跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

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

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1196新增论文
+992其中 AI 相关
+66已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-10 11:15 · 全站最近入库：2026-11-10 11:14各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 12:01 — 2026-11-10 12:01（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：2026-11-10 11:15最近发现新增版本：2026-11-10 11:14库内论文最新更新时间：2026-11-08 04:43

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。

19,084 已收录论文16,280 AI 相关4,962 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 18,970 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 11:14（北京时间）
新论文 · v1arXiv:2611.10697

Hallucination-Guided Unlearning: Using Hallucination Traces to Reveal Overfitted Memories

Jiayu Zhang, Ziqi Zhong, Yuliang Gai, Canran Xiao

原文摘要

Selective unlearning is increasingly important for the safety and compliance of large language models. Harmful or memorized content is often entangled with useful knowledge and difficult to enumerate. We use the model's own failures to identify candidates for unlearning. We propose Hallucination-Guided Unlearning (HGU), which uses hallucinations as diagnostic signals. HGU localizes unsupported spans via evidence and internal consensus, traces a sparse set of high-responsibility MLP neurons, and edits them with compact gates under a utility-preserving KL constraint. On TOFU, HGU achieves the best MU-FE trade-off, with Avg scores of 0.7221 (forget05) and 0.7699 (forget10), and the highest SepS H-Avg (0.4382/0.4715) under mixed forget/retain prompts. On the WMDP auxiliary task, HGU yields the strongest forgetting (e.g., 14.2 on Economics) while improving Retain (52.7) and MMLU (57.2). These results suggest that tracing hallucinations enables targeted, post-hoc unlearning that better balances forgetting efficacy and general utility without full retraining.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.39311

Tight Asymptotic Bounds on the Size of Order Graphs

Ruben Becker, Adrián Gómez-Brandón, Gonzalo Navarro, Nicola Prezza

原文摘要

Order graphs were introduced by Arroyuelo et al.\ (TODS 2024) as a generalization of the ring index, to support worst-case optimal joins on relations of arity $d$ while storing few columns: the index stores one column per edge, so its size is proportional to the number of edges of an order graph. It was known that the minimum number of edges lies between $Ω(2^d\sqrt d)$ and $O(2^d d)$, and the lower bound had been claimed to be $42$ for $d=6$. We first exhibit an optimal order graph with only $40$ edges for $d=6$, and show that the proof of that lower bound holds only for unions of cycles, whereas order graphs can be smaller than the smallest set of cycles. We give a corrected statement and proof that holds for every order graph: there must be at least $\max_m\binom dm\lceil m/2\rceil$ edges. This bound is $40$ (hence tight) for $d=6$. We then settle the asymptotic question: the minimum size is $Θ(2^d\sqrt d)$. This is obtained via an explicit construction, based on symmetric chain decompositions of the Boolean lattice, with at most $(d-1)\binom{d}{\lfloor d/2\rfloor}+2^d$ edges. The upper bound is within a factor $4+O(d^{-1/2})$ of the lower bound, and both numerically and asymptotically better than trie switching. Finally, we cast the problem as a set cover with connectivity constraints, which yields an exact ILP formulation and a greedy heuristic. With them we find optimal order graphs for $d\le 6$ in the bidirectional and for $d \le 7$ in the unidirectional model, showing that our lower bounds are tight there, and improve the best known order graphs for $d=7$ and $8$.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2509.26305

Feedback Forensics: A Toolkit to Measure AI Personality

Arduin Findeis, Timo Kaufmann, Eyke Hüllermeier, Robert Mullins

原文摘要

Some traits making a "good" AI model are hard to describe upfront. For example, should responses be more polite or more casual? Such traits are sometimes summarized as model character or personality. Without a clear objective, conventional benchmarks based on automatic checks struggle to measure such traits. Evaluation methods using human feedback such as Chatbot Arena have emerged as a popular alternative. These methods infer "better" personality and other desirable traits implicitly by ranking multiple model responses relative to each other. Recent issues with model releases highlight limitations of these existing opaque evaluation approaches: goblin-obsessed, sycophantic and generally over-the-top personalities have resulted in model rollbacks and extensive media coverage. Despite these known issues, limited public tooling exists to explicitly evaluate model personality. We introduce Feedback Forensics: an open-source toolkit to track AI personality and related behavioural traits, both those encouraged by human (or AI) feedback, and those exhibited across AI models trained and evaluated on such feedback. Feedback Forensics is adaptive and can automatically find new traits appearing in models. We demonstrate the toolkit's usefulness in two steps: (A) first we analyse the personality traits encouraged in popular human feedback datasets including MultiPref, PRISM and data from Chatbot Arena; and (B) then use our toolkit to analyse how much popular models exhibit such traits. We release (1) our Feedback Forensics toolkit alongside (2) a web app tracking AI personality in popular models and feedback datasets and (3) the underlying annotation data, see https://github.com/rdnfn/feedback-forensics.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.00123

Visual Affect Analysis: Predicting Emotions of Image Viewers with Vision-Language Models

Filip Nowicki, Hubert Marciniak, Jakub Łączkowski, Bartosz Wilczek, Krzysztof Jassem, Tomasz Górecki, Vimala Balakrishnan, Desmond C. Ong 等 9 位作者

