跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1111新增论文
+874其中 AI 相关
+133已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 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 2026-11-19 08:50 — 2026-11-20 08:50(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:2026-11-20 08:48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

浏览论文库

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

找到 23,249 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.23608

JEPA as a Transferable Optimizer: Learning and Understanding Black-Box Optimization from Reward-Agnostic Pretraining

Mayukh Debnath, Manan Roy Choudhury

原文摘要

Black-box optimization evaluates candidates through simulations, rollouts, or experiments, often without gradients. Learned optimizers are usually judged by whether they outperform existing methods. We ask a complementary question: what information does a learned optimizer use from its search history? We introduce JEPA-PS (JEPA Policy Search), based on a Joint-Embedding Predictive Architecture. It is pretrained on random rollouts using parameter vectors and scalar returns. Its latent-prediction objective predicts the next point in an optimization trajectory rather than its reward or gradient, allowing us to examine what was tried and how well it performed. At test time, JEPA-PS reads a short evaluation history and proposes a candidate in one forward pass, without task descriptions, reward shaping, or test-time gradients. We evaluate it on 15 control environments against 12 optimizers, including evolutionary methods, Bayesian optimization, CMA-ES, and an LLM optimizer. JEPA-PS is competitive with tuned classical baselines and outperforms the LLM optimizer by more than 2x on Swimmer at 71x lower per-step cost. It also transfers zero-shot to environments excluded from pretraining. Null-model comparisons and decoder-training ablations indicate that its latent representation carries information beyond simple history statistics; every trained decoder variant performs worse than the default frozen representation. Our main finding is that the history JEPA-PS uses depends on the task. On smooth landscapes it uses the full trajectory, whereas on rugged landscapes the best-seen point carries nearly all the signal. This memory requirement has a weak positive correlation with fitness-distance correlation (FDC; r=0.112, n=7), while an independent reward-ordering sensitivity probe does not corroborate the relationship (r=-0.024, n=7). Code: https://github.com/mdebnath22/jepa-props.

cs.LG · cs.AI

版本更新 · v2arXiv:2611.11826

How Path Integral Diffusion Decides a Finite Spin Glass

Michael Chertkov

原文摘要

When an AI diffusion-type generator samples a frustrated spin glass, which macroscopic alternatives does it decide first, and when? We study this for bridge-diffusion models of the Path Integral Diffusion (PID) type started from a point source. We show that every isotropic PID is a time-changed Gaussian stochastic localization, and conversely every signal-to-noise schedule is realized by a PID protocol. What a continuous-time generator decides therefore does not depend on the protocol, which only sets when and at what cost. We describe the generator's state by its partial commitments: the probabilities it assigns, at each moment, to nested classes of configurations fixed by the target. The partial commitments are martingales that move only along class contrasts. Their ensemble average gives the information about each level at an exact rate set by squared magnetization contrasts. In the balanced, effectively binary approximation, a split reaches half of its class information near γ=1.044/λ_P, where λ_P is the leading eigenvalue of the parent covariance. The theory is applied to Bethe-lattice and Sherrington--Kirkpatrick (SK) glasses with up to 24 spins. It is observed generically that a trajectory first shifts its weight to one of the two mirror halves of the zero-field measure and then to the glassy classes inside it. These classes appear near the glass transition, keep their identity on cooling and are absent in a ferromagnet on the same graphs. Sparse (Bethe) and dense (SK) glasses differ in how often and how strongly such classes exist, not in how trajectories commit to them. For a generator that takes finitely many steps, the protocol matters through the late, local stage rather than the macroscopic decisions. Sampled posteriors at N=32,64 and small trained denoisers show the same sequence.

cond-mat.dis-nn · cond-mat.stat-mech · cs.AI · stat.ML

新论文 · v1arXiv:2611.23606

VIBRA: Backward-Compatible Cross-Modal Retrieval with Consensus Barycenters

Shubing Yang, Xutong Liu, Dongfang Zhao

原文摘要

Backward-compatible retrieval enables a new encoder to query the gallery that an old model has already encoded, so that a cross-modal retrieval system can be upgraded without re-encoding billions of items. Existing compatible methods either fit the old query and stay near the accuracy of the old model, or run the old and the new encoder for every query. We propose VIBRA, which matches relevance on the old gallery, corrects the errors of a single model with the barycenter of several views, which is itself a query in the old space, and trains the new encoder to inherit this consensus, so that models absent at deployment still shape every query. We show that the barycenter gains margin over the average of its views exactly when their hardest irrelevant items differ, and we characterize the share of this gain that one encoder can reach. On five benchmarks with five upgrades among six CLIP, MetaCLIP and SigLIP2 backbones, VIBRA is the best compatible method in all 50 settings, improving Recall@1 by up to 5.6 points over the strongest baseline and by up to 18.0 points over the old model, while adding less than 1 ms to the latency of the new encoder.

cs.CV · cs.IR

版本更新 · v2arXiv:2611.02461

Training Autoregressive Language Models on Rounded, Bounded, and Censored Numerical Labels via Exact Likelihood

Jingquan Yan, Yuwei Miao, Yang Xie, Junzhou Huang

原文摘要

Numerical labels often specify a set of possible values: a measurement is rounded, a laboratory test reports only a bound, or a program is stopped at a timeout. We introduce boundary marginalization, the first method that trains an autoregressive language model on the exact likelihood of such observations through its existing digit tokens. A fixed-width, order-preserving numeral representation groups consecutive grid values under shared digit prefixes. An interval is a union of such groups, so its exact probability and gradient follow from at most two boundary paths, the successive digit prefixes of its endpoints, each of length logarithmic in the number of grid values. The resulting objective unifies precise, rounded, bounded, and censored supervision and trains digit decisions at the resolution supplied by each observation. The same computation supports exact distributional queries and unbiased gradients for the continuous ranked probability score on exact labels. Experiments show recovery of a conditional distribution from rounded and censored reports alone, improved likelihood on naturally censored molecular measurements, and more accurate code latency distributions on two backbones. Exact interval updates remain tractable as the numerical support grows to one million values.

