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

+1352新增论文
+1083其中 AI 相关
+143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 15:04各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 15:15 — 2026-11-19 15:15(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:2026-11-19 06:59最近发现新增版本:2026-11-19 15:04库内论文最新更新时间:2026-11-19 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。

27,409 已收录论文22,787 AI 相关8,342 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 8,342 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v2arXiv:2609.10740

Governing AI Research Through Peer Review: A Mixed-Methods Study of the Longitudinal Effects of Ethics Flags Across Resubmissions

Kento Nishi, Alec Laprevotte, Isaiah Bullock, Mfoniso Andrew

原文摘要

Selective AI conferences have recently begun enforcing ethics flags and related review requirements, with the goal being to steer research towards safer and more responsible practices before publication. But do these requirements actually steer research as intended? In this paper, we show that authors more often revise how projects are presented following ethics flags than redirect their underlying research agendas. We first study the longitudinal effects of ethics flags by following rejected and withdrawn ICLR submissions with ethics flags into later public resubmissions, tracking manuscript changes after the ICLR review ends, when the original reviewers no longer oversee the project. We qualitatively code these resubmissions into five categories based on what changed after review and find that in 83% of 446 cases, authors leave the flagged concern unaddressed or revise the paper without changing the implicated methods or procedures. Then, we ask: if authors rarely change the research in response to ethics flags, what do they change instead? To answer this, we manually read reviews and rebuttals from 25 cases and directly interview authors about their rebuttal processes and resubmission decisions. We find that authors often concede concerns during rebuttal when reviewers can update their assessments, but drop those concessions after rejection when they do not regard the criticism as a sound reason to change the research. Interview participants describe publication changes as separate from changes to research direction, calling review an "editorial process" that shapes "what stories get seen" and, in another case, saying peer reviews are "mostly to filter out papers." Authors more readily change what they publish than what they study or build; we therefore recommend policy changes, especially disclosure of prior ethics flags upon resubmission so accountability carries over.

cs.CY

版本更新 · v2arXiv:2606.15123

CVE-Conditioned Exploit Generation with LLMs: A Data-Centric Study of Benchmarking and Fine-Tuning

Yiwei Chen, Lichi Li, Kai Cheung, Vinny Parla, Ganesh Sundaram

原文摘要

We study the task of CVE-conditioned exploit generation, where a model drafts proof-of-concept (PoC) exploits given software vulnerability context. We adopt a data-centric approach, constructing a high-quality dataset via multi-stage preprocessing and introducing a scalable evaluation framework with LLM-as-judge and fine-grained rubrics. Under this unified setup, we benchmark 17 large language models across 8 evaluation criteria, providing systematic insights into their zero-shot capabilities. We further show that a compact 8B open-weight model, when fine-tuned on curated data, achieves over 42.5% improvement in exploit quality and rivals some proprietary models when combined with simple test-time rejection strategies. Our results highlight the importance of data quality, structured supervision, and evaluation design for reliable exploit generation, suggesting that these factors can be as critical as model scale in adapting LLMs to cybersecurity tasks.

cs.CR · cs.LG

版本更新 · v2arXiv:2609.24492

Identity-Consistent Analysis of Long-Shot Windsurfing Video: A Domain-Specific Offline Tracking System

Bertil Braun, Felix Muehlenberend

原文摘要

Long-shot windsurfing video combines small targets, large camera pans, prolonged overlaps, and rapidly changing backgrounds. The desired output is not a generic MOT trace but a separate, stable rider-relative video for each surfer; one false identity merge can invalidate an otherwise useful result. We present an offline analysis system that detects surfers, forms conservative local tracklets, links them globally with camera-compensated motion and a foreground-masked sail-color descriptor, and uses two pose keypoints on the rig to drive a rider-relative virtual camera. The tracking stage is evaluated on 21 manually reconstructed development videos containing 41,004 retained observations. On this fixed-observation protocol, the production system achieves 0.957 pairwise precision, 0.918 recall, and 0.937 F1, compared with 0.792 F1 for OC-SORT and 0.828 for BoT-SORT. Compared with OC-SORT, it reduces fragmentation excess from 845 to 42, but nine of its 95 output tracks mix rider identities and these errors affect seven of the 21 videos.