原文摘要

Vision-language models (VLMs) show promise for large-scale affect inference from images, but their alignment with human affective ratings remains unclear. We benchmarked 16 proprietary and open-source VLMs on three validated affective image datasets: the International Affective Picture System, the Nencki Affective Picture System, and the Library of AI-Generated Affective Images. In a zero-shot setting, models performed two tasks: (i) top-emotion classification and (ii) prediction of human ratings on 1--7/9 Likert scales for discrete emotions and affective dimensions. We also evaluated rater-conditioned prompting on the LAI-GAI dataset using de-identified participant metadata. Best models showed strong discrete emotion classification (60%--80% on six-emotion tasks; 60%--75% on a 12-category task), with anger and surprise predicted least accurately. For continuous ratings, models aligned moderately to strongly with human judgments ($r > 0.75$) but showed consistent biases, especially weaker performance on arousal and overestimation of response intensity. Rater-conditioned prompting had only small, inconsistent effects. Overall, VLMs captured broad affective patterns but sometimes lacked the nuance, although newer model generations performed better.

cs.HC · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.05227

Regret Equals Integrated Covariance: Exact Identities for the Value of Information in Stochastic Optimization

Irene Aldridge

原文摘要

For a stochastic program $\min_{z\in Z} c^T z + h(z)$ with a random cost vector $c$, regret, or the expected value of perfect information, is usually computed by re-solving the problem scenario by scenario. We show that regret is determined by the covariance between the cost vector and the optimal decision $π^s(c)$. The identity is exact and holds without regularity assumptions once the covariance is integrated along the path from the mean to each scenario. With $c_s=E[c]+s(c-E[c])$, $Reg=-\int_0^1 s^{-1} Cov(c_s,π^s(c_s))\,ds$. Three consequences follow. First, the plain covariance is always an upper bound: $0\le Reg\le-Cov(c,π^s(c))$. Second, when the optimal decision rule is affine, as in unconstrained and equality-constrained (e.g., budget-constrained Markowitz) quadratic programs, regret equals exactly one half of the covariance. For purely linear objectives, an affine rule forces zero regret. Third, the ratio of regret to covariance lies in $[0,1]$ and is governed by the shape of the covariance profile along the path. The noise level at which this profile first becomes positive is a decision-stability margin that tightens the bound. The identity also holds scenario by scenario for any predicted cost, so it applies to linear and combinatorial programs with discontinuous decision rules. We give dimension-free concentration bounds and a central limit theorem for the plug-in estimator. Across 7 problem classes, 8 cost distributions, and the shortest-path benchmark of Elmachtoub and Grigas (2022) with $10^6$ draws per configuration, the identities hold to within quadrature error, and the covariance bound holds in every scenario.

econ.EM · cs.IT · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10694

Perception, Not Reasoning, Limits Visual Theory of Mind

Mohamed Rayan Barhdadi, Syed Talal Wasim, Juergen Gall, Erchin Serpedin, Hasan Kurban

原文摘要

Vision-language models pass text-based false-belief probes at near-human levels but drop by over twenty percentage points on abstract panels the moment the same problem is conveyed visually. The consensus diagnosis is conceptual, prescribing new belief-reasoning modules. We argue the dominant bottleneck is perceptual: not what the model cannot reason about, but what it cannot see. We propose a five-condition dissociation protocol that holds the reasoning task constant while varying perceptual fidelity from visual only to text only, and quantify the result with the Perceptual Contribution Ratio, the share of the visual-to-text gap a given fidelity closes. We test this on two kinds of scenes: abstract 2D panels in the Heider--Simmel tradition, and naturalistic 3D game scenes from MuMA-ToM and MindPower. The evaluation covers seven VLMs and roughly 159,000 API calls. Ground-truth scaffolds substantially close the gap in every setting, and on the abstract panels and MuMA-ToM they match or exceed the text-only reasoning. Whereas scaffolds built by automatic parsers, including frontier VLMs, fail. The most common error in the visual-only condition is \emph{reality bias}, which accounts for 60\% of false-belief failures. Models report where an object actually is, not where an absent agent believes it is. This points to a perceptual front-end that fails to track which agents were present at each moment. Under the evaluated protocol, structured visual scene-state extraction, rather than belief inference, is the dominant bottleneck for visual ToM.

cs.CV · cs.AI · cs.CL · q-bio.NC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33012

Recursive Semantic Divergence for LLM Agent Consistency

Harshavardhan Abichandani, Penny Chong, Atin Ghosh, Daniel Dahlmeier

原文摘要

Large Language Model (LLM) agents with tool use can behave inconsistently across independent runs from identical states. They may call different tools, produce contradictory outputs, or follow divergent strategies.This variability compounds over time and undermines deployment reliability. Existing evaluation metrics primarily measure task correctness via completion-based scores and do not capture consistency in agent behavior across executions. Separately, agent behavior is analyzed either at the token level using probability distributions or at the single-response level using semantic clustering, but neither captures how inconsistency propagates across future turns of a trajectory. We introduce Recursive Semantic Divergence (RSD), a trajectory-level consistency metric adapted from bisimulation metrics in reinforcement learning. RSD measures the expected cumulative semantic disagreement between two independent rollouts of the same agent from the same state, using natural language inference to detect logical inconsistency. It is defined recursively over future states and approximated by a neural network trained on independent rollouts. The learned metric estimates future divergence from the current state, providing a consistency score at each turn without requiring the full trajectory to complete. When used as a reward signal for fine-tuning, RSD reduces AUC coefficient of variation (CV) by up to 30.9% on tau2-bench and 50.5% on ToolSandbox. Across Qwen-2.5 and Qwen-3.5 models, RSD reduces AUC CV in seven out of eight model-benchmark settings, while improving the final task progress in all eight settings.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2511.15856