cs.LG

版本更新 · v2arXiv:2604.17283

HorizonBench: Long-Horizon Personalization with Evolving Preferences

Shuyue Stella Li, Bhargavi Paranjape, Kerem Oktar, Zhongyao Ma, Gelin Zhou, Lin Guan, Na Zhang, Sem Park 等 12 位作者

原文摘要

Personal assistants now talk with the same user for months, and users' preferences change as their lives change; an assistant that keeps serving a preference the user has outgrown fails that user. Real conversations do not record when or why a preference changed, and existing benchmarks either hold preferences fixed or have the user state the change, so they cannot tell whether a model forgot what the user said or failed to update its belief about the user. We introduce HorizonBench and its data generator, which samples how a user's preferences change and generates six months of conversation from that sequence; each change follows a life event that the user mentions without stating the new preference. A human longitudinal preference dataset that we collect and release, 83,024 ratings from 160 people over 13 weeks, sets how often and how much life events change preferences. HorizonBench contains 4,245 questions from 360 users, and when a preference has changed, its earlier value is one of the answer options. All 25 frontier models we evaluate choose the outdated preference more often than evenly spread errors would predict, and the best reaches 52.8% accuracy. Two of the newest models score no higher when given only the relevant conversations than with the full history, yet one added sentence stating the change raises their accuracy by 11 to 22 points, and retrieval and memory methods do not recover the lost accuracy. Remembering what a user said and knowing what the user prefers now are therefore separate capabilities, and HorizonBench, its generator, and the human dataset support research on both.

cs.CL · cs.AI

新论文 · v1arXiv:2611.23601

FutureBench: A Renewable Framework for Evaluating Knowledge-Context Conflict in LLMs

Yi-Cheng Lai, Hen-Hsen Huang

原文摘要

Asking a model to check retrieved text can also tell it which source to trust. We introduce FutureBench, a renewable framework for evaluating knowledge-context conflict using timestamped questions, controlled passage triplets, and no-context probes. Across 3,629 questions and six models, Verify (a prompt combining checking with passage priority) raises false-answer adoption in all five models tested on pre-cutoff events, mainly by displacing answers that were correct under Baseline, which allows both passage evidence and model knowledge. On post-cutoff events, only o4-mini increases adoption (+13.7 percentage points). A four-prompt comparison on 902 post-cutoff questions finds that passage priority without checking raises adoption, while moving to Verify lowers it in all five models. Adversarial-Aware, which warns of misleading passages and prioritizes model knowledge, restores 82.5-98.9% of displaced pre-cutoff answers with under one point of change in true-passage accuracy. FutureBench supports repeated evaluation on fixed cohorts and extension to new events as models change.

cs.CL · cs.AI

版本更新 · v4arXiv:2303.06705

Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement

Yuanhao Cai, Hao Bian, Jing Lin, Haoqian Wang, Radu Timofte, Yulun Zhang

原文摘要

When enhancing low-light images, many deep learning algorithms are based on the Retinex theory. However, the Retinex model does not consider the corruptions hidden in the dark or introduced by the light-up process. Besides, these methods usually require a tedious multi-stage training pipeline and rely on convolutional neural networks, showing limitations in capturing long-range dependencies. In this paper, we formulate a simple yet principled One-stage Retinex-based Framework (ORF). ORF first estimates the illumination information to light up the low-light image and then restores the corruption to produce the enhanced image. We design an Illumination-Guided Transformer (IGT) that utilizes illumination representations to direct the modeling of non-local interactions of regions with different lighting conditions. By plugging IGT into ORF, we obtain our algorithm, Retinexformer. Comprehensive quantitative and qualitative experiments demonstrate that our Retinexformer significantly outperforms state-of-the-art methods on thirteen benchmarks. The user study and application on low-light object detection also reveal the latent practical values of our method. Code, models, and results are available at https://github.com/caiyuanhao1998/Retinexformer . An online Gradio demo is available on Hugging Face at https://huggingface.co/spaces/CaiYuanhao/Retinexformer

cs.CV

新论文 · v1arXiv:2611.23600

Entropy-Regularized Integrated Gradients for Stable Feature Attribution

Rukmangadh Sai Myana, Sumit Kumar Jha, Yanzhao Wu

原文摘要

Path-based attribution methods like Integrated Gradients (IG) are widely used to interpret neural networks, yet imperceptible input perturbations can drastically alter their attribution maps while leaving model predictions unchanged. We introduce Entropy-Regularized Integrated Gradients (ERIG), a path-based attribution method that intrinsically attenuates gradient irregularities along the integration path using maximum-entropy softmax weighting with temperature parameter $τ$. We quantify the effect of the entropy-regularized weighting on attribution stability by using the Lipschitz properties of the model and its gradients. We decompose the attribution change under an input perturbation into a model-response term, whose bound is $τ$-independent, and a weight-variation term, whose bound decreases at rate $\mathcal{O}(1/(2τ))$. Their ratio $R(τ)$ characterizes the trade-off between gradient information and attribution stability. We further add a new dimension to attribution evaluation by adapting classical noise estimators into two metrics, LINV-C and LINV-P, that quantify attribution noise. Across eleven CNN and Transformer backbones on ImageNet and Oxford-IIIT Pet datasets, our experiments show that, relative to the next-best method, ERIG remains comparable on ranking-based fidelity metrics while improving localization by approximately 24% and attribution stability by approximately 47-fold on average, reaching up to four orders of magnitude improvement over IG, all at negligible additional computational cost.