cs.CV

版本更新 · v2arXiv:2609.04523

MaxKernel: Agentic Kernel Generation for TPUs

Shangkun Wang, Nina Cai, Charles Hoong, Julian Walker, Gerson Kroiz, George Vanica, Deepak Patil, Andi Gavrilescu 等 10 位作者

原文摘要

Designing and authoring high-performance custom kernels for accelerators is a complex task that requires deep hardware-level expertise. Large Language Models (LLM) can be leveraged together with real-time compiler feedback to build agentic systems for kernel generation. In this work, we present MaxKernel, a multi-agent system that implements three distinct paradigms for TPU kernel development: (1) a Human-in-the-Loop (HITL) agent for collaborative, step-by-step design; (2) an Autonomous (Auto) agent that executes a fully automated, metric/trace-driven optimization loop; and (3) a Graph-Based Autonomous Search that scales the Auto agent for global exploration of the design space. All three paradigms leverage a shared pool of specialized sub-agents to handle planning, implementation, self-debugging, testing, and hardware profiling. We evaluate MaxKernel on JaxBench, a comprehensive suite of 50 diverse kernel tasks for TPUs, alongside complex, real-world workloads from state-of-the-art open-source models. We demonstrate that MaxKernel consistently generates highly optimized implementations, matching expert hand-tuned baselines and delivering significant performance across the benchmark. Our agent is open-sourced and available https://github.com/AI-Hypercomputer/accelerator-agents/tree/main/MaxKernel.

cs.AI · cs.PF · cs.PL

版本更新 · v2arXiv:2607.20345

Closing the Lab-to-Store Gap: A Data-Efficient Post-Training and Experience-Driven Learning VLA Framework for Retail Humanoids

Roger Sala Sisó, Tiago Silvério, Jakob Sand, Tran Nguyen Le

原文摘要

Closing the gap between benchmark performance and reliable real-world operation remains a central challenge for Vision-Language-Action (VLA) humanoid robots, which must handle execution errors, distribution shifts, and environmental variability. This paper presents DEED (Data-Efficient Post-Training and Experience-Driven Learning), a systems-level approach evaluated on a supermarket chip-restocking task using a Unitree G1-Edu humanoid robot and the GR00T N1.6 foundation model. DEED comprises three key components: (1) a data-efficient post-training pipeline with control-frequency alignment, data curation, task-relevant visual highlighting, and reduced VLA dependence; (2) a real-world study of experience-driven refinement, adapted from RECAP via a text-based advantage prefix and a vision-language value function; and (3) a latent-space analysis tool for studying in- and out-of-distribution behavior. Our results suggest that bridging the lab-to-store gap is primarily a systems integration challenge rather than an architectural one: careful data design and targeted post-training can transform a policy that fails under naive fine-tuning into a competent real-world system using only a single GPU.

cs.RO · cs.AI

版本更新 · v3arXiv:2609.14892

An explicit solution of the five-expert prediction PDE and the exact optimality set of COMB

Jeff Calder, Nadejda Drenska

原文摘要

In this paper, we derive an explicit solution of the stationary prediction with expert advice PDE for five experts. The formula is given in three regions. In the first two regions, it is the four-expert solution plus a single integral with an elementary positive density. In the third region, it is a finite sum of hyperbolic products whose coefficients are determined by one scalar quadrature. Our formula establishes that the rank ordered adversary $(1,0,1,0,0)$ achieves the Hamiltonian maximum in the PDE everywhere in the ordered sector, while the COMB strategy $(1,0,1,0,1)$ is optimal only on a lower dimensional subset of the sector (where $x_1=x_2$ and $x_3=x_4$). The verification of the Hamiltonian inequalities is a tedious task, part of which is completed with a computer assisted proof. The verification reduces to 21 scalar inequalities, which we prove using 147 exact rational Bernstein polynomial certificates. The exact certificates and their independent arithmetic checks are included in a supplement to this paper, and a Lean 4 formalization machine-checks the verification and both main theorems, apart from the viscosity characterization.

math.AP · cs.GT · cs.LG · math.OC

版本更新 · v5arXiv:2607.22877

Towards Trustworthy Physical Intelligence: From Theory to Practice Across Life Cycle

