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

+1112新增论文
+875其中 AI 相关
+133已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 20:16 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 20:33 — 2026-11-19 20:33(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 20:16最近发现新增版本:2026-11-19 19:09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。

27,982 已收录论文23,249 AI 相关8,559 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 8,559 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 20:10(北京时间)
版本更新 · v14arXiv:2509.04154

Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation

Peter Racioppo

原文摘要

We introduce Robust Filter Attention (RFA), a formulation of self-attention as a robust state estimator. Each token is treated as a noisy observation of a latent trajectory governed by a linear stochastic differential equation (SDE), and attention weights are determined by consistency under this model rather than static feature similarity. Under isotropic noise and decay assumptions, RFA matches the computational complexity of standard attention. On language modeling benchmarks, RFA matches or improves on RoPE's perplexity within the training window while remaining stable under zero-shot extrapolation to longer contexts, where RoPE degrades sharply. The framework also provides a dynamical interpretation of standard positional mechanisms, connecting rotational embeddings and recency biases to transport and uncertainty propagation induced by dynamics.

cs.LG · cs.AI

版本更新 · v3arXiv:2605.02416

Capacity-Aware Multi-UE Handover Optimization for LEO Satellite Networks Using Dueling DDQN

Po-Heng Chou, Chiapin Wang, Chung-Chi Huang, Kuan-Hao Chen, Chien-Yu Chen

原文摘要

Frequent handovers and finite satellite capacity make multi-user mobility management challenging in low Earth orbit (LEO) satellite networks. This paper develops a capacity-aware multi-user handover framework based on a double deep Q-network (DDQN) with a dueling architecture. Both training and evaluation employ sequential user equipment (UE) processing with shared satellite occupancy, while action masking excludes invisible or capacity-infeasible satellites. The state incorporates satellite visibility, achievable link quality, remaining capacity, previous association, short-term visibility, and time information. A fixed multi-criteria reward balances throughput, blocking, handover cost, connection persistence, and short-term visibility, while expert trajectories are used only for replay-buffer initialization. Simulations under different UE densities and satellite capacities show that the proposed framework maintains high average throughput per UE and low blocking rates with moderate handover frequency. Ablation results show that removing the remaining-capacity vector has only a limited effect on performance when sequential occupancy tracking and feasible-action masking are retained.

cs.IT · cs.LG

版本更新 · v2arXiv:2512.12663

PerNodeDrop: A Method Balancing Specialized Subnets and Regularization in Deep Neural Networks

Gelesh G. Omathil

原文摘要

Deep neural networks possess strong representational capacity yet remain vulnerable to overfitting, primarily because neurons tend to co-adapt in ways that, while capturing complex and fine-grained feature interactions, also reinforce spurious and non-generalizable patterns that inflate training performance but reduce reliability on unseen data. Noise-based regularizers such as Dropout and DropConnect address this issue by injecting stochastic perturbations during training, but the noise they apply is typically uniform across a layer or across a batch of samples, which can suppress both harmful and beneficial co-adaptation. This work introduces PerNodeDrop, a lightweight stochastic regularization method. It applies per-sample, per-node perturbations to break the uniformity of the noise injected by existing techniques, thereby allowing each node to experience input-specific variability. Hence, PerNodeDrop preserves useful co-adaptation while applying regularization. This narrows the gap between training and validation performance and improves reliability on unseen data, as evident from the experiments. Although superficially similar to DropConnect, PerNodeDrop operates at the sample level. It drops weights at the sample level, not the batch level. An expected-loss analysis formalizes how its perturbations attenuate excessive co-adaptation while retaining predictive interactions. Empirical evaluations on vision, text, and audio benchmarks indicate improved generalization relative to the standard noise-based regularizer.

cs.LG · cs.AI · cs.CV

版本更新 · v2arXiv:2605.02413

Spatial-Temporal Learning-Based Distributed Routing for Dynamic LEO Satellite Networks

Po-Heng Chou, Chiapin Wang, Shou-Yu Chen, Hsiang-Ming Wang, Kuan-Fu Chen

原文摘要

This paper proposes a spatial-temporal learning-based routing framework for dynamic low Earth orbit (LEO) satellite networks. The routing problem is formulated as a partially observable Markov decision process (POMDP), where each satellite independently selects its next hop using network-state observations and destination information. A graph attention network (GAT) extracts spatial features from the dynamic satellite topology and queue states, while a long short-term memory (LSTM) network captures their temporal evolution. The resulting representation is integrated into a deep Q-network (DQN) for destination-aware next-hop selection without a separate traffic-prediction stage. Simulations in a 45-satellite LEO constellation under normal and bursty traffic demonstrate packet delivery performance comparable to a graph neural network (GNN)-enhanced routing baseline, although the proposed method incurs higher delay and queue occupancy. Ablation studies further demonstrate the complementary benefits of spatial and temporal learning.

cs.NI · cs.LG

版本更新 · v2arXiv:2610.01662

Lower Bounds for Stochastic First-Order Algorithms with Variance Reduction in Nonconvex--Concave Minimax Optimization