cs.LG · cs.AI · cs.CV

新论文 · v1arXiv:2611.23598

DuoCL: Dual-Path Online Continual Learning

Jebacyril Arockiaraj, Dhruv Parikh, Rajgopal Kannan, Viktor Prasanna

原文摘要

Online continual learning (OCL) requires learning from a data stream whose arrival rate is independent of model training speed. When training cannot keep pace, computationally expensive gradient-based methods update less frequently, limiting adaptation. Analytic methods reduce this overhead, but their frozen backbones cannot adapt representations to changing distributions. We propose DuoCL, a dual-path OCL framework whose fast analytic path accumulates feature statistics from every incoming minibatch while its slow path periodically adapts the backbone. The slow path adjusts its sample count to the available compute budget without interrupting fast-path learning. Feature alignment compensates for drift in the accumulated classifier statistics. Across four datasets and three computational budgets, DuoCL improves online accuracy by an average of 9.67 percentage points over the strongest gradient-based baseline in each setting. DuoCL consistently outperforms analytic learning under distribution shifts, with gains of up to 4.00 percentage points on CIFAR-C, and achieves higher accuracy than prior methods across disjoint class-incremental, domain-incremental, and Si-Blurry settings.

cs.LG

新论文 · v1arXiv:2611.23596

Efficient Variance-Aware Reinforcement Learning in Time-Inhomogeneous Linear MDPs

Qingyue Zhao, Qiwei Di, Jiafan He, Heyang Zhao, Kaixuan Ji, Quanquan Gu

原文摘要

We study variance-dependent reinforcement learning in episodic time-inhomogeneous linear Markov decision processes (MDPs) with feature dimension $d$, horizon $H$, and $K$ episodes. While recent works have established variance-dependent regret with $\tilde{O}(1)$ deterministic-regime overhead for linear mixture MDPs (Zhao et al., 2023) and worst-case nearly minimax optimal regret $\tilde{O}(d\sqrt{H^3 K} + d^7 H^8)$ for linear MDPs (He et al., 2023),, existing variance-aware analyses for linear MDPs (Li and Sun, 2023; Huang et al., 2023) rely on a coarse concentration step whose resulting regret guarantees retain a polynomial $\tilde{O}(K^{1/4})$ additive term even in deterministic environments. We propose VA-LSVI-UCB++, a computationally efficient algorithm that achieves the variance-dependent regret bound $\tilde{O}(d\sqrt{H\min\{\mathrm{Var}_K^*,\mathrm{Var}_K^π\}}+d^5H^4)$, where $\mathrm{Var}_K^*$ and $\mathrm{Var}_K^π$ denote the cumulative conditional variances of the optimal value function and the played policies' value functions along the realized trajectory. Our result adapts to the minimum of the two realized trajectory variances, recovers the worst-case minimax optimal leading term $\tilde{O}(d\sqrt{H^3 K})$, and collapses to $\tilde{O}(d^5 H^4)$ in deterministic environments, free of polynomial-in-$K$ dependency. At the core of our analysis is a simultaneous three-way reference-advantage decomposition for the optimistic, pessimistic, and squared value function estimators coupled with variance self-bounding and Freedman-type value-difference arguments, which tightens the pessimistic and second-moment confidence radii by a factor of $\tilde{O}(d H)$ and removes the inverse-variance-floor blowup.

cs.LG · math.OC · stat.ML

新论文 · v1arXiv:2611.23591

GRAFT: Graph-Regularized Prototype Fields for Realistic Test-Time Adaptation of VLMs

Maxx Richard Rahman, Wolfgang Maass

原文摘要

Unlabeled test data can improve the zero-shot classifier of a vision-language model, yet transductive and test-time adaptation methods often fall below the zero-shot baseline when only a few vocabulary classes are present in a batch or when streams are correlated. We trace this failure to a shared design: every class owns independent parameters estimated from its own samples, so absent or rare classes are left at biased text anchors or fitted to foreign samples. We propose Graph-Regularized Anchor-displacement Field Transduction (GRAFT), which models the adapted prototypes as text anchors plus a displacement field that is partially pooled over a semantic class graph through a Gaussian Markov random field prior, together with an explicit class-presence model. Inference is closed-form and gradient-free on cached features. Anchor-only shrinkage and a single global shift are the two extreme settings of the prior; absent classes are provably harmonic extensions of the present ones, and the pooling strength can be chosen by empirical Bayes. Under the realistic batch and online protocols on eleven benchmarks and four ImageNet shifts, GRAFT improves over the zero-shot model in every setting and over anchor-based transduction where few classes are present.

cs.CV · cs.LG

版本更新 · v4arXiv:2403.04116

Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis

Yuanhao Cai, Yixun Liang, Jiahao Wang, Angtian Wang, Yulun Zhang, Xiaokang Yang, Zongwei Zhou, Alan Yuille