GLOBE: Accurate Surrogates for Boundary-Driven PDEs via Domain-Inspired Architectures and Equivariance

Peter Sharpe

原文摘要

We introduce GLOBE, a nonlinear neural surrogate for boundary-driven, homogeneous, weakly nonlinear PDEs that draws inductive bias from boundary-element methods and equivariant ML, representing solutions as superpositions of learnable Green's-function-like kernels evaluated from boundary faces to targets. The architecture is translation-, rotation-, and parity-equivariant; discretization-invariant; and units-invariant via rigorous nondimensionalization. On AirFRANS (steady incompressible RANS over NACA airfoils), a compact ~117k-parameter GLOBE model has lower mean-squared error than published values for the strongest reported ML surrogates on both the interpolation and low-data splits, in single-run comparisons under the released AirFRANS normalization. The model evaluates fields at arbitrary points, handles non-watertight meshes, and generalizes under Reynolds number and angle-of-attack distribution shifts. We further introduce a hierarchical Barnes-Hut acceleration that exploits the kernel's far-field decay to reduce evaluation cost from quadratic to near-linear in the number of boundary elements, with a tunable opening angle that recovers exact dense evaluation in the zero-angle limit. Quantitative validation focuses on 2D AirFRANS; on 3D DrivAerML cars, GLOBE predicts surface and volume fields on the full meshes, and we compare it with a matched Transolver baseline. Together, these results show that boundary-element-inspired inductive biases can substantially improve the accuracy of ML surrogates for boundary-driven PDEs while scaling to large 3D meshes.

cs.LG · physics.flu-dyn

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10693

Machine Hearing: Can Audio LLMs Generalize Beyond Human Auditory Perception?

Liwei Liu, Jun Tao, Xingyuan Li, Xuenan Xu, Chen Zhang, Junyi Wang, Boya Zhang, Xiaoyu Yang 等 11 位作者

原文摘要

Multimodal LLMs have made remarkable progress in perceiving the physical world, while their perceptual scope remains largely human-centric, focusing on what humans can directly see or hear. This progress raises the prospect of perception beyond human limits, such as extending hearing to sounds that are inaudible to humans. More broadly, the physical world is full of waves, vibrations, and oscillations, only a small fraction of which are directly audible to humans. This invites the extension of multimodal LLMs toward a broader form of machine hearing, which remains largely underexplored. To investigate this direction, we introduce the Machine Hearing Benchmark (MHB), comprising 6,128 instances across 13 tasks and seven domains. MHB spans highly heterogeneous input regimes, with sampling rates from approximately $10^{-5}$ to $10^6$ Hz, sequence lengths from $10^1$ to $10^6$ samples, and both single- and multi-channel inputs. Evaluations of current open-source and proprietary Audio LLMs (ALLMs) reveal limited zero-shot transfer to machine hearing. Supervised adaptation on machine-hearing data alone does not close this gap, suggesting that the challenge extends beyond data exposure to a systematic mismatch between existing audio front ends and machine-hearing inputs. To address this mismatch, we introduce MachEar, a lightweight encoder extension that complements the pretrained Audio LLM for machine-hearing inputs. The results show that MachEar equips a pretrained Audio LLM with stronger machine-hearing capabilities while largely preserving its existing audio understanding performance.

cs.SD · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.18495

Physics-Unrolled Neural Operator for Accelerating High-Fidelity Wireless Ray Tracing

Rafid Umayer Murshed, Saif Ur Rahman, Mingyue Tang, Elahe Soltanaghai

原文摘要

Site-specific wireless design relies on ray tracing to predict how signal strength varies across a floorplan, but a converged indoor radio map takes tens of seconds to simulate and planning a single building requires thousands of them. A learned surrogate can remove most of that cost, yet training one runs into a second problem: high-fidelity labels are exactly what is too expensive to produce at scale, so the affordable labels come from finite-ray simulations that carry residual Monte Carlo noise. We address this with RayNO, a physics-unrolled neural operator that reconstructs the converged output of a ray tracer from one cheap low-fidelity run and scene priors. Rather than treating a radio map as a generic image, RayNO refines the field through three stages matched to reflection, diffraction, and scattering, each supervised by a label of matching physical complexity. We prove that when the label error is conditionally unbiased the learned operator can end up closer to the high-fidelity reference than the labels it was trained on, and we verify that condition directly in the simulator using repeated independent ray seeds. Across diverse floorplans, RayNO outperforms image-to-image baselines, wireless learning models, monolithic neural operators, and classical multi-fidelity regression on both image-quality and wireless deployment metrics, while reducing the cost of a high-fidelity map from roughly 28 s to 0.11 s.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10691