Jiayi Song, Zi Xu

原文摘要

We establish complexity lower bounds for stochastic first-order algorithms in nonconvex--concave minimax optimization, allowing algorithms to use variance reduction. Our main contribution is a lower bound for a zero-respecting algorithm class that permits variance reduction, extending beyond the algorithmic restrictions imposed by some existing lower bounds. We consider objectives with an $L$-Lipschitz continuous joint gradient, a compact convex dual domain of Euclidean radius at most $D_Y$, and a primal value function, defined by maximizing the objective over the dual variable, with initial suboptimality at most $Δ$. The target accuracy $\varepsilon$ is measured by the gradient norm of the Moreau envelope of the constrained primal value function with parameter $1/(2L)$. Under an unbiased stochastic first-order oracle with variance at most $σ^2$ and mean-squared smoothness, we prove the lower bound $Ω\!\left(L^2D_YΔ\varepsilon^{-3}+L^3D_Y^2Δσ^2\varepsilon^{-6}\right)$. This result quantifies the dependence on accuracy, dual-domain radius, and oracle noise even when variance reduction is allowed. We also establish complementary lower bounds for nonconvex--strongly-concave minimax optimization. With dual strong-concavity parameter $μ>0$ and condition number $κ:=L/μ$, we obtain $Ω\!\left(LΔ\sqrtκ\,\varepsilon^{-2}+LΔκσ^2\varepsilon^{-4}\right)$ under the bounded-variance oracle model. Under the additional mean-squared smoothness condition with constant $\bar L$, we obtain $Ω\!\left(LΔ\sqrtκ\,\varepsilon^{-2}+Δ\bar Lσκ^{3/2}\varepsilon^{-3}\right)$. Together, these results identify complexity barriers across the concave and strongly concave regimes, with the main nonconvex--concave bound remaining valid for algorithms that use variance reduction.

math.OC · cs.LG · stat.ML

版本更新 · v4arXiv:2602.11908

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation

Shani Goren, Ido Galil, Ran El-Yaniv

原文摘要

LLMs are widely used, yet they remain prone to factual errors that erode trust and limit adoption in high-risk settings. One approach to mitigate this risk is to equip models with uncertainty estimation mechanisms that abstain when confidence is low. However, this binary "all-or-nothing" approach is excessively restrictive in long-form settings, often discarding valuable information. We introduce Selective Abstraction (SA), a framework that enables LLMs to trade specificity for reliability by selectively reducing the detail of uncertain content. We formalize SA through selective risk and coverage, and propose Atom-wise Selective Abstraction, a claim-level instantiation that decomposes responses into atomic claims and replaces uncertain atoms with higher-confidence, less specific abstractions. We develop a novel end-to-end pipeline for evaluating long-form generation that instantiates risk as factual correctness and measures coverage as retained information. Our comprehensive empirical evaluation across five LLMs and two long-form factual benchmarks shows that atom-wise SA consistently improves the risk-coverage trade-off, outperforming seven baselines, including claim removal, self-revision, sampling-based aggregation, and chain-of-verification. It improves AURC by up to 35.61% over claim removal, demonstrating that reducing specificity boosts reliability while preserving substantial information. We further provide a risk-guided procedure for selecting a confidence threshold that satisfies a target risk.

cs.AI · cs.CL · cs.LG

版本更新 · v2arXiv:2605.00654

Reinforcement Learning with Markov Risk Measures and Multipattern Risk Approximation

Andrzej Ruszczynski, Tiangang Zhang

原文摘要

For a risk-averse finite-horizon Markov Decision Process, we introduce a special class of Markov coherent risk measures, called mini-batch measures. We also define the class of multipattern risk-averse problems that reduce to linear MDPs in the risk-neutral case. We use both concepts in a feature-based $Q$-learning method with multipattern $Q$-factor approximation and we prove a high-probability regret bound of $\widetilde{\mathcal{O}}\big(d^{3/2}HN^{H-1}\sqrt{K}\big)$, where $d$ is the number of features, $H$ is the horizon, $N\ge2$ is the mini-batch size, $K$ is the number of episodes, and $\widetilde{\mathcal{O}}$ hides logarithmic factors. We also propose an economical version of the $Q$-learning method that streamlines the policy evaluation (backward) step. The theoretical results are illustrated on a stochastic assignment problem and a short-horizon multi-armed bandit problem.

cs.LG · cs.AI · math.OC · stat.ML

版本更新 · v2arXiv:2607.20436

Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models

Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz

原文摘要

Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption. A checkpoint can appear fixed under evaluation-style prompts while the same behavior persists under ordinary-use prompts. Output scores reveal this mismatch but do not locate it. We investigate whether the distinction is encoded in a stable internal site and introduce an audit that fits a paired activation contrast at a path-patching-informed mid-depth window, then modifies the resulting coordinate on held-out prompts. The intervention reduces the evaluation-to-deployment gap by more than $0.12$ in ten of twelve model--behavior settings and closes it (post-intervention gap below $0.06$) in four, across four full-matrix instruction-tuned model instances; among the eight settings with $n{\geq}120$ paired questions, six reduce and one closes. A fifth model supports localization and edit-provenance checks, and in the twelve settings deployment-framed rates change by at most $6.1$pp. On retrained checkpoints, random directions at the same dose do not reproduce the effect, and off-window controls do so only in part. The strongest literal evidence for an evaluation-versus-deployment distinction comes from sandbagging, whose prompt framing is explicitly evaluative; sycophancy and refusal test framing-contingent task distinctions. The two weak cells, both sycophancy, show where a single-coordinate audit at a fixed window is not sufficient. The audit is a non-adaptive, white-box diagnostic for controlled fine-tuned checkpoints, not a training-time defense, a guarantee of deployment safety, or evidence about naturally arising failures.

