跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+64已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 21:56各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 22:17 — 2026-11-16 22:17(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 21:56库内论文最新更新时间:2026-11-14 02:59

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

23,827 已收录论文19,941 AI 相关6,922 有修订112 HF 社区发现

浏览论文库

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

找到 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.11732

Particle Filtering with Generative Trajectory Models for State Estimation and Control

Lukas Lao Beyer, Samvit Das, Sertac Karaman

原文摘要

Generative models can support both state estimation and control in robotics. For control, a common approach is to use the model as a policy that directly samples actions conditioned on observation histories. However, models that jointly represent states, actions, and observations can also predict how the robot state and its environment evolve. We investigate whether these predictions can improve state estimation and control through a change in inference procedure, without modifying the pretrained model. To this end, we use particle filtering to maintain competing hypotheses about state histories. A single pretrained diffusion model generates these hypotheses along with their predicted observations and associated action proposals. As new measurements arrive, particles are reweighted according to how well their predicted observations match the measurements. While particle filtering conventionally uses these weights only for state estimation, we also use them to guide action selection, favoring proposals associated with hypotheses that better explain the observations. Simulation experiments in partially observed navigation and vision-based manipulation demonstrate improvements in both state estimation and task performance compared to action generation without filtering, using the same pretrained model and no additional test-time information.

cs.RO · cs.LG

版本更新 · v2arXiv:2610.29153

Cycle structure of best-response dynamics in random bimatrix games

Georgios Nikolaos Karelas, Gábor Lugosi, Rui-Ray Zhang

原文摘要

We study the best-response dynamics in games with random payoffs. We consider two-player bimatrix games, with $n$ strategies each. We assume that payoffs come from a continuous distribution, and study the best-response dynamics of these games, after imposing some structure on their payoff matrices. In particular, we focus on symmetric games, antisymmetric games, common-interest games, zero-sum games, and games with independent payoffs. When two players take turns in playing the best response to the opponent's action, they eventually end up cycling through the same sequence of actions. The main focus of the paper is the cycle structure of large random games. In particular, we study the number of cycles, the number of cycles of a certain length, the length of the longest cycle, and related quantities. We show that the structure of the game has an important impact on the typical cycle structure. Our arguments are based on a representation of the best-response dynamics of these games as directed bipartite graphs, and on the cycle structure that arises in them.

cs.GT

版本更新 · v2arXiv:2610.16121

Double circulant LCD codes over $\mathbb{F}_2+u\mathbb{F}_2$ and their related binary LCD codes

Xingxing Xu, Bo Wu, Jon-Lark Kim

原文摘要

Linear complementary dual (LCD) codes are linear codes that intersect their dual trivially. We study double circulant (Euclidean) LCD codes over the finite chain ring $R=\mathbb F_2+u\mathbb F_2$, where $u^2=0$. Using the Chinese Remainder Theorem and the factorization of $x^n-1$, we derive an explicit enumeration formula, with a separate treatment of the constituent corresponding to $x-1$, which is not obtained by a formal specialization of the previously known counting formula over $\mathbb F_q[u]/(u^k)$. Assuming Artin's primitive root conjecture for $2$, we show that the binary Gray images contain an asymptotically good family of rate $1/2$ which attains the asymptotic Gilbert--Varshamov bound, i.e., whose relative distance can approach $H_2^{-1}(1/2)$ from below. More importantly from the constructive viewpoint, by combining Gray images with a known extension construction, we obtain a binary LCD code with previously unknown parameters $[29,15,7]$ and construct two explicit permutation-inequivalent binary LCD codes with parameters $[45,23,9]$ and nine binary LCD codes with the best known parameters.

cs.IT · math.RA

版本更新 · v4arXiv:2307.06090

Can Large Language Models Aid in Annotating Speech Emotional Data? Uncovering New Frontiers

Siddique Latif, Muhammad Usama, Mohammad Ibrahim Malik, Björn W. Schuller

原文摘要

Despite recent advancements in speech emotion recognition (SER) models, state-of-the-art deep learning (DL) approaches face the challenge of the limited availability of annotated data. Large language models (LLMs) have revolutionised our understanding of natural language, introducing emergent properties that broaden comprehension in language, speech, and vision. This paper examines the potential of LLMs to annotate abundant speech data, aiming to enhance the state-of-the-art in SER. We evaluate this capability across various settings using publicly available speech emotion classification datasets. Leveraging ChatGPT, we experimentally demonstrate the promising role of LLMs in speech emotion data annotation. Our evaluation encompasses single-shot and few-shots scenarios, revealing performance variability in SER. Notably, we achieve improved results through data augmentation, incorporating ChatGPT-annotated samples into existing datasets. Our work uncovers new frontiers in speech emotion classification, highlighting the increasing significance of LLMs in this field moving forward.

cs.SD · eess.AS

版本更新 · v3arXiv:2606.16933

A Unified Taxonomy and Evaluation Framework for Distributional Shifts in Reinforcement Learning

Ardianto Wibowo, Paulo E Santos, Amer Baghdadi, Matthew Stephenson, Karl Sammut, Jean-Philippe Diguet

