跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+814新增论文
+671其中 AI 相关
+98已有论文修订
+94新增 AI 导读

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

统计口径与数据新鲜度

统计 2026-11-18 14:24 — 2026-11-19 14:24(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-19 06:59最近发现新增版本:2026-11-19 06:59库内论文最新更新时间:2026-11-18 08:00

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

26,871 已收录论文22,375 AI 相关8,156 有修订112 HF 社区发现

论文修订列表

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

找到 8,156 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v4arXiv:2602.06054

Novelty Reviewer: A Large-Scale Dataset and Model for Reviewer-Aligned Novelty Assessment

Abeer Mostafa, Thi Huyen Nguyen, Zahra Ahmadi

原文摘要

Assessing novelty in AI research is arguably the most consequential yet least reliable step in peer review. Reviewer judgments of novelty remain inconsistent and dependent on comparisons to prior work that are often incomplete. We release a large-scale Novelty Reviewer Dataset built from 102,021 official reviews of 37,899 ICLR and NeurIPS submissions (2022-2025). For each submission, it provides the reviewers' novelty statements, a paper-level novelty assessment, and a novelty score on a four-point scale. On top of this dataset, we build Novelty Reviewer, a literature-aware framework that learns how reviewers judge novelty and grounds these judgments in semantic comparisons to existing research. We fine-tune a large language model on the dataset to capture reviewer-aligned novelty evaluation behavior. Given a manuscript, the framework extracts structured representations of its ideas, methods, and claims; retrieves semantically related papers; and constructs a knowledge graph that enables concept-level comparison to prior work. Based on the retrieved evidence, the model produces calibrated novelty scores alongside human-like explanatory assessments, reducing overestimation and improving consistency relative to existing approaches. Furthermore, we analyze different LLMs' abilities to assess originality and detect potential conceptual plagiarism. We publicly release the dataset, the model, and the code with documentation to support research on automated novelty assessment and peer review.

cs.CL

版本更新 · v2arXiv:2610.22272

The Information Bottleneck and the Privacy Funnel are NP-hard

Roberto Bruno, Ugo Vaccaro

原文摘要

Given a joint distribution $P_{XY}$ of random variables $X,Y$ on finite alphabets, the information bottleneck method seeks a representation $T$ of $X$ that is as informative as possible about $Y$ while compressing $X$; the privacy funnel asks for a representation that discloses much about $X$ while leaking little about $Y$. In both scenarios $T$ and $Y$ are conditionally independent given $X$. We show that computing the optimal value $\operatorname{IB}(P_{XY},R) = \sup_T \{ I(Y;T) : I(X;T) \le R \}$ of the information bottleneck problem, as well as its Lagrangian relaxation $L_β(P_{XY}) = \sup_T [ I(Y;T) - βI(X;T) ]$, is NP-hard. Moreover, unless $\mathrm{P} = \mathrm{NP}$, neither $\operatorname{IB}(P_{XY},R)$ nor $L_β(P_{XY})$ can be approximated in polynomial time within an additive error of order $|\mathcal{X}|^{-(1+α)}$, for every fixed $α> 0$. We also prove that computing the privacy funnel $\operatorname{PF}(P_{XY},r) = \inf_T \{ I(Y;T) : I(X;T) \ge r \}$ and its Lagrangian relaxation $Λ_β(P_{XY}) = \inf_T [ I(Y;T) - βI(X;T) ]$ is NP-hard, and that, unless $\mathrm{P} = \mathrm{NP}$, neither can be approximated in polynomial time within an additive error of order $|\mathcal{X}|^{-2}$.

cs.IT

版本更新 · v2arXiv:2609.09299

Literati: Towards Anytime Optimal Shape Generalized Trees via AO*

Nakul Upadhya, Eldan Cohen

原文摘要

Decision trees are prized for their interpretability and strong performance on tabular data, but popular greedy top-down induction algorithms can yield suboptimal and unnecessarily complex structures. Optimal decision tree methods address this through global optimization, yet remain restricted to axis-aligned threshold splits, which limit the expressivity of each node and often force deep, complex trees to capture non-linear feature effects. Shape Generalized Trees (SGTs) generalize threshold splits to learnable univariate shape functions, improving expressivity and enabling more compact trees. However, existing SGT induction algorithms are greedy and offer no optimality guarantees. In this work, we introduce Literati, the first algorithm for optimal SGT induction. We propose a novel AND/OR graph formulation of the problem that jointly optimizes tree structure and shape function complexity. To solve this AND/OR graph, we develop an AO*-based algorithm with two enhancements that improve anytime performance while preserving optimality: a secondary heuristic for OR-node selection and a round-robin policy for AND-node exploration. Across 24 real-world datasets, Literati achieves higher training and test accuracy than state-of-the-art tree approaches.