A Geometric Theory for Nonequilibrium Transformer Dynamics

Aythami Bethencourt de León, Darryl D. Holm

原文摘要

We develop a variational and geometric theory based on statistical physics for the joint evolution of Transformer attention and token representations at fixed model parameters. To this end, we introduce a free energy for the attention and model the evolution of the attention weights by its Fisher--Rao gradient flow. At fixed token representations, we prove that the softmax matrix is the unique free-energy minimiser and that every positive attention trajectory converges to it. For prescribed time-dependent representations, we show that the attention dynamics becomes linear after a change to logit variables. This result yields tracking bounds relative to the instantaneous softmax and sufficient conditions for attention to converge to a fixed matrix. Hamiltonian dynamics for the representations and their momenta are then coupled to the attention relaxation driven by the same energy. This coupling results in an energy-dissipation law. We also develop two alternative Hamiltonians incorporating the attention value map. We prove global well-posedness of the attention flow and all three coupled systems.

cs.LG · math-ph · math.PR · nlin.AO · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10690

JoVox: Joint Hierarchical Flow Matching for Lightweight Voxel Generation

Xiangjun Tang, Jianqi Chen, Peter Wonka

原文摘要

Generating high-fidelity voxels while keeping their lightweight nature remains an open problem in computer vision. Current generators are either high-fidelity but computationally heavy, or lightweight but of lower fidelity. Hierarchical methods keep the lightweight nature of voxels. However, their coarse levels, which decide where all finer cells can appear, are generated with the least information about the shape and are never revisited, so they are often plausible but wrong. Our key insight is to let finer cells take part in deciding coarse cells. To this end, we propose JoVox, a discrete flow matching framework that learns the joint distribution of all levels of the voxel hierarchy, instead of a separate distribution for each level, so that coarse cells can be predicted with finer cells already generated nearby. Within this framework, we further introduce a two-level prediction, which outputs the cells two levels finer at once instead of one level finer, halving the number of levels that the network processes and yielding voxels of higher fidelity. We also introduce an unmasking strategy that revisits early decisions once finer cells are generated and corrects inconsistencies in masked diffusion models. Our framework outperforms the baselines on both unconditional and image-conditioned voxel generation. Compared with the current state-of-the-art TRELLIS.2, we achieve 8x higher training throughput, 1/15 of the FLOPs in a forward pass, train on 4 vs. 32 GPUs, and obtain higher quality with an 11% lower Chamfer distance.

cs.CV · cs.GT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10689

RetinaGuard: Risk-Controlled Agentic Triage for Multi-Disease Retinal Screening

Sohaib Sulman, Muhammad Atif Saeed, Akhtar Jamil, Alaa Ali Hameed, Roland Aydin

原文摘要

Retinal screening programmes need to know which automated decisions can be accepted without review. This paper presents RetinaGuard, an agentic triage framework in which quality, diagnostic, uncertainty, verification and explanation agents gather evidence for each fundus photograph, a learned failure predictor estimates the probability that the decision is unsafe, auxiliary tools are invoked only when their expected value of information exceeds their cost, and the acceptance threshold is certified by conformal risk control. On the RFMiD test split, RetinaGuard was compared with confidence and calibrated-uncertainty referral at matched referral budgets and equal certified safety, using two RETFound primary models of different strength. With the weaker model (macro-AUROC 0.896), verifier disagreement added significant information, RetinaGuard captured 119 of 280 unsafe decisions at a 20% budget against 88 for lowest-confidence referral, and at a nominal 5% unsafe level it accepted 37.0% of cases against 10.3%. With the stronger model (0.925) the verifier added nothing beyond uncertainty and the advantage shrank to a few percentage points. In both settings its coverage at the nominal 5% level stayed near 37.7%, gating cut computation by about 30%, and a quality agent reduced unsafe acceptances under most image corruptions. The benefit of agentic evidence gathering thus depends on how much the primary model's own uncertainty already reveals about its errors.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10688

Performance Benchmarking of Federated Learning Frameworks for Medical Image Classification

Vithor Pileco, Luan Mantegazine, Claudio Geyer

原文摘要

Selecting a Federated Learning (FL) framework requires understanding the resource demands of its training and evaluation workflow. This work compares Flower, NVIDIA FLARE, and FedBioMed using two-dimensional MedNIST classification with ResNet-10 in a containerized, single-host environment. Following a dated review of repository activity and documented medical applications, we evaluated nine configurations per framework, with three random seeds, for a total of 81 executions. The configurations varied federation size, communication rounds, and batch size. We monitored execution time, CPU and RAM consumption, host-level GPU utilization, server network traffic rates, and model accuracy at the end of each execution. The implementations shared nominal learning settings while retaining differences in data splitting and federated evaluation. Configuration-blocked non-parametric analysis identified differences in execution time, client and server memory, GPU utilization, and network traffic rates. NVIDIA FLARE exhibited the lowest server-memory consumption and the highest host-level GPU utilization, Flower exhibited the highest average server network traffic rate, and FedBioMed required more client memory and longer execution time. No statistically significant difference in final accuracy was detected within the evaluated short training schedules; this does not establish convergence or equivalent predictive performance. The results characterize the configured workflows under shared hardware resources. They provide a concrete case study of system behavior, with conclusions bounded by workflow asymmetries, local networking, and the lightweight MedNIST workload.

cs.DC · cs.PF

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.28764

Geometry-aware similarity metrics for neural representations on Riemannian and statistical manifolds