原文摘要

Distributional shift in reinforcement learning (RL) is defined inconsistently across the literature, and it is studied alongside out-of-distribution (OOD) generalization and non-stationarity without a clear account of how the three terms are related. Methods are also often described as robust after evaluation under only a few particular changes, leaving the scope of such claims unclear. We develop a unified taxonomy that brings the three terms under one definition of distributional shift. We factorize the joint distribution of a one-step interaction into five components, each produced by its own generating function: initial-state distribution, observation mechanism, policy implementation (distinct from the policy being optimized), transition dynamics, and reward mechanism. A shift is specified by what changes (the changed components) and when it changes (the interaction regime: OOD, non-stationary, or combined), while changes in interaction data and performance are treated as observed effects. We complement the taxonomy with an evaluation framework that measures immediate generalization and subsequent adaptation, summarizing adaptation in a shift adaptation score (SAS). Published benchmark results, controlled Gridworld experiments with DQN, A2C, and PPO, and a mapping of selected studies show that method responses and rankings vary with the shifted component, and that existing evaluations cover only some components. Robustness claims should therefore be bounded by the components and regimes evaluated, since strong performance under one shift does not establish robustness under others. Identifying an unknown component-level source from observed interaction data remains a direction for future research.

cs.LG · cs.AI

新论文 · v1arXiv:2611.11727

State Media at Retrieval Time: A Large-Scale Audit of Russian State-Aligned Sources in AI Chatbot Responses

Laura Kurek, Elijah Covert, Rafael I Bonilla, Eric Gilbert, Ceren Budak

原文摘要

The Pravda Network is a Russian state-aligned media aggregator, with over 110 websites and more than 15 million articles published since 2023. Given its prolific and repetitive output, emerging scholarship argues that the Pravda Network was built to influence AI systems. We conduct a large-scale audit of leading AI chatbots to understand: (1) the retrieval rates of Pravda Network articles, (2) the conditions of retrieval, and (3) whether chatbot responses affirm or caveat this content. We build a 10,000 prompt corpus from sampled Pravda Network headlines varied along two dimensions (headline rewording and user skepticism) and query 11 AI chatbots via the web interface (n=104,997 completed responses). Overall, we find susceptibility to Pravda Network retrieval to be infrequent---appearing in 7.3% of responses---and highly platform dependent---with three chatbots responsible for 94% of retrievals (You.com, Claude, and Copilot). Among the frontier models, Claude is an outlier: ChatGPT, Gemini, and Meta AI retrieved no Pravda Network articles, likely indicative of a domain-level filtering policy. All 11 chatbots, however, retrieved other Russian state-aligned media to some degree (median=13.56% of responses). When Pravda Network articles are surfaced, caveat rates vary widely by platform (from 5.3% to 76.2%), with You.com providing the fewest caveats. We also identify the tactic of headline washing: where 9.92% of sampled Pravda Network headlines attribute their reporting to other, often more credible, media outlets, while the articles themselves are republished from Russian state-aligned media. We discuss headline washing's potential to launder state media as independent reporting. With this audit, we provide a systematic analysis of AI chatbots' susceptibility to Russia's latest attempt to manipulate the information environment.

cs.AI

新论文 · v1arXiv:2611.11726

The Dark Matter of Clinical Data: An Identification Limit on Disentangling Physiology from Care Process in electronic health records

Mohammad Shahin, Krittaphas Chaisutyakorn, Dimitrios Proios, David Restrepo, Vishala Mishra, Boya Zhang, Aadarsh Sivaraman, Sparsh Roy 等 14 位作者

原文摘要

Representations learned from electronic health record (EHR) data encode patient physiology together with the clinical process that decides what is measured, when, and for whom. We formalize the data-generating process with latent physiology, ordering intent, laboratory values that exist only when measured, a learned representation, and clinical environments, and analyze two strategies for undoing this entanglement. First, no division of the information carried by laboratory "value" and "ordering" channels is identified from a single dataset: when ordering depends on the analyte, its distribution among untested patients is not recoverable, and a sentinel code for the undefined recorded value makes it carry all the entropy of the ordering indicator, fixing partial information decomposition (PID) for every redundancy measure satisfying the Williams-Beer axioms and invariant under injective re-encoding. Second, cross-site invariance of representation-conditional outcomes is a falsifiable implication of biological invariance taken jointly with exclusion and representation-sufficiency conditions, but not an identification strategy: we construct observationally equivalent models that disagree about biological invariance, whether the invariance test fails or passes. For binary physiology this happens exactly when case mix differs, the representation is lossy, and physiology affects the outcome. A worked example yields a 9.6-percentage-point cross-site gap under an unchanged biological mechanism. Tests performed for every patient remove the ordering gate, and measured tests can restore identification: biological invariance is identified when a test exactly summarizes outcome-relevant physiology, or, for binary physiology, when two tests with independent errors are available at sites with different case mix. Cross-site analyses should be reported as tests of a stated joint hypothesis.