cs.LG

版本更新 · v2arXiv:2610.03645

Exponential quantum space advantage in random data streams

Adam Bouland, Matthew Ding, Siddhartha Jain

原文摘要

We show two unconditional quantum space advantages in the random-order streaming model. First, we show the Yamakawa-Zhandry Code Intersection problem admits exponential quantum advantage in the streaming model when its inputs are streamed in random order. This means quantum computers exhibit exponential space advantage even when simply receiving $(x,f(x))$ pairs for a uniformly random function $f$ in a uniformly random order. Notably, our classical space lower bound does not follow from a communication lower bound. Instead, we utilize density-restoring partitions from communication complexity directly with potential-function analysis in the style used to prove memory-sample tradeoffs for learning. The resulting argument is distinct from both lines of work. Second, we use our framework to show quantum space advantage for the Optimal Polynomial Intersection (OPI) problem in certain regimes via a streaming version of the Decoded Quantum Interferometry algorithm. In particular, we show that for degree $d$ and $n$ evaluation points, attaining $1/2 + Ω(\sqrt{d/n})$ fraction of satisfied OPI constraints via streaming requires $Ω(n)$ classical bits of memory but only $O(d\log n)$ qubits. This yields provable quantum advantage in a "low-rate" regime when the number of evaluation points is much larger than the degree, with a space advantage that can be as large as exponential in certain parameter settings.

quant-ph · cs.CC

版本更新 · v3arXiv:2610.10904

Unconditional Boolean Dynamic Lower Bounds from Disjointness

Young Kun Ko

原文摘要

We prove an unconditional $Ω((\log n/\log\log n)^2)$ lower bound on the maximum of the worst-case update time and expected query time for the insert-only version of Patrascu's multiphase Disjointness problem [STOC 2010]. The bound holds in the zero-error cell-probe model with logarithmic word size. Patrascu's reductions transfer it to directed reachability under edge insertions, already on directed acyclic graphs of depth $2$. This improves the $\widetildeΩ(\log^{3/2} n)$ bound of Larsen and Yu [SICOMP 2025] to the quadratic-logarithmic scale previously attained for dynamic range counting and multiphase Inner Product. The bound also transfers to a broad collection of dynamic graph, algebraic, geometric, and string problems. We also obtain a separation between amortized and worst-case time for streaming regular-expression membership. For a simple family of expressions of maximum length $M$ over a polynomial-size alphabet, a deterministic algorithm uses $O(1)$ amortized time per symbol on every input stream, whereas every zero-error cell-probe algorithm with word size $w=Θ(\log M)$ requires $Ω((\log M/\log\log M)^2)$ time on some symbol. The proof adapts Ko's 2.5-round multiphase communication framework [FOCS 2026] from Inner Product to Disjointness. Our main technical observation is that the protocol's verification step allows a one-sided corruption bound to replace the discrepancy property used for Inner Product.

cs.DS · cs.CC

版本更新 · v4arXiv:2510.25126

Why Freeze the Encoder? A Controlled Study of End-to-End Sequence-Graph Learning for User Behavior

Yuen Chen, Yulun Wu, Samuel Sharpe, Igor Melnyk, Nam H. Nguyen, Furong Huang, C. Bayan Bruss, Rizal Fathony

原文摘要

Modeling user behavior couples two distinct signals: a per-user sequence of events and a persistent user-to-user relation graph. Standard pipelines preserve these native formats by combining them in two stages: a sequence encoder is pretrained, its per-user embeddings are frozen, and a graph model is trained on top to allow for cheap serving and cross-task reuse. We ask a simple question: does training the sequence and graph models end-to-end help, and if so, when? To isolate the impact of the training strategy, we hold a standard sequence-encoder-to-GNN pipeline fixed and vary only the optimization method; on Brightkite, a matched control that starts both pipelines from the same pretrained encoder and changes only whether it is updated attributes a 10.6-point MRR gain to end-to-end updating. Across relationship prediction and fraud detection on five real-world datasets, we find that the benefit of end-to-end training is conditional: it improves clearly over frozen two-stage pipelines on relationship prediction, where the relation graph appears to carry much of the signal, whereas gains shrink where the predictive signal is largely node-local (fraud detection), a regime in which a text-fed relational graph transformer achieves competitive results. Furthermore, recasting the data as a temporal graph yields inconsistent results compared to this native sequence-graph formulation. Ultimately, this work provides a controlled empirical account of when jointly training the two structures helps.

cs.LG · cs.AI

版本更新 · v2arXiv:2609.12263

A First-Principles Evaluation of Graph-Based Network Intrusion Detection Systems

Rui Zhao, Wajih Ul Hassan

原文摘要

Graph-based network intrusion detection systems (GIDS) report strong benchmark detection metrics, but those metrics establish little about deployability. We approach the problem from first principles: rather than inheriting the preprocessing, windowing, and thresholding conventions of each published system, we ask what a controlled comparison requires and impose it uniformly. The result is GIDS-Eval, an evaluation framework that decomposes a GIDS into six interchangeable stages and turns those conventions into explicit experimental variables, so reported performance can be attributed to individual stages instead of whole pipelines. We survey nine representative GIDS, reimplement five of them within GIDS-Eval, and evaluate them on four datasets under one matched protocol. We identify nine recurring evaluation gaps and quantify the impact of each: two crafted edges achieve full evasion against three of the eight detector-dataset pairs with anything to hide; the snapshot window alone accounts for a mean 38.3% relative swing in average precision (AP); aligning preprocessing across systems moves AP by up to 61.8 percentage points for a single detector; and none of the 18 detector-dataset pairs we replay can alert as events arrive. We introduce GIDS-Lite, an encoder-free control built in the same framework, which ranks first by AP on two of the four datasets at up to 575$\times$ lower runtime. Architectural complexity is therefore not a consistent driver of detection quality under our matched protocol on current benchmarks, but it does enlarge the runtime, calibration, and attack surfaces operators must defend.