Yang Wang, Hongxuan Liu, Xinghui Xu, Arjun Menon, Xiaoran Cai, Yunyu He, Alex Tarvo, Jingzong Zhou 等 43 位作者

原文摘要

Physical intelligence refers to intelligence systems that understand, reason about and act in accordance with the physical world and its underlying laws, dynamics, and constraints. Unlike conventional AI systems, physical intelligence interacts continuously with uncertain physical environments, and its actions produce consequences that are physically irreversible. As existing trustworthy AI frameworks have been developed primarily for digital AI systems, they do not fully capture the distinctive challenges of Physical Intelligence, such as physical safety, cyber-physical security, and physical manufacturing process. To address this gap, our paper develop a foundation for understanding, operationalizing, and governing trustworthy physical intelligence. First, we characterize the fundamental capabilities of physical intelligence. Second, we investigate the role of physical laws and principles in AI and analyze the associated challenges of physical intelligence. Third, we provide a unified structure of the end-to-end physical intelligence life cycle across five core stages and introduce the Trustworthy Physical Intelligence Operationalization (T-PAIO) framework. Fourth, we formulate the Trustworthy Physical Intelligence (T-PAI) Principles as a theoretical framework that synthesizes key trustworthiness dimensions and establishes a conceptual foundation for the governance of physical intelligence systems.

cs.AI · cs.HC · cs.RO

版本更新 · v2arXiv:2610.35933

Deterministic Causal Quantization with Bounded Error: Adaptive Reconstruction and Entropy bounds

Rama Cont, Massoud Heidari

原文摘要

We study compression of real-valued stationary sources under a deterministic error bound: every sample must be reconstructed within a prescribed tolerance $\varepsilon$ on every input sequence. Reconstructions are causal, depending only on present and past inputs. Rates are measured by the entropy of the quantizer output, which block entropy coding can approach, and compared with the minimum rate of unrestricted block quantization under the same error constraint. A uniform scalar quantizer with cells of width $2\varepsilon$ is within one bit per sample of this minimum whenever finite-entropy scalar quantization is possible, without density, independence, or mixing assumptions. Under entropy and Sobolev regularity conditions, the gap is at most $2\mathcal{J}\varepsilon^2/(π^2\ln 2)$, where $\mathcal{J}$ is the asymptotic Fisher information per sample. Thus the cost of causal reconstruction vanishes at a quadratic rate as the tolerance decreases. A uniform grid, however, cannot adapt to the source. We construct an adaptive quantizer whose encoder and decoder maintain a common finite set of reconstruction values, updated from the transmitted symbols alone; suitable initialization reproduces any uniform grid. When its initial values are at least $\varepsilon$ apart, its rate is within two bits per sample of the minimum for every such source. For sources uniform within separated intervals of width $2\varepsilon$, storing the interval centers attains the minimum and its Shannon lower bound. Such configurations can outperform every uniform grid of the same cell width: over sources with well-separated intervals, the best uniform grid's worst-case excess rate is $1/(2\ln 2)\approx 0.72$ bit per sample.

cs.IT · math.PR

版本更新 · v2arXiv:2603.17022

Contingency-Aware Planning via Certified Neural Hamilton-Jacobi Reachability

Kasidit Muenprasitivej, Derya Aksaray

原文摘要

Hamilton-Jacobi (HJ) reachability provides formal safety guarantees for dynamical systems, but repeatedly solving the HJ partial differential equation in changing environments limits its use in real-time planning. This paper introduces learning-based reachability and an online safety certification that together enable real-time contingency-aware planning in unknown environments with probabilistic safety guarantees. We use Fourier Neural Operator (FNO) to approximate the HJ solution operator under varying obstacle configurations. To certify the learned reach-avoid set, we recast robust scenario optimization as multiple hypothesis testings over its sublevel sets, which yields a simultaneous guarantee across candidate levels and recovers the largest certifiable volume at the prescribed safety level. Within this certified set, the induced recovery policy is guaranteed to return the system to a safe region in finite time under any admissible disturbance. Numerical results show that the learning and certification pipeline updates reach-avoid sets at real-time rates and is demonstrated on youBot simulation.

cs.RO · eess.SY

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