N Alex Cayco-Gajic, Arthur Pellegrino

原文摘要

Similarity measures such as centred kernel alignment (CKA) or representational similarity analysis (RSA) are widely used to compare the representational geometries employed by different neural networks to solve the same task. Yet, because existing methods compare the extrinsic geometry of representations in state space, rather than their intrinsic geometry, they may fail to capture subtle yet crucial distinctions between fundamentally different computations. Here, we introduce metric similarity analysis (MSA), a novel method which leverages tools from Riemannian geometry to compare the intrinsic geometry of neural representations under the manifold hypothesis. We show that MSA can be used to (i) disentangle neural computations of deep networks in rich vs. lazy learning regimes, (ii) compare the dynamics of recurrent neural networks and state-space models, and (iii) investigate the statistical manifolds of diffusion models. Overall, we introduce a mathematically grounded and broadly applicable framework to understand the mechanisms behind neural computations by contrasting their intrinsic geometries.

cs.LG · cs.AI · math.DG · q-bio.NC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10684

Audit Before You Merge: Provenance, Probing, and Continual LoRA Composition

Lenny Aharon, Neta Glazer, Lior Aharon

原文摘要

Post-hoc merging of public LoRA adapters is an attractive gradient-free path to continual adaptation, but reliable measurement of catastrophic forgetting in this setting depends on infrastructure that prior work has not addressed. We treat each adapter merge as a sequential task in a continual-learning setting, with the instruction-tuned base model's capabilities as Task 0, and study forgetting on Llama-3.1-8B-Instruct. Public adapter hubs contain modules that fail basic provenance checks: silent base-version mismatches and near-zero delta norms whose inclusion inflates measured interference by ~10pp. We propose a two-check audit (base-model match, non-trivial delta norm) and a leakage-free probing protocol as preconditions for any forgetting study in this setting. On an audited 4-adapter set, naive merging causes -10.5pp on GSM8K and -18.3pp on HumanEval, while Task Arithmetic at lambda=0.5 sits within a standard error of the unmerged baseline. A coordinate search including negative coefficients identifies the math adapter as probe-optimal at lambda=-0.5, outside the reach of positive-only mergers, suggesting forgetting has structure that negation-aware merging may exploit. The same protocol replicates on Mistral-7B-Instruct-v0.3, where 2 of 4 candidate adapters fail the audit and the audited merge reproduces the same merge-method ranking on GSM8K, supporting that our findings are not Llama-specific.

cs.AI · cs.CR · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10683

TransMem: Transition-Aware Retrieval for Evolving Personal Memory

Shigeng Chen, Linhao Luo, Changlong Shi, Zhangchi Qiu, Shirui Pan

原文摘要

Long-term personalized agents are increasingly expected to answer queries over user histories in which preferences, goals, and constraints evolve across interleaved conversations. Existing retrieval-based and structured-memory systems can surface relevant facts, but often return isolated memory units that do not explain which earlier preference was refined, contradicted, or superseded by later evidence. We introduce TransMem, a transition-aware memory retrieval framework that stores preference updates as explicit retrieval units alongside ordinary factual memories. During memory construction, TransMem routes user interaction history into topic-structured memory graphs, detects shift events, and grounds them as transition records. At inference time, TransMem first retrieves factual anchors and then adaptively expands over transition records, producing a compact context of factual anchors and accepted transition records. Experiments on PersonaMem and PersonaBench across two Qwen backbones show that TransMem outperforms representative retrieval-based and structured-memory baselines. Controlled analyses further show that transition records and adaptive expansion contribute beyond factual anchoring, chronological expansion, flat transition retrieval, and fixed-hop traversal. These results suggest that preference-update records are useful retrieval units for long-term personalization.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.09586

DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos

Can Li, Zhoujian Li, Ren Li, Jie Gu, Lei Lei, Jingmin Chen, Lei Sun

原文摘要

World models for deformable objects should recover not only geometry and appearance, but also underlying physical dynamics, interaction grounding, and material behavior. Learning such a model from real videos is challenging because deformable linear, planar, and volumetric objects evolve under high-dimensional deformation, noisy interactions, and complex material response. The model must infer a physical state from visual observations, roll it forward under new interactions, and render the resulting dynamics with high visual fidelity. We therefore present DeformMaster, a video-derived interactive physics-neural world model that turns real interaction videos into an online interactive model of deformable objects within a unified dynamics-and-appearance framework. DeformMaster preserves structured physical rollout while using a neural residual to compensate for unmodeled effects, grounds sparse hand motion as distributed compliant actuators for hand-continuum interaction, represents material response with spatially varying constitutive experts, and drives high-fidelity 4D appearance from the predicted physical evolution. Experiments on real-world deformable-object sequences demonstrate DeformMaster's ability to roll out future dynamics and render dynamic appearance, outperforming state-of-the-art baselines while supporting novel action rollout, material-parameter variation, and dynamic novel-view synthesis. Code and video demos are available at the project page: https://can-lee.github.io/deformmaster-web/