cs.CR

版本更新 · v2arXiv:2601.17126

Foundation model for particle collision data analysis

Ting-Hsiang Hsu, Bai-Hong Zhou, Qibin Liu, Yue Xu, Shu Li, George Wei-Shu Hou, Benjamin Nachman, Shih-Chieh Hsu 等 11 位作者

原文摘要

Data-intensive collider experiments increasingly require models that transfer across high-dimensional, partially observed measurements, yet most analyses still optimize separate models for each task. Here, to address this bottleneck, we introduce EVENET, an event-level foundation model pretrained on 500 million simulated collision events using self-supervised learning and physics-informed supervision. The model constructs a shared particle-cloud representation from the variable-length set of physics objects in each event. Across searches for heavy resonances and exotic Higgs decays, EVENET outperforms both established and state-of-the-art baselines, particularly in low-statistics regimes. We validate transfer to experimental data by rediscovering the $Υ$ meson in CMS Open Data. The pretrained model also supports precise extraction of quantum-correlation observables that remain stable under the tested systematic variations. Together, these results establish a reusable backbone for diverse collider analyses, improving downstream adaptation after a substantial one-time pretraining investment.

hep-ex · cs.LG · hep-ph

版本更新 · v2arXiv:2602.20408

A Cognitive Framework for Idea Diversity in Large Language Models

Yuting Deng, Melanie Brucks, Olivier Toubia

原文摘要

Consumers, marketers, and new product developers increasingly rely on LLMs for ideation. Yet ideas generated by independent LLM sessions tend to be less diverse than ideas generated by independent samples of humans, raising concerns that widespread reliance on LLMs could homogenize marketplace ideation and decrease consumer welfare. We identify two mechanisms undermining LLM idea diversity, informed by theories of creative ideation from new product development and cognitive psychology. First, LLMs aggregate knowledge into a unified distribution rather than exhibiting the knowledge partitioning inherent to human populations, where each person occupies a distinct region of the knowledge space. Second, at the individual level, LLMs exhibit fixation just as humans do, where early outputs constrain subsequent ideation. Two product-ideation experiments demonstrate that targeted prompting interventions can address both mechanisms. Persona modifiers based on ordinary individuals improve knowledge partitioning but amplify fixation. This fixation can be mitigated by using chain-of-thought (CoT) prompting, and combining both strategies produces the highest idea diversity, outperforming humans. These findings offer a theoretically grounded framework for understanding LLM idea diversity and practical strategies for leveraging AI's efficiency without compromising the idea diversity that sustains marketplace variety and consumer welfare.

cs.CY · cs.AI · cs.HC

版本更新 · v5arXiv:2509.07274

LLM Analysis of 150+ Years of German Parliamentary Debates on Migration Reveals a Shift from Post-War Solidarity to Anti-Solidarity in the Last Decade

Aida Kostikova, Ole Pütz, Steffen Eger, Olga Sabelfeld, Benjamin Paassen

原文摘要

Migration has been a core topic in German political debate, from postwar expellee displacement to labor migration and recent refugee movements. Large-scale analysis of such political discourse has traditionally required extensive manual annotation, limiting coverage. Large language models (LLMs) offer a scalable alternative. Using a theory-driven annotation scheme, we examine how well LLMs annotate subtypes of solidarity and anti-solidarity in German parliamentary debates and whether the resulting labels support valid downstream inference. We first evaluate multiple LLMs across model size, prompting strategies, fine-tuning, historical versus contemporary data, and systematic errors. The strongest models, especially GPT-5 and gpt-oss-120B, achieve macro-F1 scores comparable to human agreement, although their systematic errors can bias downstream results. We therefore combine soft-label model outputs with Design-based Supervised Learning (DSL) to reduce bias in long-term trend estimates. Beyond the methodological evaluation, we interpret the resulting annotations from a social-scientific perspective across the Reichstag (1867-1933), West German Bundestag (1949-1990) and Re-Unified German Bundestag (1990-2025) corpus to trace trends in solidarity and anti-solidarity toward migrants, with detailed analysis of postwar Germany (1949-1957) and contemporary Germany (2009-2025). We find relatively high levels of solidarity in the postwar period, especially in group-based and compassionate forms, and a marked rise in anti-solidarity since 2015. We argue that LLMs can support large-scale social-scientific text analysis, but their outputs require rigorous validation and, where systematic errors are present, statistical correction.

cs.CL · cs.CY · cs.LG

版本更新 · v3arXiv:2605.16610

Tensor Cookbook: Mastering Tensors through Diagrams

Beheshteh T. Rakhshan, Guillaume Rabusseau

原文摘要

High-dimensional data arise naturally in many areas of science and engineering, including machine learning, signal processing, computational physics, and statistics. Such data are often represented as tensors, multi-dimensional generalizations of matrices. While tensors provide a natural representation for multi-modal structure, their direct manipulation quickly becomes challenging as the order grows: the number of parameters increases exponentially, and algebraic expressions involving many indices become difficult to interpret and implement. Tensor networks (TNs) provide an effective framework for addressing these challenges. Originally introduced by Penrose and developed extensively in quantum physics, the graphical language of tensor networks encodes contractions as edges in a graph, reducing notational overhead and revealing structural properties obscured by index notation. Despite the central role of high-dimensional tensors in modern machine learning and numerical analysis, tensor network diagrams remain underutilized outside quantum computing, partly due to the lack of a self-contained mathematical reference accessible to a broad technical audience. This manuscript provides a self-contained guide to tensor networks and their use in tensor algebra. We present the main operations on tensors, contractions, products, and reshaping through, graphical notation, and show how classical tensor decompositions and related computations are naturally expressed in this framework. We also illustrate how tensor networks simplify the derivation of gradients and the manipulation of high-dimensional probability distributions. Throughout, we show that the diagrammatic approach yields genuinely shorter and more transparent proofs of classical identities, rank bounds, and gradient formulas that would otherwise require laborious index manipulation.