原文摘要

X-ray is widely applied for transmission imaging due to its stronger penetration than natural light. When rendering novel view X-ray projections, existing methods mainly based on NeRF suffer from long training time and slow inference speed. In this paper, we propose a 3D Gaussian splatting-based method, namely X-Gaussian, for X-ray 3D reconstruction. Firstly, we redesign a radiative Gaussian point cloud model inspired by the isotropic nature of X-ray imaging. Our model excludes the influence of view direction when learning to predict the radiation intensity of 3D points. Based on this model, we develop a Differentiable Radiative Rasterization (DRR) with CUDA implementation. Secondly, we formulate a principled Radiative Gaussian Volume Querying (RGVQ) method that defines a continuous attenuation field from the original radiative point attributes and enables direct CT volume reconstruction through CUDA-based parallel querying. Thirdly, we customize an Angle-pose Cuboid Uniform Initialization (ACUI) strategy that directly uses the parameters of the X-ray scanner to compute the camera information and then uniformly samples point positions within a cuboid enclosing the scanned object. On novel view synthesis, X-Gaussian outperforms SOTA methods by 6.5 dB while enjoying less than 15% training time and over 73x inference speed. On CT reconstruction, X-Gaussian outperforms SOTA methods by 0.40 dB and 4.34 dB on synthetic and real scenes, while achieving 4.30x faster inference of the learned CT volume. Code, models, and datasets are at https://github.com/caiyuanhao1998/X-Gaussian . More video and interactive visualizations are presented on our project page at https://caiyuanhao1998.github.io/project/X-Gaussian . We also built an online Gradio demo page on HuggingFace at https://huggingface.co/spaces/CaiYuanhao/X-Gaussian .

eess.IV · cs.CV

新论文 · v1arXiv:2611.23589

Recoverability, Not Invariance: Certified Safety for Robots at the Limits of Performance

Thomas A. Berrueta, Joshua D. Ibrahim, Gilchrist X. Johnson, John Lathrop, Soon-Jo Chung

原文摘要

Safety certification in robotics typically rests on forward invariance of the deployed controller, a property that demands high-fidelity models at the edge of the operating envelope, exactly where models are least reliable and robots perform best. As a result, many of the behaviors we most want robots to run, from learned policies to aggressive maneuvers at the limits of traction, cannot be certified at all. We introduce recoverability, a contraction-theoretic safety concept that resolves this tension by certifying a robot's ability to reengage a trusted recovery mode rather than the invariance of a deployed behavior. We prove that switching to the recovery mode from anywhere inside a certified tube guarantees exponential convergence, even under disturbances and model error. To decide when to switch, we derive the contraction insertion gradient, the first-order effect of a recovery insertion on the certificate, and embed it in a switching-time program in which feasibility alone guarantees safety and optimality only shapes performance. To supply the certificates, we develop sequential convex synthesis that monotonically grows the certified tube toward the exact viability kernel. We validate our approach in simulated quadrotor flight through uncertain obstacles, where it outperforms invariance-based safety filters, and in hardware deployments aboard a full-scale IndyNXT autonomous racecar, where it repeatedly recovers the car from an aggressive raceline at the limits of handling in the rain. Recoverability provides a certified exit strategy, extending formal safety guarantees to aggressive, learned, and experimental behaviors without requiring their invariance.

cs.RO · eess.SY

版本更新 · v2arXiv:2606.11480

FedRAN: Accurate and Efficient Analytic Federated Continual Learning

Jebacyril Arockiaraj, Dhruv Parikh, Jayashree Adivarahan, Rajgopal Kannan, Viktor Prasanna

原文摘要

Federated continual learning (FCL) enables distributed clients to learn from evolving data streams while retaining knowledge from previously observed tasks. Existing optimization-based FCL methods often rely on repeated local training, incurring communication overhead and feature drift across clients. Analytic alternatives avoid iterative training, but high-dimensional random features used to improve accuracy require communicating a Gram matrix whose cost grows quadratically with feature dimension. Communication-efficient alternatives reduce this cost by statistically reconstructing the Gram matrix from first-order summaries. We propose FedRAN, a low-rank analytic FCL framework that instead compresses the required second-order structure directly through spectral summaries that are merged across clients and tasks. The retained rank explicitly controls the tradeoff between approximation fidelity and communication, reducing second-order communication from quadratic to linear in feature dimension for a fixed rank. FedRAN further supports label scarcity through prototype-based pseudo-labeling. Across CIFAR-100, ImageNet-R, and VTAB, FedRAN improves average accuracy by up to 4.8 percentage points over the strongest baseline, uses 30.6-121.8x less per-client communication, and is 190.3x faster than optimization-based baselines.

cs.LG

新论文 · v1arXiv:2611.23588

ARISE: Practical Self-Evolving Memory for Accurate and Cost-Efficient Enterprise Agents

Jiangyun Zhang, Zhou Tang, Kristen Surrao, Zhiyu Chen, Albert Guan, Tor Nitayanont, Yupei Zhang, Roopali Singh 等 15 位作者

原文摘要

Enterprise LLM agents operate in dynamic environments where foundation models evolve rapidly, workflows update frequently, and deployments need to satisfy accuracy and cost requirements. We propose ARISE (Agent Refinement through Iterative Self-Evaluation), a practical memory architecture in which the agent's memory evolves from its own failures without updating model weights, tools, or workflow logic. ARISE uses the model itself or a teacher model to attribute the failures and propose corrections. Then, ARISE keeps the corrections as retrievable micro memory, consolidates them into macro rules, and accepts a rule update only if held-out accuracy rises. Across 14 enterprise-workflow domains from SOP-Bench and $τ^2$-bench using 5 models, ARISE-Teacher, which uses Claude Opus 4.6 for attribution and consolidation, gains 10.9 pp over the baseline on SOP-Bench and 5.8 pp on $τ^2$-bench. ARISE-Teacher also outperforms GEPA by 4.5 pp on $τ^2$-bench and 1.4 pp on SOP-Bench. With the deployment model as its own attributor, ARISE-Self still gains 10.0 pp on SOP-Bench. ARISE-Teacher uses 4.0% fewer model calls and 5.2% fewer output tokens at comparable per-task cost (-1.0%).

cs.AI · cs.MA

版本更新 · v4arXiv:2511.20851

When Features Beat Noise: A Noise-Driven Hypothesis Testing Method for Feature Selection