cs.LG · stat.ME

新论文 · v1arXiv:2611.11725

The Value of Not Knowing: How Fresh Eyes through Naive LLMs Fuel Creativity

David B. D'Ambrosio, Alon Albalak, Joel Lehman, Kenneth O. Stanley

原文摘要

Many major scientific advances come from approaching a problem with a new or novel perspective. While large language models (LLMs) with internet-scale knowledge seem poised to take such perspectives, their consistent generation remains elusive. Instead, models are drawn to dominant views and preexisting, in-field bias. To explore the potential of fresh eyes to increase creativity, this paper proposes naive LLMs, models that are made intentionally ignorant of a specific topic. Through deprivation in training or intentional forgetting, naive models are unburdened by existing dogma, allowing them to be free to make new associations and conjectures. These naive models can then be paired with a stronger mentor model that can refine their unique perspectives into concrete proposals. For the 1B and 7B models tested in this paper, naive models consistently produce seed ideas that are more novel and useful than baseline counterparts, and mentor refinement improves the ideas even further. Thus, contrary to the prevailing tradition of scaling up training data, we demonstrate a case where less information is actually more powerful, in particular when the aim is to discover genuinely outside-the-box solutions.

cs.AI · cs.CL · cs.LG

新论文 · v1arXiv:2611.11724

Explaining and interrupting collective misalignment in language model systems

Edoardo Chidichimo

原文摘要

In collectives, language model agents can exchange individually innocuous messages that together support a policy violation. Understanding and preventing collective misalignment requires answering the question of which messages sufficiently influenced and necessarily enabled the violation. Collective Dependence Analysis (CDA) operationalises necessity and sufficiency to explain decisions and find the fewest removals interrupting support within tested combinations. Tests covered constructed violations, unscripted agent conversations, and recorded interactions, with selected message removals reducing violations from 93% to 6% in controlled cases. Using O(N) model evaluations for N messages, CDA achieves the same violation reduction with half the deletions of a frontier LLM judge given the transcript and asked for all supporting messages in eligible operational cases. CDA also proposes the mechanism through which the collective misalignment emerged. Nonetheless, complete explanations remain difficult on unfamiliar tasks and some removals can inadvertently disrupt correct decisions. CDA unifies explanations of collective misalignment with experimentally tested interventions.

cs.CL · cs.AI

新论文 · v1arXiv:2611.11721

Decalage: Uncovering the Gap Between Model-Generated Reasoning and Actual Code Implementation in Small Language Models

Saif Uddin Mahmud, Afsana Tasnim, Ahmed Ryan, Md Rayhanur Rahman

原文摘要

Agentic code generation often asks a model to explain its reasoning before it writes code, and a common way to make such a workflow safer is to add a security instruction to the prompt. We test what that instruction does in small language models, which are attractive because they run locally and cheaply. Four open code models of 1.5B to 3B parameters generate C++ from 166 sections of eleven public requirements documents, once with a general prompt and once with a secure prompt. The secure prompt more than doubles the share of reasoning about validation, resource handling and threats, and we find no evidence that the rise is larger for requirements with security content. The code changes only in part. Among functions with a body and reasoning, the share with a check that our lexical test recognises rises from 23% to 39%, but more than a quarter of the functions remain stubs, compile rates stay low, and half or more of the functions whose reasoning mentions a check contain no such check. Two rounds of compiler-feedback repair leave more than 80% of sections unusable, and neither cppcheck nor an exploratory ESBMC run separates the prompts on the usable code. A hand check by two annotators supports the stub measure and the direction of the reasoning result. For small models, a security instruction changes the reasoning broadly but the code only in part, so the reasoning should be checked against the code rather than trusted.

cs.SE

新论文 · v1arXiv:2611.11720

ShadowBench-MCP: Measuring Shadow Invocations in MCP-Style Tool Routing

Eyhab Al-Masri, Wenjun Yang

原文摘要

LLM agents increasingly act as routers for tools, APIs, and software-supply-chain workflows, making an execution path - rather than generated text alone - a security-relevant model output. We study shadow invocation: a task-preserving request variant that causes an LLM router to select a riskier execution path, potentially skipping validation, provenance, staging, redaction, or audit controls even though the request does not ask for a malicious action. We introduce ShadowBench-MCP, a benchmark and metric suite that separates task preservation (TPSS), operational pressure (OPSS), and route-geometric drift (RGAS), and combines them in the pre-execution SODS score. In a focused policy-ablation study using a Groq-hosted qwen/qwen3-32b router, 120 routing decisions yield 96 original-versus-variant comparisons across six security-sensitive workflows. Efficiency-first routing produces a 29.2% shadow-invocation rate and 26.7% safety-tool skip rate. Policy-aware routing reduces these to 4.2% and 1.7%, respectively, corresponding to an 85.7% relative reduction in shadow invocations. Pre-execution signals distinguish shadow routes with ROC AUC up to 0.94. These results are early, single-router evidence of a policy-dependent routing-layer security effect, not a claim of universal vulnerability.