cs.LG · cs.GL

版本更新 · v2arXiv:2603.02258

Universal Conceptual Structure in Neural Translation: Probing NLLB-200's Multilingual Geometry

Kyle Elliott Mathewson

原文摘要

Do multilingual translation models organize meaning around a shared conceptual space, or do they primarily encode language identity and surface form? We probe the encoder geometry of Meta's 600M-parameter NLLB-200 model across 135 languages and 101 Swadesh concepts in contextualized carrier-frame and decontextualized bare-word regimes against null and confound controls. First, two-way variance partitioning reveals an additive language-shift plus conceptual-manifold geometry: language shifts account for 45.7% of variance on bare words vs. 13.7% in context, and mean-centering improves the between-to-within-concept distance ratio (vs. a 0.99 permutation null) by 2.14x on bare words (1.15 to 2.46; 2.27x across disjoint scripts) and 1.19x in context (2.25 to 2.69), with conceptual separation peaking at Layer 10 (mutual k-NN overlap jumping 4.35x). Second, semantic category explains 25.4% of Swadesh convergence variance ($F(7,93)=4.53$, $p=2.21\times 10^{-4}$; partial $F=7.74$ controlling for fertility and length)---over 20x orthography or phonology ($R^2\le 0.012$)---while the advantage of Swadesh over non-loanword concrete nouns ($d=0.54$--$0.69$) is mediated by Zipfian subword compactness ($p=7.43\times 10^{-7}$). Third, language distances track ASJP NLD and LDND phonetic distances within subfamilies under block-permutation and cross-script controls ($ρ_s=0.65$--$0.67$, block $p=10^{-4}$; global bare-word Mantel $ρ_s=0.24$, $p=0.001$), and CLICS$^3$ colexified concepts lie closer across string-distinct, within-category ($ρ_s=0.32$), and bare-word ($d=1.79$) controls ($d=1.43$, $p=1.55\times 10^{-33}$). Finally, basic color terms recover the Berlin and Kay hierarchy ($ρ_s=0.91$--$0.93$, $p\le 2.18\times 10^{-4}$), and semantic offsets exceed distance-matched controls ($p=3.55\times 10^{-5}$, $d=1.06$). We release InterpretCognates, an interactive toolkit and reproducible suite.

cs.CL · cs.AI · cs.LG

版本更新 · v2arXiv:2609.34270

Bayesian Active Learning for Intent Disambiguation in Interactive Robot Planning

Huao Li, Carson Sobolewski, Augustinos Saravanos, William Tan, John Karigiannis, Chuchu Fan

原文摘要

Interactive robot planning requires robots to infer and execute human intentions from natural language instructions that are often ambiguous, incomplete, or underspecified. Although large language models (LLMs) provide a powerful interface for clarification, relying on the generative model to drive an multi-turn conversation can introduce systematic failures. We propose a Bayesian framework that treats clarification as an active learning problem over grounded Signal Temporal Logic (STL) task specifications. Our method uses LLMs to initialize candidate formal specifications and translate informative contrasts into natural-language clarification questions, while Bayesian optimization maintains uncertainty estimation over user intent and selects queries that maximize information gain. After convergence, the inferred STL specification is passed to a formal planner to synthesize a verifiable robot trajectory. Across four simulated and real-world task domains, our approach generally achieves higher task satisfaction and requires fewer clarification rounds than LLM baselines, while helping smaller models close the performance gap against larger reasoning models.

cs.RO · cs.AI · cs.HC

版本更新 · v5arXiv:2608.28469

Distributed Cross-Layer Optimization for Covert Multi-Hop, Multi-Modal Networks: Exponentially Fast Convergence and Robust Tracking

Sirin Chakraborty, Andrea Panebianco, Yuchen Tian, Kevin S Chan, Fikadu Dagefu, Yin Sun, Ness B. Shroff

原文摘要

This paper develops the first distributed cross-layer algorithm for joint congestion control, routing, scheduling, and power control in covert multi-hop, multi-modal wireless networks, where adversarial wardens (Willies) monitor radio modalities via energy detection. The Detection Error Probability (DEP), the probability that a Willie fails to reliably detect ongoing transmissions, is generally non-concave in the transmit powers, making DEP-based covert network optimization challenging. We resolve this by constructing the tightest concave lower bound on the log-DEP, yielding a conservative convex problem that guarantees satisfaction of the original DEP constraints and unifies hard covertness constraints and covertness-utility maximization in a single problem. We develop a Parallel Proximal Alternating Direction Method of Multipliers (PP-ADMM) algorithm for the resulting cross-layer problem and prove global Q-linear convergence, i.e., exponentially fast convergence, to the set of optimal solutions under standard regularity conditions. Numerical results confirm linear convergence and demonstrate robust tracking performance under channel fading and Willie mobility.