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2512.23818

Energy-Tweedie: Score meets Score, Energy meets Energy

Andrej Leban

原文摘要

Denoising and score estimation are classically linked through Tweedie's formula, which relates the posterior mean under Gaussian noise to the Stein score of the noisy marginal. In this work, we extend this perspective beyond Gaussian noise to a broad class of Gibbs (energy-based) noise distributions, with the generalized Gaussian family as an example. We derive the Energy-Tweedie identity: when the denoising posterior is viewed through the lens of scoring rules, the path derivative of a kernel scoring rule defined by the noise potential recovers the Stein score of the noisy marginal. Thus, the familiar correspondence between Gaussian noise, posterior means, squared loss, and Tweedie's formula is lifted to a distributional correspondence between Gibbs noise distributions, full posterior laws, kernel scoring rules, and the Energy-Tweedie identity, which gives a Tweedie-style relation for each noise potential. Among its consequences, this identity gives a posterior-samples-to-score route to score estimation, yields a principled criterion for estimating unknown noise parameters, and enables diffusion-style sampling along user-chosen paths through the noise-parameter space, supplying the score-based perspective on recent generative methods trained with scoring rules.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.10654

Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights

Jixiang Qing, Henry Moss, Matthias Sachs

原文摘要

We consider the active learning problem where the goal is to learn an unknown function with low prediction error under an unknown Boltzmann distribution induced by the function itself. This self-induced weighting arises naturally in problems such as potential energy surface (PES) modeling in computational chemistry, yet poses unique challenges as the target distribution is unknown and its partition function is intractable. We propose \texttt{AB-SID-iVAR}, a Gaussian Process-based acquisition function that approximates the intractable Bayesian target distribution in closed form while avoiding partition function estimation, and is applicable to both discrete and continuous input domains. We also analyze a Thompson sampling alternative (\texttt{TS-SID-iVAR}) as a higher variance Monte Carlo variant. Despite the unknown target, under mild conditions, we establish that the terminal prediction error vanishes with high probability, and provide a tighter average-case guarantee. We demonstrate consistent improvements over existing approaches in this setting on synthetic benchmarks and real-world PES modeling and drug discovery tasks. Our code is available at https://github.com/TsingQAQ/SIDAL

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10682

Burden, Bounty, or Bliss? Muscle-Aware Retargeting and Null-Space Exploration for Whole-Body Musculoskeletal Control

Ruiyang Kong, Takeshi Oishi

原文摘要

Learning whole-body musculoskeletal control from human motion is important for developing human-like robots, assistive devices, and rehabilitation systems. This task presents two main challenges, namely reference trajectories that are kinematically plausible but difficult to reproduce through muscle-driven dynamics, and a highly redundant 700-dimensional action space in which unstructured exploration can easily disrupt the target motion. In this paper, we propose a motion-to-policy pipeline that exploits muscle redundancy in two complementary stages. First, muscle-aware retargeting (MAR) performs bounded adaptation of kinematic trajectories subject to hard semantic, anatomical, and contact constraints. We motivate the constraint bounds by analyzing how reference-trajectory artifacts affect muscle-driven tracking. Second, null-space exploration (NSE) estimates a one-control-frame mapping from muscle excitations to generalized forces and injects bounded, anatomically structured perturbations along its null space into the actions of a value-guided flow policy. On a 24-clip motion-capture benchmark, MAR and NSE together solve every reference, reach the full horizon with half the samples of the baseline pipeline, and lower joint-center error by 44% without late collapse. To the best of our knowledge, this is the first end-to-end pipeline that transforms monocular video into a trained whole-body imitation policy controlling 700 muscles.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10681

Formalizing Patient-Set Semantics for OMOP CDM-Based Clinical Trial Feasibility Assessment:A Neuro-Symbolic Methodology for Traceable Site-Feasibility Patient Counts

Sohyeon Jeon

原文摘要

This study examines the interpretation and execution of natural-language eligibility criteria for clinical trial site-feasibility patient-count estimation using the OMOP Common Data Model (CDM). It treats each count as the size of a patient set produced under explicitly declared choices about clinical concepts, temporal conditions, exclusions, proxies, and available data. The study presents NS-CoT, a neuro-symbolic pipeline that uses an LLM to interpret and structure criteria, followed by symbolic processing and deterministic SQL compilation. Intermediate representations and execution records document how criteria are translated into patient sets and counts. Evaluation uses synthetic OMOP CDM data, controlled benchmarks, and a multi-site simulation. Comparisons with a direct-SQL baseline examine execution success, count agreement, patient-set agreement, and preservation of reference-defined site-feasibility labels and rankings. Performance varies across evaluation settings. Layer-wise inspection also supports the identification of implementation and policy errors, followed by correction and re-evaluation. The work investigates the reviewability and fidelity of cohort computation relative to declared reference definitions. It does not establish that these definitions capture a unique clinical ground truth or demonstrate improved recruitment, site selection, or trial outcomes in practice.

cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.15400

One Agent to Guide Them All: Empowering MLLMs for Vision-and-Language Navigation via Explicit World Representation

Zerui Li, Hongpei Zheng, Fangguo Zhao, Yanyan Shao, Jian Zhou, Sihao Lin, Shijie Li, Qi Wu