Mousam Sinha, Tirtha Sarathi Ghosh, Koushik Biswas, Ridam Pal

原文摘要

Feature selection has remained a daunting challenge in machine learning and artificial intelligence, where increasingly complex, high-dimensional datasets demand principled strategies for isolating the most informative predictors. Despite widespread adoption, many established techniques such as Boruta, Recursive Feature Elimination and other wrapper based methods suffer from notable limitations; some incur substantial computational cost, while others offer no definite statistical driven stopping criteria or assess the significance of their importance scores. This paper proposes a novel feature selection method that addresses these limitations. Our approach introduces multiple random noise features and evaluates each feature's importance against the maximum importance value among these noise features incorporating a non-parametric bootstrap-based hypothesis testing framework to establish a solid theoretical foundation. We establish the conceptual soundness of our approach through statistical derivations that articulate the principles guiding the design of our algorithm. To assess reliability and practical utility, we validated the method on controlled simulations and diverse real-world datasets, where it consistently outperformed established feature-selection approaches including Boruta, Model-X Knockoffs, RFE, LASSO, Elastic Net, and mRMR in recovering meaningful signals. Hence, the method emerges as a robust algorithm for principled feature selection, enabling the distillation of informative predictors that support reliable inference, enhanced predictive performance, and efficient computation.

stat.ML · cs.LG

新论文 · v1arXiv:2611.23585

SPICE: Stochastic Policy for Interaction in Cluttered Environments

Nidhi Parayil, Benjamin Greenland, Thierry Peynot, Chris Lehnert

原文摘要

Agricultural tasks such as harvesting and pruning require robots to reach through dense foliage, where contact is often unavoidable and vision is obstructed. Intermittent contact creates an imbalance between free-space and contact-rich observations, complicating the learning of contact-responsive behaviours. We present SPICE, a tactileconditioned diffusion policy for reaching targets in dense plant canopies using tactile sensing as the sole environmental feedback. SPICE exhibits three behaviours: moving through compliant foliage, manoeuvring around partially obstructing stems, and manipulating branches that block the target path. To the best of our knowledge, SPICE is the first tactile-conditioned diffusion policy for target reaching through physically cluttered plant canopies. Across over 180 real-robot trials, SPICE was evaluated against tactile-conditioned, image-conditioned, and reactive-control baselines. Spatial tactile information and explicit contact conditioning proved important, with SPICE achieving 95% branch-manoeuvring success versus 45% for the strongest tactile baseline. SPICE also achieved branch manipulation beyond the reactive controller and remained effective under visual occlusion, where the image-conditioned DP failed. Zero-shot transfer across 40 trials on unseen tomato and lime plants achieved 87.5% success rate. These results demonstrate the potential of tactile-conditioned generative policies for interaction in visually occluded plant environments.

cs.RO · eess.SY

版本更新 · v2arXiv:2609.24708

SPARSER: Sparse Variable Projection by Exploiting Separable Structure in Robotic Perception

Nikolas R. Sanderson, Andrew Fishberg, Haoyu Han, Heng Yang, Jonathan P. How, Hanumant Singh, Michael Everett, Alan Papalia

原文摘要

Robotic perception often requires solving large nonlinear least-squares (NLS) problems. While sparsity has been well exploited to scale solvers, separability remains underexploited: some variables (e.g., landmarks) appear linearly in the residuals and admit a closed-form solution once the others (e.g., poses) are fixed. Variable projection (VarPro) exploits this by analytically eliminating the linear variables, yielding a reduced problem with favorable properties. However, VarPro is rarely used in robotic perception, largely because gauge symmetries (e.g., invariance to global shifts and rotations), common in perception, complicate standard VarPro approaches. We present SPARSER (Sparsity Preserving Analytic Reduction for Separable Estimation in Robotics), a VarPro scheme for problems with gauge symmetries that jointly exploits separability and sparsity. Via one-time preprocessing, it builds a matrix-free Schur complement operator that evaluates costs, gradients, and Hessian-vector products of the reduced problem and integrates with standard iterative NLS solvers. We characterize the applicable problem class and common special cases admitting further analytical savings. The method extends to robust costs via iteratively reweighted least squares (IRLS): symbolic preprocessing is reused across reweightings, so each IRLS iteration needs only a numerical refactorization. On 42 benchmark datasets spanning pose-graph optimization, range-aided SLAM, sensor network localization, and structure from motion, SPARSER is fastest on 41 on CPU and 35 on GPU, and is the only method to solve all. On 24 real-world multi-robot SLAM datasets with outlier-corrupted loop closures, our robust variant is the only method to solve all and is fastest on each, running 1.1-3.1x faster than the graduated non-convexity (GNC) solver in GTSAM. We release open-source C++ code and all datasets.

cs.RO

版本更新 · v2arXiv:2611.20382

Signs of Wear: Evaluating Intelligent Speed Assistance Under Synthetic Adverse Conditions

Johannes Fabian Hahn, Mao Shan, Julie Stephany Berrio Perez

原文摘要

Intelligent Speed Assistance (ISA) systems rely on cameras to recognize speed-limit signs, yet existing benchmarks underrepresent the weathered, dirty, and overgrown signs commonly encountered on rural roads. We use generative image editing to introduce different forms of wear into real street-level images of speed-limit signs. The resulting ISA-Wear dataset contains paired original and edited images. Guided by text instructions, a multimodal image-editing model adds snow, rust, vegetation, faded paint, or mud to the speed-limit sign in a street-level frame at three severity levels. Where appropriate, the surrounding scene is adapted as well, and the viewpoint is kept. Every edited frame has an unedited counterpart, and we only evaluate frames whose original is recognized correctly, so any failure can be attributed to the wear. Since the model alters the sign's geometry in 21\% of the edits, all edits are filtered by a geometric check and a manual review. Severity is measured as the LPIPS distance between the original and the edited sign plate. On 716 worn frames, we find that in detect-then-read pipelines, wear breaks detection before it breaks reading. The detector finds only 62\% of the worn signs, even though it finds every one of them in the original frames. Missed detections account for 78--87\% of failed reads, a pattern that a zero-shot detector shares. Given the annotated sign box, as in the crop-based benchmarks, a classifier still reads 78\% of the worn signs, but only 56\% when it has to rely on the detector

cs.CV · eess.IV

版本更新 · v2arXiv:2611.10923

Prescriptive Learning of Linear Policies with Feasibility Guarantees for Binary Decision-Making