cs.CL · cs.AI · cs.SE

版本更新 · v6arXiv:2307.12454

Extracting total Amb programs from proofs

Ulrich Berger, Hideki Tsuiki

原文摘要

We present a logical system CFP (Concurrent Fixed Point Logic) supporting the extraction of nondeterministic and concurrent programs that are provably total and correct. CFP is an intuitionistic first-order logic with inductive and coinductive definitions extended by two propositional operators: Restriction (binary), a strengthening of implication, and a unary operator for total concurrency. The source of the extraction is formal CFP proofs, the target is a lambda calculus with constructors and recursion extended by a constructor Amb (for McCarthy's amb) which is interpreted operationally as globally angelic choice and is used to implement nondeterminism and concurrency. The correctness of extracted programs is proven via an intermediate domain-theoretic denotational semantics. We demonstrate the usefulness of our system by extracting a nondeterministic program that translates infinite Gray code into the signed digit representation. A noteworthy feature of CFP is the fact that the proof rules for restriction and concurrency involve variants of the classical law of excluded middle that would not be interpretable computationally without Amb. This is a revised and extended version of the conference paper presented at ESOP 2022 with the same title that contains full proofs of all major results.

cs.LO

版本更新 · v2arXiv:2604.11281

Epistemic Trust as a Mechanism for Ethics Integration: Failure Modes and Design Principles from 70 Moral Imagination Workshops

Benjamin Lange, Geoff Keeling, Kyle Pedersen, Carmen Heringer, Susan B. Rubin, Ben Zevenbergen, Amanda McCroskery

原文摘要

Bottom-up responsible innovation initiatives aim to empower technology development teams to engage in ethical reflection, yet such interventions frequently fail to achieve practitioner engagement. This paper proposes epistemic trust -- the degree to which practitioners regard an intervention, its facilitators, and its content as credible -- as a conceptual model linking intervention design to engagement. Drawing on philosophical work on testimony and practice-based qualitative analysis of over 70 moral imagination workshops with engineering teams between 2019 and 2025, we identify five dimensions of epistemic trust (Relevance, Inclusivity, Agency, Authority, and Alignment) and present a typology of 24 failure modes that arise when these dimensions are inadequately addressed. We derive nine design principles for cultivating epistemic trust, grounded in our operationalization of moral imagination through technomoral scenarios and structured deliberation. Our findings contribute to the literature on collaborative socio-technical integration by specifying the conditions of uptake that existing frameworks leave undertheorized.

cs.CY

版本更新 · v3arXiv:2605.02206

Validity-Gated Evaluation of Multimodal Machine Unlearning

Abdullah Ahmad Khan, Hamid Laga, Ferdous Sohel

原文摘要

Machine unlearning aims to remove the influence of training data without retraining a model from scratch. Evaluation of vision-language models relies on forget accuracy (FA), retain accuracy (RA), membership inference, and similarity to a retain-only reference, but evaluation pipelines are rarely tested. We propose a validity-gated unlearning audit (VGUA) with three checks: the forget set must be memorized without duplicate leakage into the retain set, the scorer must measure correctness, and the training code must implement the intended procedure. Applying these checks reveals that random MMBench splits leak duplicate questions, a lenient scorer hides memorization, and two coding errors remove the signal while training completes. After correcting these problems, we evaluate 234 unlearned models using six methods, three learning rates, and three backbones. Each model is compared with a retain-only reference trained using low-rank adaptation (LoRA). The results depend on update strength. Among models with RA at or above 0.70, lower FA generally indicates closer agreement with the retrained FA-RA operating point. Aggressive updates overshoot this point, collapse RA, and reverse method rankings. Relative to the original model, 78% of healthy models move closer to the retrained model's scores, whereas 94% move farther from it in activation space. Membership-inference advantage does not reliably track retraining alignment. Under option-shuffled training, unlearned models answer 25% of reordered forgotten ScienceQA questions, compared with 6% for the retain-only reference. These results show that multimodal unlearning conclusions depend on pipeline validity, update strength, and the comparison criterion.