cs.CR · cs.AI · cs.MA · eess.SY

版本更新 · v2arXiv:2606.19882

Multimodal Concept Bottleneck Models

Tongqing Shi, Ge Yan, Tuomas Oikarinen, Tsui-Wei Weng

原文摘要

Concept Bottleneck Models (CBMs) enhance the interpretability of deep neural networks by aligning the features extracted from images with human-interpretable concepts. However, conventional CBMs typically use a linear classifier that maps concept activations to a fixed set of predefined classes, limiting their flexibility in open-vocabulary settings. In this paper, we propose Multimodal Concept Bottleneck Model (MM-CBM) to address these issues and extend CBMs into CLIP structure. MM-CBM utilizes dual Concept Bottleneck Layers (CBLs) to align both the image and text embeddings into interpretable features. This allows us to perform new vision tasks like zero-shot classification or image retrieval in an interpretable way. Compared to existing methods, MM-CBM achieves 23.28% accuracy improvement on average across four standard benchmarks. Our method maintains competitive performance compared with black-box CLIP model while offering interpretability. Under classification tasks, MM-CBM's accuracy is on average 3.94% lower than CLIP in the target-dataset adaptation setting and 9.84% in the zero-shot transfer setting. Under image-text retrieval tasks, it achieves an average gap of 2.48% for image retrieval and 9.22% for text retrieval.

cs.CV · cs.LG

新论文 · v1arXiv:2611.11718

Accelerated Reinforcement Learning for Soft Robotics: Hours Instead of Years

Roshan S. Kaundinya, Hehui Zheng, Robert K. Katzschmann, George Haller

原文摘要

Reinforcement learning (RL) requires large amounts of interaction data or a reliable simulator, both hard to obtain for nonlinear soft robotic hardware. Recent work shows that a time-scale separation inherent to soft robot dynamics justifies their reduction to low-dimensional invariant manifolds, known as adiabatic spectral submanifolds (aSSMs). We demonstrate that an aSSM-reduced model, a simple polynomial ordinary differential equation learned purely from pre-collected data, can serve as an RL training environment. On a pneumatically actuated soft arm, we train a trajectory-tracking policy in 3 hours on a six-dimensional aSSM-reduced model and deploy it without fine-tuning, whereas reproducing this policy training extrapolates to 3 years of hardware interaction. Our policy tracks dynamic targets with 40% lower error than otherwise identical policies trained on a 4.8-million-parameter recurrent neural network (RNN) or a 1.7-million-parameter transformer, which take 13 and 100 hours to identify, against 5 minutes for our mathematically justified 6,924-parameter model.

cs.RO · cs.AI · cs.LG · math.DS

新论文 · v1arXiv:2611.11717

Autonomous Continual Learning and Knowledge Transfer via Cortex-Inspired Neural Assemblies

Kevin L. McKee

原文摘要

Unlike the brain, artificial neural networks (ANNs) suffer from "catastrophic forgetting": complete overwriting of solutions when re-training on new functions ("concept shift") or on a disjoint domain of the current function ("domain shift"). ANNs require each batch of data to be roughly representative of the complete distribution, a typically expensive and impractical requirement. In this paper, we introduce Functional Task Networks (FTNs), a method of continual learning and knowledge transfer modeled after several properties of the mammalian neocortex. FTN is formulated as a distributed, stochastic mixture of experts in which a sparse, binary routing mask is computed at inference time using a small support sample of input-output pairs. Per-batch reconfiguration of the router during training, together with mask-overlap-filtered replay, shapes a basis of overlapping, partially trained subnetworks. Unrelated tasks route through mostly separate assemblies, related tasks overlap on shared components. On block-sequentially trained continual learning and knowledge transfer tasks FTN retains solutions nearly as well as disjoint-mask isolation and attains the lowest pre-update head-start loss among matched-architecture comparators. The learned mask-overlap geometry tracks the known concept-sharing structure where available. We show experimentally that under correlated concept shift, support-set mask reconfiguration is necessary even for retention. Under domain shift, the distributed bank with replay is sufficient to handle retention without the configurer. Forward transfer, or head-start, and backward transfer, are also contributed by support-set mask configuration.

cs.LG

新论文 · v1arXiv:2611.11713

Binary Belief Propagation Fixed Points: Finiteness, Rigidity, and Topological Complexity

Yusuke Watanabe

原文摘要

A fixed finite binary Ising model has only finitely many admissible complex belief propagation fixed points, even at degenerate parameter values. Families of positive fixed points obtained by varying external fields can nevertheless have nontrivial topology. We study this distinction through the external-field projection. For a fixed field, we prove finiteness by bounding the pole orders of the magnetizations on a hypothetical complex solution curve. The generic degree on the support graph then bounds the total local multiplicity. A graph has a single smooth real line as its full positive response for every choice of positive couplings, base field, and strictly positive sweep direction exactly when it contains no two vertex-disjoint connected subgraphs of cycle rank at least two. Two such subgraphs suffice to create a circular component. For a plane obtained by varying two vertex fields, connected simple bipartite cubic graphs with one uniform coupling and a universal bound on the fixed fields realize every genus. The minimum number of vertices grows logarithmically in the genus, by a matching algebraic upper bound on Betti numbers. Finally, we certify the complete field discriminant of an eighteen-vertex product model and recover its torus component's genus from the counts of distinct roots on all field cells. The three main theorems, including the logarithmic size bounds, are formally verified in Lean 4 with Mathlib.

cs.IT · math.AG · math.CO

新论文 · v1arXiv:2611.11712

Variational Approach to Optimal IPS Estimator for Multi-logger Off-Policy Evaluation