Farzaneh Pourahmadi, Trine Krogh Boomsma, Pierre Pinson

原文摘要

Binary decision-making under uncertainty arises across a wide range of applications, including energy systems scheduling, transportation, and workforce planning. While machine learning has been increasingly applied to accelerate or replace mixed-integer solvers in such settings, existing approaches rely on predictive learning, training models to reproduce optimal decisions from labeled data, which lacks knowledge of counterfactual outcomes and provides no guarantees that the resulting decisions will be feasible. This limitation is further compounded under distributional shift, where policies trained on historical data may produce systematically infeasible decisions. We propose a prescriptive learning framework for binary decision-making that addresses both limitations. Rather than predicting optimal labels, the framework jointly optimizes over linear decision policies and feasible assignments across all training scenarios, allowing feasible alternatives and their operational performance to be considered directly during training. We further extend the framework to a distributionally robust chance-constrained formulation using a Wasserstein ambiguity set, which enforces feasibility with a prescribed probability under the worst-case distribution in the ambiguity set and enables a tunable trade-off between robustness and solution quality. We demonstrate the framework on two case studies, namely a unit commitment problem and a staff allocation problem. Out-of-sample experiments under test distributions that either match or differ from the training distribution show that the robust model is more conservative when the two distributions coincide, while under distributional shift it substantially reduces unmet demand and lowers total cost by up to 76.5% relative to classical predictive learning.

cs.LG · stat.ML

版本更新 · v4arXiv:2601.16823

Disentangling generalization and memorization in large language models using chess

Leonard S. Pleiss, Maximilian Schiffer, Robert K. von Weizsaecker

原文摘要

Large Language Models (LLMs) exhibit remarkable capabilities, yet it remains unclear to what extent these reflect sophisticated recall or genuine reasoning ability. We introduce chess as a controlled testbed aimed at disentangling these faculties. Leveraging the game's structure and scalable engine evaluations, we construct a taxonomy of positions varying in density of relevant priors -- ranging from common states solvable by memorization to completely novel ones requiring generalization. Crucially, our approach achieves this distinction without requiring explicit knowledge of the models' training data. Applying this taxonomy, we combine a longitudinal analysis of the GPT lineage with a rigorous evaluation of contemporary models, including Claude Opus and Gemini. Our analysis reveals a steep gradient: performance consistently degrades as the density of relevant priors decreases. Notably, for tasks with few relevant priors, base model performance regresses to the random-play baseline, and all models propose illegal moves at sharply increasing rates, indicating that they fail to reliably apply the fixed rules of the game in unfamiliar positions. While newer models improve, progress slows significantly for tasks with sparse priors. Furthermore, while reasoning-augmented inference improves performance, its relative marginal benefit per token decreases in the absence of relevant priors. These results suggest limitations in systematic generalization, highlighting the need for mechanisms beyond scale to achieve robust performance when deprived of relevant priors.

cs.CL · cs.AI

新论文 · v1arXiv:2611.23581

ExiST: Existence-Aware Self-Training for Semi-Supervised Multi-Organ Segmentation

Maxx Richard Rahman, Prakhar Kumar, Wolfgang Maass

原文摘要

Semi-supervised multi-organ segmentation should learn more than a dozen organs from a handful of labeled scans, and the smallest organs occupy less than one percent of the foreground. We identify a failure mode of self-training that is specific to this regime. When a teacher misses a small organ in a scan, every voxel of that organ receives the confident pseudo-label background, and the student is trained toward the organ absence. Repeated over many scans, this loop extinguishes tail organs. In a pilot study, removing the gallbladder from the pseudo-labels reduced its Dice on AMOS from 36.5 to 1.0. We argue that a missing organ should be treated as unresolved rather than absent and propose Existence-aware Self-Training (ExiST). It builds pseudo-labels by leave-one-out consensus of independently trained networks, screens them with a quality gate on validation scans, and infers, per scan and per organ, whether the organ was found. For every unresolved organ, the background voxels of that scan receive the set-valued target, trained with a marginal cross-entropy that accepts either answer and a Dice term that skips uncertain voxels. We show that this loss never pushes a candidate organ toward absence and never favors one member of the set, which leaves the decision to labeled evidence. ExiST outperforms the current state-of-the-art methods and reaches 77.1 mean Dice on Synapse with 20% labeled scans and 75.9 on AMOS with 5% labeled scans.

cs.CV · cs.AI

新论文 · v1arXiv:2611.23578

DOCK: Dual-Stream-Inspired Self-Supervised Object-Centric Representations Grounded in Robot Kinematics