cs.CV · cs.LG

版本更新 · v2arXiv:2605.10575

Acceptance Cards:A Four-Diagnostic Standard for Safe Fine-Tuning Defense Claims

Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz

原文摘要

Safe fine-tuning defenses are often endorsed on the basis of a held-out gap reduction, but the same reduction can come from sampling noise, subject artifacts, capability loss, or a mechanism that does not transfer. We introduce Acceptance Cards: an evaluation protocol, a documentation object, an executable audit package, and a claim-specific evidential standard for safe fine-tuning defense claims. The protocol checks statistical reliability, fresh semantic generalization, mechanism alignment, and cross-task transfer before treating a gap reduction as a full-card pass. Re-scored under this installed-gap protocol, SafeLoRA fails the full-card pass on Gemma-2-2B-it: under strict mechanism-class coding it fails all four diagnostics, and under a permissive shrinkage relabel it still fails three of four. This is a narrow installed-gap audit on one model family, not a global judgment of SafeLoRA's effectiveness. In a 46-cell audit, no cell satisfies the strict conjunction. The closest family is a near miss that passes reliability and mechanism checks where the required data are available, but fails the fresh-subject threshold, lacks a strict transfer pass, and carries a measurable deployment-accuracy cost.

cs.CR · cs.AI · cs.LG

版本更新 · v2arXiv:2509.25808

Improving Sampling Efficiency in RLVR through Adaptive Rollout and Response Reuse

Yuheng Zhang, Wenlin Yao, Changlong Yu, Yao Liu, Qingyu Yin, Bing Yin, Hyokun Yun, Lihong Li

原文摘要

Group relative policy optimization (GRPO) trains large language models with verifiable rewards by normalizing rewards within response groups. When every response in a group receives the same reward, the advantages vanish and the group provides no policy gradient signal. We propose Adaptive Rollout and Response Reuse Policy Optimization (AR3PO) to obtain informative groups with fewer generations. Adaptive rollout samples responses to each prompt in stages and stops sampling once the model generates a correct response. If all sampled responses are incorrect, response reuse replaces one of them with a past correct response to the same prompt, when available, and recomputes the group advantages. Policy-recomputed reuse trains on the updated groups using probabilities recomputed under the rollout policy; advantage-only reuse uses historical responses only to compute advantages. Across four mathematical benchmarks with 7B and 8B models, AR3PO consistently improves over GRPO and achieves performance comparable to DAPO while requiring up to $4.2\times$ fewer generated responses. Experiments with a 32B model also show comparable performance to DAPO at a similar training stage with substantially fewer generated responses.

cs.LG

版本更新 · v2arXiv:2605.09025

MedFL-Stress: A Systematic Robustness Evaluation of Federated Brain Tumor Segmentation under Cross-Hospital MRI Appearance Shift

Kiran Naseer, Naveed Anwer Butt

原文摘要

Federated learning lets hospitals train segmentation models without sharing patient data, but standard evaluation reports one number: mean Dice across all sites. That number can look competitive while one hospital runs far behind the rest. Our results suggest this gap is not primarily a federation problem. Under controlled MRI appearance shift on BraTS 2020, even a centralised model trained on all data (single seed) shows a 0.055 best-worst client gap. Under FedAvg, federation adds a further 0.030 on top of that. In our setup, appearance shift accounts for most of the gap and federation widens it. We test five methods - centralised, FedAvg, FedProx, FedBN, and q-FedAvg - under this protocol. q-FedAvg achieves the best worst-client Dice in both full-data and subsampled regimes while also maintaining the highest mean Dice among FL methods: no accuracy-fairness tradeoff in our setting, though its margin over FedAvg is not significant at five seeds (p=0.436). FedProx significantly lowers the worst client across five seeds (p=0.019). Worst-client rankings are identical across both evaluation regimes, but FedBN's worst-client spread across seeds is nearly double FedAvg's - a reliability gap that single-seed evaluation cannot see. MedFL-Stress packages this stress test as a reproducible protocol. The main practical message: report worst-client Dice and confirm rankings across evaluation regimes before drawing conclusions from any FL benchmark.

cs.CV · cs.LG

版本更新 · v2arXiv:2605.06884

Muon with Nesterov Momentum: Heavy-Tailed Noise and (Randomized) Inexact Polar Decomposition

Sayantan Choudhury, Xiaoran Cheng, Martin Takáč, Sen Na, Mladen Kolar

原文摘要

Most first-order optimizers treat matrix-valued parameters as vectors, ignoring the intrinsic geometry of hidden-layer weights in neural networks. Muon addresses this mismatch by updating along the polar factor of a momentum matrix, but its theoretical understanding has lagged behind practice. In particular, practical implementations incorporate Nesterov momentum, compute the polar factor only approximately, and operate with stochastic gradients that may be heavy-tailed. We close this gap by developing a convergence theory for Muon with Nesterov momentum and inexact polar decomposition in non-convex matrix optimization under heavy-tailed noise. Our analysis builds on a unified framework for inexact polar decomposition that captures practical iterative approximations such as Newton-Schulz and quantifies how their errors propagate through the optimization dynamics. Under uniform bounds on polar errors, we establish an optimal iteration and sample complexity of $O \left(\varepsilon^{\frac{-(3α-2)}{(α-1)}} \right)$ for finding an $\varepsilon$-stationary point, where $α\in(1,2]$~denotes the heavy-tail index. For the inexact-polar setting with $σ_1=0$, we also provide guarantees that do not require prior knowledge of $α$. We analyze a randomized low-rank polar decomposition that is substantially more efficient than full-space methods while remaining compatible with our theory. Numerical experiments further demonstrate the effectiveness of the proposed inexact and randomized~variants.

