expose a gap between locally stable generation and persistent world consistency that is largely missed by existing benchmarks. Code and benchmark resources are available at https://github.com/Untitled-W/WorldProbe.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39717

Implicit Bias of (Stochastic) Gradient Descent on Deep Linear Diagonal Networks

Wiebke Bartolomaeus, Holger Rauhut

原文摘要

Modern machine learning models are often overparameterized, i.e., have more parameters than training data. This typically implies that the loss function admits multiple minimizers so that training methods (and their hyperparameter choices) have significant influence on the computed solution. We study this so-called implicit bias phenomenon in the context of training deep linear diagonal networks. Previous work has shown that the gradient flow for learning such networks converges to (almost) sparse solutions when initialized small. For an arbitrary number of layers, we extend this analysis to the practically more realistic (stochastic) gradient descent iterations. Our approach identifies (stochastic) gradient descent as a perturbed (stochastic) mirror gradient descent. This allows us to establish convergence and characterize the limiting solution, relating it to weighted $\ell_1$-minimization. Moreover, we provide sufficient conditions on the step sizes and quantify the influence of the step sizes on the implicit bias.

cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39716

Adaptive Federated Optimization Across Smooth and Nonsmooth Regimes

Zimeng Wang, Ali Dadras, Alp Yurtsever

原文摘要

AdaGrad-style methods can simultaneously adapt to both the order and constants of smoothness in centralized optimization. However, existing extensions to federated optimization with heterogeneous client objectives and multiple local steps require the smoothness order to be specified in advance. We address this limitation with AdaFed, a federated method that adapts across several regimes under a single choice of parameters. In the deterministic setting, AdaFed achieves an $O(1/T)$ convergence rate for both smooth nonconvex and smooth convex objectives, and an $O(1/\sqrt{T})$ rate for Lipschitz nonsmooth convex objectives up to logarithmic factors. Under a light-tailed stochastic-gradient noise assumption, these guarantees extend to the stochastic setting with additional logarithmic factors and noise-dependent terms. Experiments across the three problem classes further support our theoretical findings.

math.OC · cs.LG

查看论文
arXiv ↗PDF ↗