Joon Suk Huh, Junghoon Seo

原文摘要

We study off-policy evaluation (OPE) in contextual bandits with data collected from multiple logging policies. Inverse propensity scoring (IPS) is a standard approach to OPE and extends naturally to the multi-logger setting. However, as highlighted by Agarwal et al. [2017], neither balanced nor weighted IPS consistently outperforms the other in this setting. We resolve this dilemma by deriving an optimal IPS estimator with sample-dependent weights that minimize variance subject to unbiasedness. Using a variational calculus approach, we obtain closed-form optimal weights, yielding an estimator that is unbiased and achieves asymptotically optimal variance within a generalized weighted-IPS estimator class. Instead of a reward model, the estimator needs only a $K\times K$ matrix and a $K$-vector of moments, where $K$ is the number of logging policies, and we quantify how much efficiency this costs relative to the semiparametric oracle. Experiments on benchmark datasets show that our estimator generally improves on existing multi-logger IPS methods. We also extend our estimator to a doubly robust form by incorporating a conditional reward estimator. We compare the resulting DR extension with the semiparametrically efficient DR estimator of Kallus et al. [2021], both theoretically and empirically. We show that the two estimators achieve the same asymptotic variance when the conditional reward estimator is consistent, while our estimator can retain semiparametric efficiency under certain forms of reward misspecification. Empirically, the proposed DR estimator often achieves lower estimation error than the existing DR baseline.

cs.LG

新论文 · v1arXiv:2611.11711

CRUSTPairs: A Cross-Language Dataset of Paired C and Rust Solutions

Vojtech Hejlek, Leonardo Jesus Almeida, Alneu de Andrade Lopes

原文摘要

C-to-Rust migration is an active agenda, but no dataset pairs the two languages at the level of whole solutions to a shared problem. We present CRUSTPairs, 1857 C/Rust implementation pairs drawn from competitive programming archives, normalised, deduplicated, and stratified into difficulty tiers by zero-shot cross-language embedding similarity, with perrecord provenance and licensing. Cross-language retrieval is hard on this data, and harder than a single baseline would suggest: TF-IDF over shared identifiers reaches MRR 0.21 and so beats a pretrained code model at 0.19, which on the hardest quarter of the data scores 1.7x chance. Finetuning reaches 0.79, and lifts that hardest quarter 10x. Renaming every user identifier settles what is being learned: the finetuned models keep 96-97% of their accuracy without them, while the pretrained model keeps 66\% - less than the lexical baseline does - and on structurally divergent pairs the finetuned models are better without identifiers than with them.

cs.SE · cs.LG

版本更新 · v2arXiv:2602.00249

SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode Diagnosis

Rishav Pramanik, Ian E. Nielsen, Jeff Smith, Saurav Pandit, Ravi P. Ramachandran, Zhaozheng Yin

原文摘要

Text-to-image (T2I) models struggle with compositional prompts requiring multiple objects, bound attributes, accurate counts, or spatial relations. Existing benchmarks face limits from fixed detector vocabularies, aggregated scores, and varying human-validation protocols. We introduce SANEval (Spatial, Attribute, and Numeracy Evaluation), an open-vocabulary compositional benchmark with two key contributions: (i) a public dataset of ~5,250 prompts paired with images from six state-of-the-art T2I models, split into algorithmically generated Simple and fully human-written Hard partitions across five compositional tasks, and (ii) a modular evaluation pipeline combining an LLM prompt parser, an open-vocabulary detector with LLM synonym expansion, and scorers for attribute binding, spatial relations, and numeracy. Each scorer emits numerical scores and diagnostic feedback for missing, extra, or mis-bound elements. Validated against human ratings (n = 500), SANEval achieves positive Pearson correlations across all categories (overall r = 0.222), outperforming CompBench++ (-0.016) and GenEval (-0.030). A manual audit of 24,012 detections shows 96.58% precision, with ablation confirming that synonym expansion is critical to pipeline performance. Dataset: [https://huggingface.co/datasets/saneval/saneval-release](https://huggingface.co/datasets/saneval/saneval-release). Pipeline: [https://github.com/nielseni6/saneval](https://github.com/nielseni6/saneval).

cs.CV · cs.AI

新论文 · v1arXiv:2611.11710

CASCoDe: A Closed-Loop Agentic Framework for Analog Sizing and Layout Co-Design

Ziming Wei, Bingyang Liu, David Z. Pan

原文摘要

Expert analog layouts differ from auto-generated ones in density and regularity, not only in legality: experts make a succession of discrete, hierarchical physical decisions and revisit each after extracted electrical results, while most existing automated flows act on a physical search space fixed before the controller runs. We present CASCoDe, a closed-loop LLM agent framework for analog netlist-to-layout design that formalizes those expert decisions as a hierarchical discrete action space-sizing selection, structural floorplan, local layout refinement, routing-attempt selection-on which the agent runs feedback-driven tree search from a circuit netlist to a verified GDS. The agent authors the circuit-specific floorplans and scripts, and an execution layer of interface adaptations over adapted tools make every action land at physical implementation and be judged by DRC, LVS, and extracted-RC simulation. On 20 SKY130 amplifiers spanning single-, two-, and three-stage topologies, CASCoDe is the only flow that delivers a DRC- and LVS-clean routed layout when meeting design specifications for every circuit. It reduces area by 59-85% (mean 71%) against a conventional P&R flow on identical PCells, raises mean device density from 0.39 to 0.74 against APPlace, MAGICAL, ALIGN and ICPI. A layout that beats every baseline in area and legality appears after 11 minutes of agent time on average, and ablations show that the structured action space and the feedback-guided tree search each reduce area and search cost.