cs.IT · eess.SP

版本更新 · v2arXiv:2610.00672

ORBIT-FMIB: Tracking Order-Resolved Epistatic Information Through ESM-2

Maryam Rahimimovassagh, Waldemar Karwowski, Ivan Garibay, Niloofar Yousefi

原文摘要

Protein foundation models support mutation-effect and structural prediction, but predictive performance alone does not reveal which forms of biological interaction information remain accessible through model depth. We ask whether ESM-2 retains higher-order epistatic information as strongly as first- and second-order information across its representation hierarchy, introducing ORBIT-FMIB, a diagnostic framework combining Walsh-based interaction decomposition with subset-conditioned neural dependence estimation. The method is validated on synthetic landscapes with known interaction structure before being applied to the dense four-site GB1 fitness landscape using frozen ESM-2 representations. An initial production run suggested ESM-2 retains higher-order epistatic information less well than lower-order information ($Δ_{\mathrm{HO-LO}}=-0.107$). An independent replication of the complete measurement grid, under matched GPU hardware and identical critic seeds, substantially reduced this contrast ($Δ_{\mathrm{HO-LO}}=-0.017$), and its sign was unstable across otherwise-defensible evaluation-pairing choices applied to the same trained critics ($-0.011$ to $+0.015$). We therefore do not currently have robust evidence that ESM-2 selectively loses higher-order epistatic information, nor that retention is equal across orders; the directional question remains open. The measurement protocol itself, including its documented removal of a positional-subset shortcut in pooled critics, remains validated and is unaffected by this finding. ORBIT-FMIB is offered as a diagnostic framework for probing interaction structure in protein foundation models; this study's own replication result illustrates why such probing requires adequately-powered reproducibility checks before its output is treated as a biological finding.

cs.LG · q-bio.QM

版本更新 · v5arXiv:2510.14716

Approaching the Continuous from the Discrete: an Infinite Tensor Product Construction

Antonio Lorenzin, Fabio Zanasi

原文摘要

Increasingly in recent years, probabilistic computation has been investigated through the lenses of categorical algebra, especially via string diagrammatic calculi. Whereas categories of discrete and Gaussian probabilistic processes have been thoroughly studied, with various axiomatisation results, more expressive classes of continuous probability are less understood, because of the intrinsic difficulty of describing infinite behaviour by algebraic means. In this work, we establish a universal construction that adjoins infinite tensor products, allowing continuous probability to be investigated from discrete settings. Our main result applies this construction to $\mathsf{FinStoch}$, the category of finite sets and stochastic matrices, obtaining a category of locally constant Markov kernels, where the objects are finite sets plus the Cantor space $2^{\mathbb{N}}$. Any probability measure on the reals can be reasoned about in this category. Furthermore, we show how to lift axiomatisation results through the infinite tensor product construction. This way we obtain an axiomatic presentation of continuous probability over countable powers of $2=\lbrace 0,1\rbrace$.

math.CT · cs.LO

版本更新 · v2arXiv:2606.00514

Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation

Hugues Van Assel, Edward De Brouwer, Saeed Saremi, Gabriele Scalia, Aviv Regev

原文摘要

Generative modeling and self-supervised representation learning (SSL) optimize structurally different objectives: generative training rewards distributional fidelity, while SSL rewards semantic coherence. Yet recent work repeatedly finds that SSL features improve generative training, though the mechanism of this synergy remains unclear. Here, we study the benefits of SSL in generative modeling in the framework of one-step generation where the role of representation is explicit: frozen SSL features are used to match generated samples to real data. We use the Sinkhorn divergence in that feature space, providing a tractable surrogate for the Wasserstein distance, the population-level discrepancy approximated by Fréchet-style evaluation metrics (such as FID). We find that this objective becomes highly effective when computed in a semantically structured SSL feature space (a 39$\times$ reduction in ImageNet FID). We trace this behavior primarily to matching estimation: semantic SSL features that suppress nuisance reconstruction details induce a more compact geometry, making distribution matching more tractable. As a consequence, the best training SSL features need not match the features used by the evaluation metric. In particular, we show that using Inception as the feature extractor can improve FID while degrading matching stability and sample quality, revealing a form of metric hacking. Using extensive experiments on ImageNet, we identify which SSL feature families lead to best generation performance and show that matching stability is a quantitative criterion for selecting them. Code is available at https://github.com/Genentech/semantic-transport-generation.

cs.LG · cs.CV

版本更新 · v3arXiv:2610.02036

Global Coherence: When Every Agent Is Right and the Team Is Still Wrong - A Local-to-Global Semantic Foundation for Multi-Agent Collaboration