原文摘要

A navigation agent must understand high-level semantic instructions and reason about precise spatial structure. Multimodal Large Language Models (MLLMs), with their strong generalization, are a promising foundation for such agents. We propose GTA, a decoupled design that separates low-level spatial state estimation from high-level semantic planning. We introduce an explicit metric world representation that combines accumulated geometry with navigation history and exposes this information to the MLLM through a multimodal interface for decision-making. We further introduce counterfactual branch reasoning that checks anticipated outcomes against subsequent observations and revises navigation decisions when they disagree. The world representation grounds waypoint selection in reconstructed metric geometry. GTA achieves 48.8% Success Rate (SR) on the full R2R-CE val-unseen split and 46.2% on a 260-episode English RxR-CE val-unseen subset. Additional comparisons on shared R2R-CE episodes and mechanism ablations support the framework's effectiveness. We also demonstrate transfer to wheeled, quadrupedal, and aerial robots. Project page: https://zeruili22.github.io/GTA/

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10679

RankShift: Evaluating Ranking Instability Across Benchmark Dimensions in Document Parsing

Halimat Afolabi, Daeyoung Lee

原文摘要

Document parsing benchmarks are often treated as stable measures of model quality, yet rankings may depend substantially on benchmark design choices. In this work, we present RankShift, a systematic study comparing OCR and vision-language models (VLMs) under controlled variation in dataset composition, matching strategy, and scoring methodology. Using OmniDocBench as a case study, we evaluate the ranking stability of 16 models across 3 dataset configurations, 6 matching strategies, and 3 scoring metrics. We quantify rank stability using pairwise rank correlation, top-k churn, and pairwise reversal rate. Our results show that the interaction between matching strategy and ground truth format is a substantial but understudied driver of instability: scoring against OmniDocBench's JSON annotations versus its Markdown rendering yields a mean Kendall's tau of approximately 0.33 under region-level matching strategies, with individual pairs as low as tau = 0.23, compared with tau = 0.77 when each page is scored as a single concatenated string. Dataset composition produces comparable instability across page-type strata (mean tau = 0.48) and layout-type strata (mean tau = 0.49), while the cross-dataset shift from OmniDocBench to Real5's Scanning reconstruction of the same pages is more stable (tau = 0.80). Metric choice is the most stable dimension, with mean tau of approximately 0.78 across NED, BLEU, and METEOR. These findings indicate that leaderboard position is not solely a property of model capability, motivating leaderboards that report not only headline scores but also the robustness of rankings across reasonable design choices.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.08740

PAC-Bayesian Bounds for Learning Partially Observed Stochastic Linear Time-Invariant State-Space Systems with Inputs and Sub-Gaussian Noise

Mihaly Petreczky, Mohamad Al Ahdab, John Leth

原文摘要

In this paper we derive a Probably Approximately Correct (PAC)-Bayesian error bound for partially observed linear time-invariant (LTI) stochastic dynamical systems in state-space form with inputs and sub-Gaussian noise. Such bounds are widespread in machine learning, and they are useful for characterizing the predictive power of models learned from finitely many data points. The bound derived in this paper relates the expectation of prediction errors with the prediction error generated by the model on the data used for learning. In addition, we show that it can also be used to derive bounds for the parameter estimation error. In turn, this allows us to provide finite-sample error bounds for the prediction error and parameter estimation error for a wide class of system identification algorithms. Furthermore, as LTI systems are a sub-class of recurrent neural networks (RNNs), these error bounds could be a first step towards PAC-Bayesian bounds for RNNs.

cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.24006

Video Object Segmentation under Aquatic Domain Shift: A Diagnostic Benchmark and Restoration Adapter

Hongshen Zhao, Jingkang Tai, Yuhang Wu, Wenkang Zhang, Xi Lan, Shangyan Wang, Tianyu Zhang, Wankou Yang

原文摘要

Underwater video object segmentation (VOS) requires temporally consistent dense segmentation in scenes where water acts as a participating optical medium. Wavelength-dependent attenuation, scattering, turbidity, and unstable illumination alter object appearance, weaken mask-level localization cues, and destabilize temporal association, yet existing VOS benchmarks provide limited support for diagnosing these aquatic factors. We introduce UW-VOS, a large-scale diagnostic benchmark with 1,431 video sequences, 307,267 mask annotations, 411 semantic categories, and 16 fine-grained attributes. UW-VOS supports both standard VOS evaluation and factorized analysis of aquatic appearance degradation, spatial localization ambiguity, and temporal identity discontinuity. We further propose the Aquatic Restoration Adapter (ARA), a physics-derived parameter-efficient module that transfers the inverse structure of underwater image formation into bottleneck feature space and can be instantiated in different VOS backbones. Experiments show that representative open-air VOS methods suffer an average 13-point $\mathcal{J}\&\mathcal{F}$ drop on UW-VOS. ARA matches or surpasses full fine-tuning in both Transformer- and memory-based VOS backbones, and outperforms standard PEFT counterparts under a matched setting. These results establish UW-VOS as a diagnostic platform for underwater video perception and ARA as a compact feature-restoration module for aquatic domain adaptation. Project repository: https://github.com/hszh/UW-VOS.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10677

Safe Offline Reinforcement Learning using Behavior Regularisation and Latent Feasibility Guidance