cs.AI

新论文 · v1arXiv:2611.11709

Data-Driven Precision Control of Soft Helicoid Robots

Roshan S. Kaundinya, Mark Leone, Roberto Sabella, Hugo Buurmeijer, Luis Pabon, John Irvin Alora, Marco Pavone, George Haller

原文摘要

A purely data-driven method grounded in the theory of adiabatic spectral submanifolds (aSSMs) was recently used to model and control nonlinear soft robotic simulators. Here, we extend the methodology to learn aSSM-reduced models from data collected from hardware soft robotic platforms. Specifically, we learn a five dimensional (5D) aSSM-reduced nonlinear ordinary differential equation (ODE) that accurately models the dynamics of a soft-helicoid trunk robot. We then use this ODE in a model predictive control scheme to demonstrate real-time precision control across various challenging closed-loop trajectory-tracking tasks, ranging from 2D to 3D trajectories with static and dynamic constraints. We find that our methodology enhances accuracy and precision across all control tasks compared to available data-driven linear methods and model-free reinforcement learning. While we focus here on a soft-helicoid trunk robot, our methodology relies solely on hardware data and is therefore applicable to a broader class of soft robotic systems.

cs.RO · cs.LG · math.DS

版本更新 · v3arXiv:2310.11531

Informed Posterior Sampling: More Efficient Online Learning with Few Offline Demonstrations in Average-Reward MDPs

Dengwang Tang, Dongze Ye, Botao Hao, Rahul Jain, Zheng Wen

原文摘要

We study efficient online reinforcement learning in the infinite horizon setting when there is an offline dataset to start with. We assume that the offline dataset is generated by an expert but with an unknown level of competence, i.e., it is not perfect and not necessarily using the optimal policy. We show that if the learning agent models the behavioral policy (parameterized by a competence parameter) used by the expert, it can do substantially better in terms of minimizing cumulative regret than if it does not do that. We establish an upper bound on regret of the exact informed PSRL (iPSRL) algorithm that scales as $\widetilde{\mathcal{O}}(\sqrt{T})$. This requires a novel prior-dependent regret analysis of Bayesian online learning algorithms for the infinite horizon setting. We then propose the informed RLSVI (iRLSVI) algorithm to efficiently approximate the iPSRL algorithm. Empirical results show that small offline expert datasets are sufficient for iRLSVI to outperform online-only algorithms on hard exploration domains.

cs.LG · cs.AI · eess.SY · stat.ML

版本更新 · v3arXiv:2605.24274

A lift for input-convex neural net training

Ali Siahkoohi

原文摘要

Input-convex neural nets parametrize the convex potentials of density models and transport maps, and their convexity requires the inter-layer weights to be non-negative. Projected gradient descent enforces this by projecting after each step, and due to mini-batch noise the boundary is re-crossed indefinitely, which leads to an active set the projection never identifies. The differentiable alternative, direct softplus, optimizes a free latent weight through a softplus positivity map. Where that latent weight is well below zero, the derivative of the map is exponentially small and scales down both the gradient and its noise. We call this region the shoulder, and a weight that reaches it therefore barely moves and stays for an exponentially long time. We propose the lift, which replaces the free latent weight by a learnable slack plus the output of a hypernetwork that reads a permutation-invariant summary of the training batch. The latent weight then varies with the same batch that forms the gradient, so the two are coupled. We show that this coupling adds a term to the variance of the update at first order, and that the slack, the batch dependence, and the shared batch are each needed for it. Where the coupling aligns positively with the loss curvature, a weight on the shoulder crosses the barriers of the loss sooner under the lift than under direct softplus, also under preconditioned stochastic gradient descent. We compare the lift with the two existing methods on several applications. Where a constrained weight of direct softplus reaches the shoulder, the lift fits the target more closely than direct softplus and reaches the same reconstruction about three times sooner. Where almost none reaches it, the methods agree.

cs.LG · stat.ML

新论文 · v1arXiv:2611.11704

Scalable Counterfactual Explanations for Time Series via Policy Learning

Peiyu Li, Pouya Hosseinzadeh, Soukaina Filali Boubrahimi, Shah Muhammad Hamdi

原文摘要

Generating counterfactual (CF) explanations for time series is challenging due to complex temporal dependencies and the computational inefficiency of traditional instance-specific optimization. We propose a policy learning framework for counterfactual explanation in time series, trained as a one-step contextual-bandit policy-learning problem. By training an actor-critic agent in the latent space of a pre-trained autoencoder, our method learns a transferable policy that captures global structural regularities. Unlike existing methods that rely on iterative optimization for each new input, the learned policy enables direct generation of valid and plausible counterfactuals through a single forward pass, avoiding per-instance optimization at inference time. Experiments on 13 UCR benchmark datasets show that our framework achieves high validity and strong plausibility across multiple anomaly detection metrics. Overall, by decoupling counterfactual generation from per-instance optimization, the proposed method provides an efficient and scalable alternative to existing approaches for time series counterfactual explanations.