Xin Heng

原文摘要

AI agents share code, documents, tools, and analyses. No participant sees the whole state, so every step can look right while the combined result is wrong. We call this the global coherence problem. It is a problem of state, not only of intelligence: a stronger model decides better locally, but cannot see what is missing from its context. The Observation-Aliasing Impossibility Theorem gives the exact condition. An agent can always act validly exactly when every world consistent with its context allows a common action. When look-alike worlds need different actions, no reasoning, role, message, or sample can guarantee the right one; with k such worlds whose valid actions are disjoint, the best randomized policy succeeds with probability 1/k. Finding the smallest sufficient context is NP-hard, but refinement finds one and keeps it current as rules change. A second failure survives full information: valid pieces can fail to fit into one world. The same theorem sets the conditions for coherence; sheaves and groupoids are one way to meet them. Models propose, and the harness decides what is valid. Ten studies test it. On TeamBench, teams overspend a shared budget in 5/5 runs; showing them the live count still leaves 4/5, and a harness that owns the budget leaves 0/5. Identity collisions that no pairwise check can see appear in 23 of 45 public alignment networks; split-view agents create them in 9 of 40 merges, and a network check removes all nine. A frontier LLM solves 40/40 revision tasks when it sees the deciding event; with the event hidden, no arm that reasons longer, votes, or splits into roles significantly beats chance, and a companion study replicates this on models from a second provider. In tau2-bench Telecom, after a silent revert, the harness scores 1.00 against 0.07 for call-time policy checks. Refinement keeps a sufficient context at 28% of the cost of sharing every field.

cs.AI

版本更新 · v5arXiv:2409.14591

Non-Cartesian Guarded Recursion with Daggers

Louis Lemonnier

原文摘要

Guarded recursion is a framework allowing for a formalisation of streams in classical (as opposed to concurrent, probabilistic, quantum) programming languages. The latter take their semantics in cartesian closed categories. However, some programming paradigms do not take their semantics in a cartesian setting; this is the case for concurrency, reversible and quantum programming for example. In this paper, we focus on reversible programming through its categorical model in dagger categories, which are categories that contain an involutive operator on morphisms. We show how to introduce the framework of guarded recursion into dagger categories with sufficient structure for data types, also called dagger rig categories. First, given an arbitrary category, we build another category shown to be suitable for guarded recursion in multiple ways, via enrichment and fixed point theorems. We then study the interaction between this construction and the structure of dagger rig categories, aiming for reversible programming. Finally, we show that our construction is suitable as a model of higher-order reversible programming languages, such as symmetric pattern matching, to which we add guarded recursion features.

cs.LO · cs.PL · math.CT

版本更新 · v3arXiv:2508.20054

Between Markov and restriction. Two more monads on categories for relations

Cipriano Junior Cioffo, Fabio Gadducci, Davide Trotta

原文摘要

The study of categories abstracting the structural properties of relations has been extensively developed over the years, resulting in a rich and diverse body of work. In a previous paper we offered a survey providing a modern presentation of these ``categories for relations'' as instances of gs-monoidal categories, showing how they arise as Kleisli categories of suitable symmetric monoidal monads. The end result was a taxonomy that organised numerous related concepts in the literature, including in particular Markov and restriction categories. This paper further enriches the taxonomy: it proposes two categories that are once more instances of gs-monoidal categories, yet more abstract than Markov and restriction categories. They are characterised by an axiomatic notion of mass and domain of an arrow, the latter one of the key ingredients of restriction categories, which generalises the domain of partial functions. The paper then introduces mass and domain preserving monads, proving that the associated Kleisli categories in fact preserve the corresponding equations and that these monads arise naturally for the categories of semiring-weighted relations.

cs.LO · math.CT

版本更新 · v2arXiv:2610.23979

SPELUNKA: A Framework for Finding Unanticipated Associations in Vision-Language Models

Cassandra Parent, Isha Agarwal, Kumail Alhamoud, Charikleia Moraitaki, Rafiya Javed, Walter Gerych, Marzyeh Ghassemi

原文摘要

Vision-Language Models (VLMs) are the backbone of many state-of-the-art multimodal systems, but often encode spurious and harmful associations from their training data. While prior work focuses on removing known biases from VLMs, methods for discovering unanticipated associations for retrieval tasks remain underexplored. We introduce SPELUNKA, an automated, inference-time framework for finding unanticipated distributional biases for retrieval tasks in VLMs without pre-specified labeled subgroups, inference-time human supervision, or model fine-tuning. Given a concept of interest, SPELUNKA generates captions for related images, extracts relevant entities from captions, and selects semantically meaningful associations. A frequency-based detection rule then identifies spurious associations by measuring over- or under-representation of these attributes in a VLM's top-ranked outputs relative to their full dataset distribution. We evaluate SPELUNKA across four datasets, and find that it 1) successfully recovers both synthetic and naturally occurring spurious correlations, 2) achieves an average AUROC of 0.93 across four datasets in identifying images strongly associated with a query, and 3) outperforms baselines in finding features that are strongly associated with a given query.

cs.CV · cs.LG

版本更新 · v3arXiv:2603.04530

Complete Diagrammatic Axiomatisations of Relative Entropy

Ralph Sarkis, Fabio Zanasi

原文摘要

Relative entropy is a fundamental class of distances between probability distributions, with widespread applications in probability theory, statistics, and machine learning. In this work, we study relative entropy from a categorical perspective, viewing it as a quantitative enrichment of categories of stochastic matrices. We consider two natural monoidal structures on stochastic matrices, given by the Kronecker product and the direct sum. Our main results are complete axiomatisations of Kullback-Leibler divergence and, more generally, of Rényi divergences of arbitrary order, for each such structure. Our axiomatic theories are formulated within the framework of quantitative monoidal algebra, using a graphical language of string diagrams enriched with quantitative equations.