Pengju Liu, Caiwen Ding

原文摘要

Latent-space planners select actions by comparing the embedding of a predicted future image with that of a goal image. This assumes that distance in the embedding reflects how far the scene is from the goal. We profile this assumption with simulator-executed futures, which removes prediction error. For six frozen DINO and V-JEPA encoders, feature distance barely tracks the object's distance to its goal: the rank correlation is at most 0.11, against 0.87 for object-mask centroids. It is dominated by background and robot patches, and frozen-feature readouts capture the arm far better than the object. Inspired by the ventral (what) and dorsal (where/how) visual streams, we propose DOCK, which learns an object representation whose changes agree with measured physical motion. A grasped object moves with the gripper, so forward kinematics on the joint angles gives a proxy for the object's displacement without annotation. From 9,951 held-object transport trajectories in 21 simulated kitchen scenes, we mine 404K displacement pairs and train three components: an object token pooled from patch features (what), a spatial ruler that makes differences of readout coordinates equal to measured displacements (where), and a dynamics predictor over object tokens (how). Used as a planning cost, the learned representation places the object in 15 of 21 tasks, as many as an oracle that reads the true object position, while mask geometry reaches 10 and frozen feature distance 9. It still solves the most tasks when the unseen robot arm is visible, and its ranking transfers to held-out layouts with unseen object instances and categories without any adaptation.

cs.CV · cs.RO

新论文 · v1arXiv:2611.23575

LuxTac: A Flexible, Scalable, and Open-Source Optical Taxel Array with Distributed Three-Axis Force Sensing for Tactile Robot Learning

Md Rakibul Islam Prince, John Pelan, Zhiyuan Zhang, Adyaa Khera, Katherine Pesetski, Adeesh Desai, Akimizu Sugiyama, Minwoo Ki 等 17 位作者

原文摘要

Low-cost tactile arrays have made touch a practical input for robot learning, but piezoresistive designs sense only pressure, while camera-based sensors that also resolve shear are too bulky to tile over a gripper. To solve this problem, we present LuxTac, a flexible, scalable optical taxel array, about 3.5 mm thick and built from off-the-shelf parts. Each taxel is a digital RGBC light-to-digital converter under a translucent white silicone layer capped by an opaque black film, so the back-scattered LED light falls monotonically with local indentation depth. The same board accepts two interchangeable gel cartridges: a plain one for normal sensing, and one with colored walls that encodes the local shear in the color of the returned light, with no camera, magnets, or bump overlay, making LuxTac, to our knowledge, the first optical taxel array to resolve shear at individual taxels. Characterized with an automated CNC indenter and a six-axis force/torque sensor, the normal cartridge responds linearly to force ($R^2$ = 0.999) from 104 mN to at least 5.8 N, with 2.0% repeatability, 5.9% hysteresis, and a taxel-to-taxel variation of 6-10% after normalization. With the shear cartridge, per-taxel models estimate the three-axis force at every taxel; across three indenter shapes and nine held-out sessions, the summed estimates reach $R^2$ = 0.96/0.96/0.92 in x/y/z, each taxel's estimate 0.92/0.93/0.94, and the median shear-direction error is 4.8 degrees. Adding LuxTac pressure readings to an Action Chunking Transformer policy substantially improves peg-in-hole success over a vision-only baseline. Design files, code, and videos are available at https://luxtac.github.io.

cs.RO

版本更新 · v3arXiv:2605.09165

Sparse Layers are Critical to Scaling Looped Language Models

Ryan Lee, Jacob Biloki, Edward J. Hu, Jonathan May

原文摘要

Looped language models repeat a set of transformer layers through depth, reducing memory costs and providing natural early-exit points at loop boundaries. However, looped models do not scale as favorably as standard transformers with unique layers. We compare standard and Mixture-of-Experts (MoE) transformers, with and without looping, and find two main results. First, we find Looped-MoE models scale better than the standard baseline while dense looped models do not. We trace this to routing divergence between loops: in Looped-MoE models, different experts are activated on each pass through the same shared layers, recovering expressivity without additional parameters. Our second finding is that looped models have better compute-quality trade-offs with early exits than standard models. Because each loop ends with the same layers that produce the final output, loop boundaries are superior exit points, as confirmed by earlier output convergence at these points. In sum, we provide a clear direction for scaling looped models: a Looped-MoE model with early exits can not only beat standard transformers at scale, but also enable significant memory and inference savings with minimal degradation in quality.

cs.LG · cs.CL

新论文 · v1arXiv:2611.23572

Receiver-Conditioned Clarification for Multi-Agent Food Assistance

Kaiwen Shi, Zheyuan Zhang, Changzhi Liu, Han Bao, Yanfang Ye

原文摘要

Food insecurity creates a pressing need for guidance that helps households find usable food resources and assess food choices in light of their circumstances. Such guidance must connect eligibility requirements, practical access constraints, and dietary needs rather than return isolated listings or generic nutritional advice. Multi-agent food assistants can coordinate these tasks, with uncertainty indicating when clarification or verification is needed before a recommendation. However, uncertainty can be lost across agent handoffs, allowing tentative interpretations to propagate as facts and obscuring opportunities for correction. Moreover, confidence that a service requirement has been interpreted correctly is not confidence that a recommendation satisfies the user's needs; local confidence cannot simply be reused as downstream reliability. We introduce an inference-time, receiver-conditioned clarification framework that preserves shared premise identities and replays consistent interpretations across dependent agents. Each receiver exposes admissible decisions and remaining evidence obligations, so question relevance reflects both decision changes and missing support. Information questions and user-confirmable fallback adjustments are evaluated together with their anticipated follow-up interactions under shared budgets. This structure connects clarification to jointly supported plans for resource navigation, nutritional reasoning, and supply-side planning.

cs.AI

新论文 · v1arXiv:2611.23570

Safe to Omit, Worth Omitting? Keeping the Answer and Cutting Latency When an LLM Agent Skips Another's Message

Xinyang Li, Chih-Hsuan Yang, Xiaolong Ma, Anjir Ahmed Chowdhury, Vikram Vasudevan, Rajeev Thakur, Feng Yan