cs.LG · cs.AI

新论文 · v1arXiv:2611.13007

Just AI Governance and the Forbidden-Boundary Principle

Na Young Ahn

原文摘要

Artificial intelligence (AI) increasingly shapes consequential decisions, yet predictive accuracy is not a sufficient justification for delegated authority. This conceptual study develops an integrated framework for assessing just AI across normative, data, model, and governance layers. Drawing on plural theories of justice, sociotechnical fairness research, and publicly available governance standards, it maps six justice requirements to observable evidence, decision rights, and remedies. It proposes a two-stage evaluation rule: exclude uses that fail independently justified minimum rights constraints, then compare eligible alternatives across multiple performance and governance criteria. As an explicitly limited normative analogy, Genesis chapter 2 motivates a Forbidden-Boundary Principle (FBP), under which an AI agent must not execute externally consequential actions outside pre-authorized boundaries. The resulting First-Principle Safe-Stop Protocol (FPSSP) comprises an independently governed policy monitor, a mandatory execution gate, a restricted or alternative safe-state controller, immutable-oriented audit trails, and accountable human authorization for recovery. We distinguish this normative and traceability contribution from existing Simplex and runtime assurance architectures; we do not claim a novel safety switch or formal proof of universal ethical compliance. A policy schema, threat model, test matrix, outcome definitions, and a prospective comparison design make the proposal falsifiable. No FPSSP implementation, experimental dataset, numerical improvement, or verified latency bound is reported. The framework supports future evaluation rather than constituting evidence of operational safety.

cs.SE · cs.AI

版本更新 · v2arXiv:2605.19215

Not all uncertainty is alike: volatility, stochasticity, and exploration

Payam Piray

原文摘要

Adaptive decision-making in biological and artificial intelligence requires balancing the exploitation of known outcomes with the exploration of uncertain alternatives. Although prior work suggests that uncertainty generally promotes exploration, it has typically treated distinct sources of environmental uncertainty as equivalent. We consider environments with latent reward states that drift over time (volatility) and are observed through noisy outcomes (stochasticity). Both of them increase posterior uncertainty, yet we show they drive optimal exploration in opposite directions: volatility enhances it, stochasticity suppresses it. We establish this asymmetry formally by extending the Gittins index framework to Gaussian state-space bandits with latent dynamics. We further derive Cause-Aware Uncertainty-Sensitive Exploration (CAUSE), a closed-form exploration bonus obtained via control-as-inference that inherits the same monotonicities. CAUSE matches or exceeds both standard exploration strategies and numerically computed index policies in environments with heterogeneous noise structure. Learning and exploration are governed by the same noise-inference asymmetry, and the framework predicts that pathological noise inference misallocates exploration in an axis-specific way, with implications for computational accounts of psychiatric conditions.

cs.AI

新论文 · v1arXiv:2611.11701

Using the Planted Clique Conjecture for Cryptography: Public-Key Encryption from Planted Clique and Noisy $k$-$\mathsf{LIN}$ Over Expanders

Riddhi Ghosal, Isaac M Hair, Aayush Jain, Amit Sahai

原文摘要

We give a public key encryption scheme that is provably secure against poly-size adversaries, assuming $n^{\log^αn}$ hardness of the standard planted clique conjecture, for any $α\in (0,1)$, and a relatively mild hardness conjecture about noisy $k\mbox{-}\mathsf{LIN}$ over expanders that is not known to imply public-key encryption on its own. Both of our conjectures correspond to natural average-case variants of NP-complete problems and have been studied for multiple decades, with unconditional lower bounds supporting them in a variety of restricted models of computation. Our encryption scheme answers an open question in a seminal work by Applebaum, Barak, and Wigderson [STOC'10].

cs.CR

版本更新 · v2arXiv:2610.23968

IMPULSE: Push First, Then Predict in V-JEPA 2 Feature Space

Tingan Jin, Chung-Hsien Chou

原文摘要

Latent world models such as V-JEPA 2 forecast in the feature space of a video encoder, but one look at an object does not reveal how hard it is to rotate, how much it bounces or how much it slides. People find out by trying: a few pokes reveal how an object responds. IMPULSE, named after the impulse response it infers, gives a predictor in frozen V-JEPA 2 feature space the same ability. A Bayesian contact memory summarizes three short calibration pushes, a predicted object pose carries it into the predictor, and a lightweight random-Fourier pose head lets the predictor use the pose. On 512 fresh objects, in a pre-specified held-out confirmation with models sealed before the data existed, the memory lowers the 1-second feature-forecast error by 11.6-12.8% relative to the same predictor without experience, for all 8 training seeds, with a 95% seed-and-object interval excluding zero. The gain also holds for 128 objects with out-of-range physics (11.7-14.0%), and the full extension beats a plain predictor by 15.5-16.6%. An information-ladder argument, exact for ideal predictors, shows that physics reaches the features only through motion, so we measure how much the pathway lets pose help. On fresh objects, the Fourier head roughly triples the gain of a perfect memory over plain pose tokens (2.8-3.2 times). Raw push measurements fed through the same pathway give a similar gain, so the Bayesian summary is not required; it condenses the trials into eight interpretable numbers. The gain is absent at contact onset and grows afterwards.