cs.LO · cs.IT · math.CT

版本更新 · v2arXiv:2610.21034

Can Autonomous Vehicles Keep Their Cool? A Survey of Thermal Side-Channel and Perception Attacks

Harsh Aaryan, Ce Zhou

原文摘要

Autonomous vehicles (AVs) couple safety-critical perception to thermally constrained compute. Physical adversaries can spoof thermal infrared (IR) sensors used for night driving, while unprivileged software co-tenants can fingerprint perception workloads from thermal, dynamic voltage and frequency scaling (DVFS), and thermal event interrupt (TEI) telemetry required for package safety. These paths differ in mechanism and privilege, but both exploit interfaces that AV stacks cannot disable without compromising Safety of the Intended Functionality (SOTIF). Existing microarchitectural and CPS surveys cover cache timing, adversarial ML, and camera or LiDAR spoofing; none frames physical thermal IR attacks and unprivileged silicon thermal telemetry as one residual-risk class. This survey systematizes thirteen works into thermal perception integrity, telemetry leakage, and model-information extraction, comparing them by privilege, timescale, co-tenancy, deployability, and AV relevance while mapping defenses to residual risk. A commodity proxy supports the software co-tenant branch only; physical IR evidence comes from cited literature. We identify open problems in on-target automotive evaluation, fusion trust under IR spoofing, chiplet thermal coupling, capability-based telemetry, and standards-ready threat analysis, motivating co-design across sensors, operating systems, silicon, and automotive standards.

cs.CR

版本更新 · v3arXiv:2605.00812

Univalence without function extensionality

Evan Cavallo, Jonas Höfer

原文摘要

It is a well-known theorem of homotopy type theory, originally due to Voevodsky, that function extensionality holds inside any univalent universe. We consider a weaker variant of the univalence axiom, asserting that the wild category formed by the universe is univalent, which we call categorical univalence. We show that categorical univalence does not imply function extensionality by an analysis of Von Glehn's polynomial model construction, which produces models of Martin-Löf type theory that always refute function extensionality. We find in particular that when the base model has a univalent universe, its polynomial model has a universe that is categorically univalent but lacks function extensionality.

cs.LO · math.LO

版本更新 · v2arXiv:2602.02457

MetaCLASS: Metacognitive Coaching for Learning with Adaptive Self-regulation Support

Naiming Liu, Richard Baraniuk, Shashank Sonkar

原文摘要

Large language models can generate fluent explanations, but effective tutoring requires supporting the learner's thought process, not just delivering content. Metacognitive tutoring targets this gap by prompting planning, monitoring, debugging, and evaluation, and, crucially, deciding when to be active versus minimally present, based on learner signals and trajectory. We introduce MetaCLASS, a learning-science grounded framework that formulates metacognitive tutoring as move selection over 11 interpretable actions aligned to self-regulated learning (SRL) processes. MetaCLASS uses a two-phase procedure that first plans a pedagogical trajectory conditioned on learner profiles (calibration, help-seeking) and then generates natural dialogue consistent with that plan. This process yields 1,015 conversations spanning 7,711 turns, each annotated with turn-level metacognitive labels and supported by comprehensive validation analyses. We benchmark nine open-source LLMs on predicting the next coach move given a question and dialogue context. The best model achieves only 43.2% accuracy in coach move prediction, and models exhibit compulsive intervention bias: in turns where effective metacognitive tutoring requires silence (41.7% of cases), models predict "no intervention'' only 6.6% of the time, while severely over-predicting high-intervention moves. These results show that traditional content-based tutoring ability does not translate to metacognitive tutoring competence, positioning MetaCLASS as a testbed for developing tutors that promote SRL.

cs.CY

版本更新 · v3arXiv:2601.00312

Quantifier Elimination Meets Treewidth

Hao Wu, Jiyu Zhu, Amir Kafshdar Goharshady, Jie An, Bican Xia, Naijun Zhan

原文摘要

In this paper, we address the complexity barrier inherent in Fourier-Motzkin elimination (FME) and cylindrical algebraic decomposition (CAD) when eliminating a block of (existential) quantifiers. To mitigate this, we propose exploiting structural sparsity in the variable dependency graph of quantified formulas. Utilizing tools from parameterized algorithms, we investigate the role of treewidth, a parameter that measures the graph's tree-likeness, in the process of quantifier elimination. A novel dynamic programming framework, structured over a tree decomposition of the dependency graph, is developed for applying FME and CAD, and is also extensible to general quantifier elimination procedures. Crucially, we prove that when the treewidth is a constant, the framework achieves a significant exponential complexity improvement for both FME and CAD, reducing the worst-case complexity bound from doubly exponential to single exponential. Preliminary experiments on sparse linear real arithmetic (LRA) and nonlinear real arithmetic (NRA) benchmarks confirm that our algorithm outperforms the existing popular heuristic-based approaches on instances exhibiting low treewidth.