math.OC · cs.LG

版本更新 · v2arXiv:2603.14320

Early Failure Detection and Intervention in Video Diffusion Models

Byungki Kwon, Sohwi Lim, Nam Hyeon-Woo, Moon Ye-Bin, Tae-Hyun Oh

原文摘要

Text-to-video (T2V) diffusion models have rapidly advanced, yet generations still occasionally fail in practice, such as low text-video alignment or low perceptual quality. Since diffusion sampling is non-deterministic, it is difficult to know during inference whether a generation will succeed or fail, incurring high computational cost due to trial-and-error regeneration. To address this, we propose an early failure detection and diagnostic intervention pipeline for latent T2V diffusion models. For detection, we design a Real-time Inspection (RI) module that converts latents into intermediate video previews, enabling the use of established text-video alignment scorers for inspection in the RGB space. The RI module completes the conversion and inspection process in just 39.2ms. This is highly efficient considering that CogVideoX-5B requires 4.3s per denoising step when generating a 480p, 49-frame video on an NVIDIA A100 GPU. Subsequently, we trigger a hierarchical and early-exit intervention pipeline only when failure is predicted. Experiments on CogVideoX-5B and Wan2.1-1.3B demonstrate consistency gains on VBench with up to 2.64 times less time overhead compared to post-hoc regeneration. Our method also generalizes to a higher-capacity setting, remaining effective on Wan2.1-14B with 720p resolution and 81-frame generation. Furthermore, our pipeline is plug-and-play and orthogonal to existing techniques, showing seamless compatibility with prompt refinement and sampling guidance methods. We also provide evidence that failure signals emerge early in the denoising process and are detectable within intermediate video previews using standard vision-language evaluators.

cs.CV

版本更新 · v2arXiv:2610.38356

Encode Once, Answer Many: Internalizing Context via Parametric Flow

Xinhao Zhong, Mengxuan Wu, Chonghua Liao, Linxi Xie, Ruicheng Feng, Kangqiao Xu, Yanpei Guo, Hao Tan 等 26 位作者

原文摘要

Large language models are typically adapted to a task either by placing knowledge in the input context, which keeps it external and re-encodes it on every call, or by fine-tuning, which internalizes it but demands a costly round of optimization per task. We aim to internalize the knowledge carried by a context directly into model parameters, without per-task optimization and without keeping the context in the input at inference time. To this end, we propose CLIK, a context-conditioned parameter generator that maps a given context to LoRA parameters for internalizing knowledge in a single forward pass through a Transformer encoder with cross-attention, requiring no test-time gradient updates. Once the generated LoRA is inserted into a frozen base model, the model answers downstream queries from the query alone, having internalized the context into its weights rather than re-reading it. Because the adapter depends only on the context, it is generated once and reused for every query on the same document, so the cost of reading that document is amortized across queries. On document question answering, CLIK substantially improves over the no-context base model and outperforms existing hypernetwork-based generators, while remaining behind a base model that reads the context directly, and it carries over to multi-turn dialogue without any multi-turn-specific training. Analysis further shows that the context-dependent part of the generated adapter concentrates in a compact and specific substructure.

cs.AI

版本更新 · v2arXiv:2605.10634

Teacher-Aware Evolution of Heuristic Programs from Learned Optimization Policies

Minyu Chen, Song Qin, Ling-I Wu, Jianxin Xue, Guoqiang Li

原文摘要

LLM-based automatic heuristic design has shown promise for generating executable heuristics for combinatorial optimization, but existing methods mainly rely on delayed endpoint performance. We propose a \emph{teacher-aware evolutionary framework} that uses independently trained learned optimization policies as behavioral teachers. Instead of deploying or imitating the teacher, our method queries it on states visited by candidate heuristic programs and uses its action preferences as local feedback for evolution. The resulting search discovers static executable heuristics guided by both task performance and teacher-derived behavioral signals. Experiments on scheduling, routing, and graph optimization benchmarks show that our method improves over performance-driven LLM heuristic evolution baselines while requiring no neural inference at deployment. These results suggest that learned optimization policies can be repurposed as behavioral feedback sources for automatic heuristic discovery.

cs.AI

版本更新 · v3arXiv:2609.37687

WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation

Muhammad Huzaifa, Lea Schönherr, Thorsten Eisenhofer

原文摘要

Active test-time adaptation (ATTA) improves robustness under distribution shift by updating a deployed model during inference while selectively querying supervision. However, most existing ATTA methods implicitly assume that supervision can be requested for every incoming test batch, which can incur substantial annotation cost over long test streams. In this work, we introduce budgeted ATTA in which labels are available for only a fraction of test batches. This formulation shifts the central challenge from deciding what to label within a batch to deciding when supervision should be applied over time. To address this challenge, we propose a budget-aware approach WISE-ATTA that allocates supervision over the test stream based on lightweight signals computed online, prioritizing periods where supervision is likely to be most useful. When a batch is selected for supervision, we further employ a drift-based sample selection criterion that targets samples exhibiting ongoing, unconverged adaptation dynamics, enabling effective updates from a single labeled example. We evaluate this approach on synthetic corruptions (ImageNet-C) and natural distribution shifts (ImageNet-R/K/A). Across settings, WISE-ATTA achieves competitive or improved performance compared to recent ATTA methods while requiring substantially fewer labels. Overall, we find that the timing of supervision is a key, yet underexplored, aspect of active test-time adaptation. Code: https://github.com/Muhammad-Huzaifaa/WISE-ATTA

cs.AI

版本更新 · v2arXiv:2605.00257

AI-Enabled Question-Answering for Chartered Accountancy: A Retrieval-Augmented Reasoning Framework