Mahesh Keswani, Parth Bhardwaj, Ankur Kumar, Raunak P. Bhattacharyya

原文摘要

Safe offline reinforcement learning (RL) seeks to learn policies that maximize return while satisfying safety constraints, using a static dataset. To characterize state-wise safety, reachability analysis identifies the feasible region, defined as the set of states from which constraints can be satisfied at every future step. Policies are commonly extracted from learned value functions with advantage-weighted regression (AWR). However, AWR relies on exponentiated weights that amplify value estimation errors, whereas behavior-regularized policy gradient methods directly utilize the action gradient of the value function and often make more effective use of learned critics. We propose Feasibility-Optimized Conditional Actor Learning (FOCAL), a method that incorporates behavior-regularized policy gradients into a conditional variational autoencoder (CVAE) actor. FOCAL optimizes this policy using a first-order objective partitioned by feasibility, updating the actor to increase return on transitions estimated to be feasible and to reduce constraint violations on transitions estimated to be infeasible. During inference, FOCAL dynamically adjusts the scale of the latent prior according to the estimated feasibility of the state to adjust the conservatism of action sampling. Theoretically, we show that for AWR, the policy update variance depends exponentially on the advantage error, whereas for FOCAL it scales linearly with the variance of the value estimation error. Across the DSRL benchmark, FOCAL satisfies the constraints on all evaluated tasks while achieving competitive or higher returns compared to baselines.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.08039

LINE: LLM-based Iterative Neuron Explanations for Vision Models

Vladimir Zaigrajew, Michał Piechota, Gaspar Sekula, Paweł Gelar, Przemysław Biecek

原文摘要

Interpreting the concepts encoded by individual neurons in deep neural networks is a crucial step towards understanding their complex decision-making processes and ensuring AI safety. Despite recent progress in neuron labeling, existing methods often limit the search space to predefined concept vocabularies or produce overly specific descriptions that fail to capture higher-order, global concepts. We introduce LINE, a novel, training-free iterative approach tailored for open-vocabulary concept labeling in vision models. Operating in a strictly gray-box setting, LINE leverages a large language model and a text-to-image generator to iteratively propose and refine concepts in a closed loop, guided by activation history. We demonstrate that LINE achieves state-of-the-art performance across multiple model architectures, yielding AUC improvements of up to 0.15 on ImageNet and 0.05 on Places365, while discovering, on average, 25% of new concepts missed by predefined vocabularies. Beyond identifying the top concept, LINE provides a complete generation history, enabling polysemanticity evaluation and producing supporting visual explanations that rival gradient-dependent activation maximization methods. The LINE source code is available at https://github.com/CredibleAI/LINE

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.05903

HAPS: Hierarchical LLM Routing with Joint Architecture and Parameter Search

Zihang Tian, Rui Li, Jingsen Zhang, Xiaohe Bo, Wei Huo, Xu Chen

原文摘要

Large language model (LLM) routing aims to exploit the specialized strengths of different LLMs for diverse tasks. However, existing approaches typically focus only on selecting LLM architectures, treating candidate models as fixed while overlooking parameter adaptation, which can substantially affect task performance. In this paper, we introduce HAPS, a hierarchical LLM routing framework that jointly searches over model architectures and parameters. Specifically, a high-level router selects among candidate LLM architectures, while a low-level router generates input-conditioned LoRA parameters for the selected architecture, expanding each candidate from a single fixed behavior into a region of reachable behaviors. The low-level router is built on the backbone of the high-level router, so that architecture selection and parameter generation share a common representation of the prompt. We further optimize the whole framework with a reinforcement learning objective. Extensive experiments show that HAPS consistently outperforms strong routing baselines across reasoning- and knowledge-intensive benchmarks, with analyses of its components, design choices, scalability, cost, and mixed open- and closed-source deployment further demonstrating the robustness of these gains. Our code is available at https://github.com/zihangtian/HAPS.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10674

Regularity in Cryptocurrency Market Cycles: A Halving-to-Halving Analysis Using Data from Google Trends and Wikipedia

Marek Zatwarnicki, Piotr Stolarski, Włodzimierz Lewoniewski

原文摘要

Bitcoin halvings provide a natural temporal structure for studying long-term dynamics of cryptocurrency markets. This paper presents a methodological framework for analyzing the regularity of Bitcoin and aggregate cryptocurrency market cycles by normalizing historical periods between consecutive halving events and projecting them onto a common relative-time scale expressed as the percentage of cycle completion. The proposed framework integrates market variables, namely Bitcoin price and aggregate cryptocurrency market capitalization, with measures of public attention derived from Google Trends search volume and Wikipedia pageviews. To obtain long-horizon daily attention indices, Google Trends data are reconstructed from overlapping 90-day windows linked by median scale ratios, following established approaches to combining high-frequency Google Trends samples. Rather than attempting to forecast future prices, the study aims to compare historical cycles, identify recurring temporal patterns, and evaluate the relationship between market dynamics and retail investor interest across different cycle-relative stages. Exploratory results point to a possible recurring structure. The maxima of the aggregate market capitalization in the two most recent completed cycles occurred at 39.0% and 37.9% of cycle completion, and the highest value of the ongoing cycle observed to date at 38.1% (534-547 days after the respective halvings), although the corresponding multiple of the halving-day value fell from 66 to 1.8. Public attention shows a similar compression of peak multiples, but not a similar timing. The paper also discusses current data limitations and outlines future research directions, including formal lead-lag analyses and expanded multi-asset investigations.

stat.AP · cs.CE · cs.SI

查看论文
arXiv ↗PDF ↗