cs.LO · cs.CC · cs.SC

版本更新 · v2arXiv:2610.10942

StoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents

Daksh Raghuvanshi, Ved Vedere, Yifan Wang

原文摘要

Reinforcement learning environments are now a primary lever for improving large language model (LLM) capabilities in post-training, yet most agentic benchmarks remain static: the world moves only when the agent acts, the reward is a terminal verdict, and the pass bar is set arbitrarily. We introduce StoreBench, a live-commerce environment in which an agent runs a mid-size online apparel store on a production-grade commerce backend, testing long-horizon planning and economic judgment under uncertainty. Customers order around the clock, suppliers reprice and fail, and market shocks arrive with partial or no warning. The agent acts through the same 29 merchant tools a human operator would use, under a windowed operation budget that makes simulated time a function of actions taken, so model latency cannot influence simulated time. Pass thresholds are calibrated against scripted anchor policies, the reward is hardened against a catalogue of reward hacks, and every episode replays identically given a sequence of actions. We evaluate seven frontier LLMs on 11 scenarios of 30 to 45 days and a full simulated year, over three world seeds at matched reasoning effort. No model matches the scripted smart-triage policy on average: the best, DeepSeek-V4-Pro, passes 49% of task-seed cells against the heuristic's 97%. Human experts working through the same tools and budgets outscore every model (mean composite 0.708 vs. 0.700). Over a full simulated year under the Claude Code harness, most models show dramatic performance improvement. In a GRPO post-training run, Qwen3.5-27B trained on only five disjoint tasks raises its mean composite on the held-out evaluation tasks from 0.136 to 0.373. We release five example training-split tasks, ten sample trajectories, and the scoring and verification tooling; the full environment and evaluation suite are withheld to keep the benchmark uncontaminated.

cs.AI · cs.CL · cs.LG

版本更新 · v2arXiv:2605.15999

Trajectory and Morphology Planning for Morphing Quadrotors in Ultra-Narrow Passages using Limited Perception

Harsh Modi, Xiao Liang, Minghui Zheng

原文摘要

This paper presents an online trajectory and morphology planning framework for morphing quadrotors to traverse passages narrower than their unfolded width using only a 2D LiDAR for obstacle sensing. Fixed-frame vehicles cannot pass through such gaps, and classical artificial potential field (APF) based obstacle costs seal them off for planners as well, because the repulsive cost grows sharply inside a tight gap. The core enabler of our framework is a novel cost reduction factor, computed in closed form from the LiDAR data, that cancels the obstacle cost along the medial axis of a narrow passage. A true opening thus becomes a low-cost corridor, while the full repulsive cost is retained everywhere else. The cost reduction factor is embedded at every prediction node of an acados-based nonlinear MPC, which jointly plans the trajectory, yaw, and fold angle of the platform. A user-specified minimum-width limit ensures that the cost reduction factor only opens the corridors that the platform can actually pass. Gazebo/PX4 simulations and hardware experiments on the MorphoCopter demonstrate autonomous folding and unfolding through curved, inclined, and cluttered passages narrower than the unfolded width, where the standard repulsive cost fails to pass safely in most of the trials. The implementation code is available at \href{https://github.com/harshjmodi1996/morphocopter_mpc}{\textcolor{blue}{Github}} and a short video about the paper is available at \href{https://zh.engr.tamu.edu/wp-content/uploads/sites/310/2026/10/Morphocopter_planning_final.mp4}{\textcolor{blue}{\textbf{video link}}}.

cs.RO · eess.SY

版本更新 · v3arXiv:2507.01216

Eco-MobiLLM: Efficient LLM Fine-Tuning on the Mobile Device via Server Assisted Side-Tuning

Xingke Yang, Liang Li, Zhiyi Wan, Sicong Li, Xiaoqi Qi, Jiang Liu, Tomoaki Ohtsuki, Xin Fu 等 9 位作者

原文摘要

There is a huge gap between numerous intriguing applications fostered by on-device large language model (LLM) fine-tuning (FT) from fresh mobile data and the limited resources of a mobile device. While existing server-assisted methods (e.g., split learning or side-tuning) may enable LLM FT on the local mobile device, they suffer from heavy communication burdens of activation transmissions. In addition, their multiple on-device forward passes over the same samples across training epochs lead to substantial iterative computation on the mobile device. To address those issues, we develop Eco-MobiLLM, an efficient LLM FT method which can be deployed on the mobile device via server-assisted side-tuning. To reduce communication cost, Eco-MobiLLM develops an activation shortcut that transmits only the tokens involved in the loss calculation instead of full activation matrices to guide the side network tuning. Besides, to improve computing efficiency and further accelerate FT convergence, Eco-MobiLLM introduces a novel two-stage training paradigm, which allows the server to reuse historical activations and saves the mobile device from repeatedly computing forward passes for the recurring data samples. Extensive experimental results demonstrate Eco-MobiLLM's superiority.

cs.LG · cs.CR

版本更新 · v2arXiv:2608.04125

Concentration from Product Moments via an Additional Element of Randomness

Michael Saks, Aravind Srinivasan, Renata Valieva

原文摘要

The standard method of exponential moments for proving concentration bounds can often be replaced by an argument based on elementary symmetric polynomials. We introduce an additional element of randomness into this framework, which reduces the problem to bounding product moments over a uniformly sampled set of indices. We show that this approach gives useful bounds in three settings. For read-$Δ$ families under limited independence, we obtain bounds governed by the degrees of randomly induced dependency subgraphs, improving the dependence on worst-case degrees. For random linear hashing over arbitrary finite fields with (semi-)random inputs, we derive fixed-bin and maximum-load bounds by controlling the rank defect of random tuples of input keys. Finally, for stochastic processes, we show how decay of product moments yields concentration bounds, recovering the spectral and mixing-time scales for finite-state Markov chains.

cs.DS