Jatin Gupta, Akhil Sharma, Saransh Singhania, Ali Imam Abidi

原文摘要

The inception of Large Language Models (LLMs) has catalyzed AI adoption in the finance sector, yet their reliability in complex, jurisdiction-specific tasks like Indian Chartered Accountancy (CA) remains limited. The models display difficulty in executing numerical tasks which require multiple steps while also needing advanced knowledge about legal regulations and the method of scaling their operations is not feasible in settings which have limited access to resources. We present CA-ThinkFlow as a parameter-efficient Retrieval-Augmented Generation (RAG) framework which operates with a 14B, 4-bit-quantized reasoning model, 14B-DeepSeek-R1, and a layout-aware Docling extraction system which maintains document structure during extraction. CA-ThinkFlow uses a basic RAG method which automatically adds retrieved information into the prompt, while it depends on the model's built-in Chain-of-Thought (CoT) functions to create context and produce correct answers. The system we developed system operates at performance levels which match large proprietary models when we tested it on the multi-level CA-Ben benchmark, achieving Scholastic Reliability Coefficient (SRC) results which equal 68.75\% of GPT-4o and Claude 3.5 Sonnet. The framework shows high efficiency and strength in handling parameters, but essential reasoning abilities fail to process complex regulatory texts which exist in fields such as Taxation.

cs.CL · cs.AI · cs.IR

版本更新 · v2arXiv:2610.08892

Hybrid++: The Bridge between PDE Models and Deep Learning for Gamma Noise Removal

Mahipal Jetta, Sujato Dutta

原文摘要

Multiplicative gamma noise is one of the dominant noise factors in Synthetic Aperture Radar (SAR) and medical ultrasound images. They are dependent on pixel level noises due to which they are highly varying across the image and harder to handle as compared to additive noise. The denoising methods to address this noise currently include classical partial differential equation (PDE) methods which are good for interpretation but lack the restoration ability as compared to the state-of-the-art models while deep neural networks like DnCNN achieve high performance but at the cost of transparency due to which practitioners are skeptical to use them in high-risk critical fields like medicine. This paper presents Hybrid++, a novel trainable nonlinear reaction-diffusion architecture that addresses both the concerns - staying interpretable while offering performance close to huge black-box models. It combines a fully learnable PDE initialization with a 3-stage reaction-diffusion network having 64-channel multiscale filter banks, 4-layer Squeeze-and-Excitation attention-based influence functions and a 64-dimensional noise level embedding. It uses a two-phase training strategy, stage-wise optimization followed by joint end-to-end refinement which enables co-adaptation of all learnable parameters. On the FoE benchmark, Hybrid++ substantially improves over classical PDE, BM3D and the original TNRD baselines. In the severe-noise setting L=1, it comes within 0.23 dB PSNR of a separately trained DnCNN while using only about 8% of its parameters.

eess.IV · cs.AI

版本更新 · v2arXiv:2606.22983

OmniCast: Interaction-Aware Serving for Real-Time Omni-Modal LLMs

Xiangyu Zhi, Peiqi Yin, Sheng Guan, Chenguang Zheng, James Cheng, Xiao Yan

原文摘要

Realtime omni-modal LMs support speech-centric conversations where users stream inputs, hear generated audio, and interrupt freely. Existing Omni-LM serving systems still rely on throughput-oriented LLM scheduling and LRU KV offloading. These policies ignore audio playback and multi-turn reuse: they may generate tokens far beyond what users hear, wasting work after barge-in, and evict KV state needed in the next turn. OmniCast is an interaction-aware serving system for realtime Omni-LM interaction. It exposes playback progress, speech activity, and barge-in events to the serving pipeline. The scheduler prioritizes first-audio and near-underrun sessions while limiting generation beyond the playback frontier. The KV manager uses next-use-aware eviction and preloads likely-needed KV during user speech to hide reload latency. On vLLM-Omni, OmniCast improves realtime serving across two Omni-LMs and mixed workloads. It lowers P90 audio TTFP by $1.55\times$ on average and up to $2.21\times$, while improving completed-request throughput by $1.15\times$ on average and up to $1.56\times$, and moves most KV reload work off the next-turn critical path.

cs.DC

版本更新 · v2arXiv:2610.22522

Agentic AI in Automated Markets

Irene Aldridge, Lourenco Belleau-Bhowmik, James Chan, Josh Chang, Kelly Deng, Pranav Dhingra, Xinda Ding, Haodong Fang 等 33 位作者