cs.CV · cs.LG · cs.RO

新论文 · v1arXiv:2611.11697

SurgTAP-3D: A Large-Scale Cross-Surgery Video Dataset with Contact-Aware 3D Motion Tracking

Jiaxin Guo, Wenzhen Dong, Taoyu Wu, Haomin Kuang, Mengya Xu, Kejian Shi, Ziyi Wang, Tongfan Guan 等 12 位作者

原文摘要

Understanding 3D scene dynamics in minimally invasive surgery (MIS) is a fundamental step toward physically intelligent and autonomous surgical systems. However, existing public datasets offer limited scalability and diversity in real-world clinical scenarios. Moreover, annotations typically focus on either tissue or instruments alone, overlooking tool-tissue interactions. This gap limits applications such as augmented reality guidance and autonomous surgery driven by vision-language-action (VLA) models or world models, which demand large-scale, high-quality 3D supervision. In this work, we construct SurgTAP-3D, a large-scale in-vivo pseudo-3D surgical motion tracking dataset and benchmark, comprising 520K frames, 4,549 action clips, and 1.4M 2D/3D point trajectories from diverse robotic and manual procedures under unified action categories. To make annotation scalable, we design a unified framework for surgical 3D point tracking that converts uncalibrated monocular surgical videos into structured 4D annotations through contact-region prompting, active-tool segmentation, dynamic bundle adjustment, and global 4D refinement. This pipeline adapts foundation priors to surgical videos and produces temporally consistent trajectories, pseudo-scale geometry, camera poses, and instrument masks. The dataset captures realistic challenges inherent to surgical environments, including occlusions, smoke, bleeding, and rapid instrument motion. We establish a comprehensive benchmark on SurgPose, SurgT, and STIR, covering both instrument and tissue tracking. We demonstrate instrument displacement estimation, deformable surface reconstruction, and foundation-model fine-tuning. Extensive experiments and analysis demonstrate the effectiveness of our dataset and annotation framework for 3D surgical point tracking, reconstruction, and surgical action understanding. Homepage: https://wrld.github.io/surgtap-3d/

cs.CV · cs.RO

新论文 · v1arXiv:2611.11696

Direct GPU Energy Measurements of Batch-Level Sharing in Mixture-of-Experts and Recurrent Models

Rafael Pina, Varuna De Silva

原文摘要

Energy claims for efficient neural networks are often inferred from operation counts. We report direct GPU energy measurements on two workloads that batch very differently, recurrent policies in GPU-vectorised multi-agent reinforcement learning (MARL) and mixture-of-experts (MoE) language models, and ask one question of both: can the rows of a batch be made to share computation, across the batch and over time, at a measured saving? On recurrent policies the answer so far is no. Shared activity patterns exist but rarely last one step, masking a frozen policy fails, and trained-in masks succeed only because a fixed mask is equivalent to a narrow GRU, at 11x the energy of a small dense policy in our implementation. Test-time steering adds nothing beyond re-picking on either workload. On MoE models the answer is yes, and granularity decides how much: on Qwen3-30B-A3B, batch-aware routing reads 25-31% fewer expert weights within KL 0.05, with benchmark changes within noise at 500 items, and uses 12-18% less energy per token on a fused forward. We also introduce persistence-aware OEA, a one-parameter rule that keeps the batch-aware cut with about 40% fewer new experts per step than native routing at batch 32-64, though its energy has not yet been measured. These are pilot measurements on one GPU type, and we state their limits.

cs.LG · cs.AI

版本更新 · v3arXiv:2605.19227

Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models

Tobias Braun, Jonas Henry Grebe, Hossein Shakibania, Anna Rohrbach, Marcus Rohrbach

原文摘要

Unified autoregressive models (UAMs) are transformer models that generate text as well as image tokens within a single autoregressive pass. Shared parameters and a multimodal vocabulary simplify the training pipeline and facilitate flexible multimodal generation, yet might introduce new vulnerabilities. In particular, we are the first to show that this unified architecture enables multimodal backdoor attacks, where a trigger can propagate malicious effects across multiple output modalities. Specifically, we present the Token by Token Backdoor Attack (ToBAC), the first backdoor attack targeting UAMs, exploring both data-based and model-based poisoning strategies. We demonstrate that inconspicuous characters or even common words can be transformed into triggers that elicit harmful behavior in autoregressive image generation. ToBAC can jointly manipulate visual outputs and accompanying text, increasing the perceived authenticity of fabricated content. With model access, ToBAC enables attacks on the Liquid model in which a subtle word (e.g., "cool") induces modality-aligned brand promotion or ideological influence in 55% of generations. Without model access, ToBAC can be induced through data poisoning, achieving an average success rate of 63.1% against JanusPro. Our code is available at https://github.com/multimodal-ai-lab/ToBAC.

cs.CR · cs.AI