原文摘要

In multi-agent systems, a receiver agent often waits for a helper agent's message (text or its latent KV cache), which can improve performance but adds latency. We study when a receiver agent can skip the message safely (the final answer rarely changes) and beneficially (the time saved exceeds the cost of deciding). Our mechanism reads the receiver agent's confidence without the message and uses a finite-sample test to certify a threshold at which, with high probability, at most 5% of skipped answers change; if none passes, the system keeps communicating. We test it on OpenBookQA, ARC-Challenge, and MMLU-Pro with three Qwen model pairs, on cross-family agents, and on SQuAD and GSM8K. Four insights emerge. First, oracle headroom is weak evidence that messages help: control inputs without answer-specific content, matched to change answers as often as real messages, reproduce a median 76% of the oracle's gain. Second, whether a message can be skipped depends on how often and how predictably it alters the answer, not on its accuracy; every certified KV-cache path is less accurate than the receiver agent alone. Third, where text messages help, skipping keeps most of their gain: on unseen questions in the four such settings, the policies skip 59 to 80% and keep an estimated 76 to 95% of the gain. In two prospective tests with all rules fixed in advance, our mechanism skips a three-agent system's verifier on 39.9% of sealed questions, keeping 12.55 of its 12.80-point gain, and a 32B helper on 68.4% of held-out questions, keeping its whole gain. Fourth, safety does not determine efficiency: at batch size one, skipping text saves hundreds of milliseconds per query and skipping KV cache far less. Certification extends to SQuAD but not to GSM8K. In eleven tests on unseen questions, every certified policy we could test kept its change rate's 95% upper bound below 5% under our answer parsers.

cs.LG · cs.CL

新论文 · v1arXiv:2611.23567

Panini- Feasible Grammar For Robot Designs

Mayukh Debnath, Manan Roy Choudhury

原文摘要

Symbolic methods make robot designs interpretable but often overlook continuous geometry; learned methods handle geometry but offer less transparent structure. We introduce a typed production grammar that uses case-role relations, parameter inheritance, and specificity-based rule arbitration to generate both manipulation skills and robot morphologies. A geometric realization map translates grammar composition into transformations in SE(3), behaving as a monoid homomorphism when inheritance is inactive and exhibiting a measurable defect when inheritance is enabled. The grammar provides a compact representation, and its arbitration decisions can be recovered from geometric containment (agreement 0.905 +/- 0.062 across 10 seeds, versus 0.611 +/- 0.090 for a Euclidean control). We also introduce PANINI, a cross-entropy search method over grammar-based morphology representations. Across 30 methods and 24 seeds, PANINI achieves the best mean rank but is not statistically distinguishable from strong generic optimizers. Its main demonstrated advantage is therefore structural rather than optimization performance: grammar-generated designs are legal by construction, and coordinated limb placement produces 95% jointly feasible edits, compared with 55% for range-constrained resampling and none for flat parameterization in 6,000 draws. These results show how typed grammars can make robot generation more interpretable and geometrically coordinated, without implying that every feasible design will locomote or that grammar-based search universally outperforms generic optimizers.

cs.RO · cs.AI

版本更新 · v3arXiv:2602.15198

Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems

Mason Nakamura, Abhinav Kumar, Saswat Das, Sahar Abdelnabi, Saaduddin Mahmud, Ferdinando Fioretto, Shlomo Zilberstein, Eugene Bagdasarian

原文摘要

Multi-agent systems, where LLM agents communicate through free-form language, enable sophisticated coordination for solving complex cooperative tasks. This surfaces a unique safety problem when a group of agents forms a coalition and colludes to pursue secondary goals and degrade the joint objective. In this paper, we present Colosseum, a framework for auditing LLM agents' collusive behavior in multi-agent settings. We ground how agents cooperate through a formal multi-agent decision-making framework and measure action-based collusive behavior in actions via regret relative to the cooperative optimum and compare it with communication-based collusive behavior. Colosseum enables audits of LLM agents for collusion under benign settings, different coalition objectives, persuasion tactics, and network topologies. We then introduce a new behavioral probe by creating secret communication channels between agents, showing that most out-of-the-box models exhibit a propensity to collude under this probe, which we term emergent collusion. Furthermore, we discover ``collusion on paper'' when agents plan to collude in text but often pick non-collusive actions. Colosseum provides a new way to audit collusion in cooperative multi-agent systems while presenting observations about how collusion emerges, what affects collusion efficacy, and which strategies may mitigate it.

cs.MA · cs.AI · cs.CL

新论文 · v1arXiv:2611.23564

LProp: Propagating Latent Uncertainty through Evidence-Conditioned Belief Revision in LLM Agents

Kaiwen Shi, Zheyuan Zhang, Weixiang Sun, Han Bao, Colby Nelson, Yanfang Ye

原文摘要

When LLM agents pass intermediate judgments downstream without uncertainty, later decisions may treat tentative assumptions as facts. Effective uncertainty propagation must preserve information for correction and update inherited beliefs as new evidence arrives. Yet scalar scores omit information needed for revision, while detailed descriptions and reflection incur additional costs. We introduce Latent Uncertainty, a latent-space estimator that preserves uncertainty-relevant information without lengthy descriptions. Building on this, we propose LProp (Latent Uncertainty Propagation), which revises inherited answer distributions using latent representations and new evidence without additional trajectory sampling. We evaluate both methods across multiple-choice, yes/no, open-ended question answering, and mathematical reasoning tasks. Our approach outperforms baselines on most metrics, while LProp achieves the lowest mean inference-token usage in all eight propagation settings. Matched feature ablations further demonstrate that inherited latent content improves error recovery beyond answer probabilities or model capacity alone.

cs.AI