原文摘要

Automated markets increasingly host autonomous, learning trading agents and are powered by formulaic automated market makers (AMMs). We study how heterogeneous agent behavior shapes stress, risk-adjusted performance, liquidity, and volatility in these types of markets. Three behavioral archetypes are modeled as agentic reinforcement learning (RL) systems: a rational arbitrageur, a manipulator, and a retail herd-follower. Each archetype is defined by its reward function within a common, asset-agnostic exposure-control environment, and each is trained with a value-based Deep Q-Network (DQN) and with REINFORCE using a learned baseline. A pilot on hourly cryptocurrency data (AAVE, ETC, SUI) motivates the hypotheses. Herd-followers produce the most frequent but shortest stress episodes, manipulators the fewest but most persistent, and rational agents the most stable rolling Sharpe ratios despite higher return volatility. SHAP attributions tie these patterns to drawdown and cross-asset signals, short-term volatility and position state, and momentum, respectively. The results motivate behavior-specific regulation rather than uniform limits on volatility or turnover.

econ.EM · cs.ET · q-fin.RM · q-fin.TR

版本更新 · v2arXiv:2610.33119

Benchmarking Classical and Quantum Machine Learning for Intrusion Detection Across Multiple Datasets

Taha M. Mahmoud, Naima Kaabouch

原文摘要

Intrusion detection is examined through a comparative benchmark of classical and quantum machine learning models on three datasets: NSL-KDD, UNSW-NB15, and MQTTEEB-D2025. The analysis focuses on how preprocessing decisions, feature selection strategies, and quantum encoding schemes shape model performance on data with differing levels of noise and complexity. A single unified pipeline is applied, covering normalization, class-imbalance handling, dimensionality reduction, and two feature selection methods: Random Forest importance and a quantum-aware approach that combines Quantum Kernel Alignment with Mutual Information (QKA-MI). Four classifiers are compared: Support Vector Machine, Random Forest, Quantum Support Vector Machine, and Pegasos Quantum SVM. The classical models perform consistently across all three datasets, whereas the quantum models depend more strongly on feature representation and kernel alignment. Quantum-aware feature selection yields marked gains for the quantum models, especially on cleaner datasets, while heterogeneous traffic remains difficult. Pegasos Quantum SVM offers a good trade-off between accuracy and computational cost, underscoring the role of preprocessing alignment in practical quantum intrusion detection.

cs.CR · cs.ET

版本更新 · v2arXiv:2607.13304

Query Language Sensitivity in Automated Sentiment Scores of LLM Responses

Dmitrij Żatuchin

原文摘要

Automated scores are often used to summarize how large language models describe brands across prompts, providers, and languages. Such scores can vary because the answers differ, because the scoring instrument behaves differently across texts or languages, or for both reasons. We examine this measurement problem in 12,933 responses from a design crossing 20 stored brand labels, eight query languages, three provider aliases, and 15 prompt identifiers. The outcome is the signed winning-class confidence from a multilingual sentiment classifier: neutral winners are coded zero, while positive and negative winners receive signed confidence. A crossed linear mixed model fitted to all responses assigns 26.49% of fitted variance to query language and 1.46% to brand. An exploratory refit after excluding English assigns 5.07% to language and 2.23% to brand. These percentages have different denominators: total fitted variance falls by 65.08%, and absolute brand variance falls by 46.65%. English contains 591 negative classifier scores among 1,620 answers, compared with 77 among 11,313 answers in the other seven languages. The result shows that the original variance decomposition is highly sensitive to English inclusion. It does not identify a causal English effect or establish that English answers are more negative toward the brands. The classifier was trained for tweet sentiment, receives no separate target-brand condition, and English is the only study language represented in its documented sentiment fine-tuning set. Automated score differences should therefore be checked as properties of both the answers and the measurement instrument before they guide substantive conclusions.

cs.IR · cs.CL

版本更新 · v2arXiv:2607.01525

Mean Field Reinforcement Learning: Theory and Algorithms for Mean Field Control

René Carmona, Mathieu Laurière

原文摘要

This monograph provides an introduction to mean field reinforcement learning through the lens of Markov decision processes arising from large-population stochastic control with mean field interactions and common noise. Starting from the connection between multi-agent reinforcement learning and mean field control, it develops the probabilistic, mathematical, and control-theoretic framework needed to formulate representative-agent learning problems, analyze their relationship with finite-population systems, and study both general and linear-quadratic models. The presentation includes dynamic programming principles, propagation-of-chaos limits, and theoretical analyses of tabular Q-learning and policy-gradient methods. It also discusses numerical implementations, including tabular schemes and deep reinforcement learning methods such as deep deterministic policy gradient. The goal is to give readers a coherent bridge between mean field control theory and reinforcement learning methodology, emphasizing the mathematical structure of the problems and the design of tractable learning approaches for large stochastic populations.

math.OC · cs.LG · cs.MA · math.PR

版本更新 · v2arXiv:2512.14221

Mask-Conditional Conformal Prediction: Valid Uncertainty For All Missing Data Mechanisms

Jiarong Fan, Juhyun Park. Thi Phuong Thuy Vo, Nicolas Brunel

原文摘要

Conformal prediction (CP) offers a principled framework for uncertainty quantification, but it fails to guarantee mask-conditional coverage when faced with missing covariates. In addressing the heterogeneity induced by various missing patterns, Mask-Conditional Valid (MCV) Coverage has emerged as a more desirable property than Marginal Coverage. In this work, we adapt split CP to handle missing values by proposing a preimpute-mask-then-correct framework that can offer valid coverage. We show that our method provides guaranteed Marginal Coverage and Mask-Conditional Validity for general missing data mechanisms. A key component of our approach is a reweighted conformal prediction procedure that corrects the prediction sets after distributional imputation (multiple imputation) of the calibration dataset, making our method compatible with standard imputation pipelines. We derive two algorithms and prove that they achieve both marginal validity and MCV. We evaluate them on synthetic and real-world datasets. It reduces significantly the width of prediction intervals w.r.t standard MCV methods, while maintaining the target guarantees.

stat.ML · cs.LG

版本更新 · v2arXiv:2609.39567

Invariant Shape Analysis of Surfaces with Spherical Topology

Tanush Shaska

原文摘要

Every real spherical harmonic of even degree is congruent to its mirror image. We prove that a real spherical harmonic of odd degree $n\ge3$ with distinct Maxwell axes is congruent to its mirror image if and only if the hyperelliptic curve of genus $n-1$ defined by its binary form has a reduced automorphism of even order whose lift acts on the form by $-1$. We then determine the locus of these curves: it is the locus of curves with an extra involution if and only if $n-1$ is a power of two, and otherwise it also contains, for each even divisor $k$ of $n-1$ with odd cofactor $d\ge3$, an irreducible family $y^2=x K(x^{2k})$, $°K=d$, with generic reduced automorphism group $\Z/2k$. For $n=3$ the condition is the vanishing of the skew invariant of the binary sextic. As an application, the invariants of the truncated spherical harmonic expansion of a genus-zero surface, in a conformal parameterization normalized by its conformal barycenter, give a descriptor that is exactly invariant under parameterization, position and scale, records handedness, and is stable in the orbit distance.

cs.CV · math.AG

版本更新 · v2arXiv:2512.20276

ActionFlow: A Pipelined Action Acceleration for Vision Language Models on Edge

Yuntao Dai, Hang Gu, Teng Wang, Qianyu Cheng, Yifei Zheng, Zhiyong Qiu, Lei Gong, Wenqi Lou 等 9 位作者

原文摘要

Vision-Language-Action (VLA) models have emerged as a unified paradigm for robotic perception and control, enabling emergent generalization and long-horizon task execution. However, their deployment in dynamic, real-world environments is severely hindered by high inference latency. While smooth robotic interaction requires control frequencies of 20-30 Hz, current VLA models typically operate at only 3-5 Hz on edge devices due to the memory-bound nature of autoregressive decoding. Existing optimizations often require extensive retraining or compromise model accuracy. To bridge this gap, we introduce ActionFlow, a system-level inference framework tailored for resource-constrained edge platforms. At the core of ActionFlow is a Cross-Request Pipelining strategy, a novel scheduler that redefines VLA inference as a macro-pipeline of micro-requests. The strategy intelligently batches memory-bound Decode phases with compute-bound Prefill phases across continuous time steps to maximize hardware utilization. Furthermore, to support this scheduling, we propose a Cross-Request State Packed Forward operator and a Unified KV Ring Buffer, which fuse fragmented memory operations into efficient dense computations. Experimental results demonstrate that ActionFlow achieves a 2.55x improvement in FPS on the OpenVLA-7B model without retraining, enabling real-time dynamic manipulation on edge hardware. Our work is available at https://github.com/Frankd35/Action-Flow.

cs.AI · cs.RO

版本更新 · v3arXiv:2606.01770

Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams

Zewen Liu, Zhan Shi, Yisi Sang, Bing He, Minhua Lin, Tianxin Wei, Dakuo Wang, Benoit Dumoulin 等 10 位作者

原文摘要

Auto-harness systems improve LLM agents by adapting prompts, skills, tools, and supporting infrastructure from execution feedback. Sustaining these gains on open-ended task streams requires handling growing histories, heterogeneous tasks, and shifting distributions. We introduce Adaptive Auto-Harness, a unified framework that separates persistent evolution workspaces from deployable harnesses and supports interchangeable evolution procedures. We compare configurations adapted from five prior approaches on recorded streams of prediction markets, security challenges, and event forecasts. With the same Sonnet solver, our full system reaches 80.9\% market all-task accuracy and 50.2\% security Pass@1, versus 22.2\% and 37.2\% without evolution; market accuracy also exceeds a market-following control's 72.0\%. Our analyses show that artifact accumulation does not guarantee sustained gains, and knowledge that transfers across tasks can still lose value as the task distribution changes. Continued evolution can therefore help preserve earlier gains through revision of accumulated knowledge. Code: https://github.com/A-EVO-Lab/a-evolve.

cs.LG · cs.AI