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

+1673新增论文
+1257其中 AI 相关
+198已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-14 03:51 · 全站最近入库：2026-11-13 20:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-13 04:14 — 2026-11-14 04:14（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：2026-11-14 03:51最近发现新增版本：2026-11-13 20:44库内论文最新更新时间：2026-11-13 02:59

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

23,348 已收录论文19,580 AI 相关6,727 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 24 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-14 03:50（北京时间）
新论文 · v1arXiv:2611.16956

Lara Mini Base: Language Diversity as a Resource, Not a Trade-off

Translated, Maria Pia Adinolfi, Isabelle Andrieu, Grazia Fiorella Anfuso, Melania Annunziata, Daniele Antonini, Marta Arena, Luca Barone 等 206 位作者

原文摘要

General-purpose language models are trained mostly on English: over open models we review, at most, non-English pretraining data makes up only a 12% share. Models built for European languages give them far more, but score well below general-purpose models of the same size. A common concern is that, in small models, languages compete for capacity. We present Lara Mini base, a model trained from scratch on 6T tokens in English and 44 other languages, which together cover all 24 official languages of the European Union. As training progresses, the 44 other languages together come to outweigh English. To give these languages enough capacity at low cost, Lara Mini base uses a mixture of experts architecture with 7.2B total and 0.6B active parameters. Among open base models with up to 2B active parameters, it achieves the highest average score across standard English, multilingual, math, and code benchmarks, ahead of models trained on 4 to 6 times as many tokens. Its margin is largest on multilingual benchmarks in the languages it supports and on math benchmarks. It supports contexts of up to 128k tokens. We find that our MoE architecture reduces capacity competition between languages. For a single user on one GPU, without quantization, it generates text at least 1.8 times faster than any model with a higher average score. We release the weights of Lara Mini base under the CC BY-NC-SA 4.0 license. In addition, we will release T-HellaSwag, a higher-quality machine translation of the commonsense reasoning benchmark HellaSwag into 110 language variants.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.01266

Fast approximation and learning of binary classification tasks in o-minimal structures using ReLU neural networks

Clemens Kinn, Philipp Petersen

原文摘要

We study binary classification tasks whose decision sets are given by definable sets in o-minimal expansions of the real field. Motivated by the cell decomposition theory of definable sets, we introduce traceable sets that isolate the analytical properties of definable sets used for fast approximation by ReLU neural networks. Under uniform bounds on the number of cells and a suitable extension assumption for the boundary functions, we prove that classifiers can be approximated in $L^p$ up to accuracy $\varepsilon>0$ by ReLU neural networks of size $\mathcal{O}(\varepsilon^{-p(n-1)/m})$, with depth independent of $\varepsilon$ and polynomially bounded weights. This establishes quantitative approximation rates for suitable definable collections in o-minimal structures using ReLU neural networks. Furthermore, the stated approximation rates are also derived for definable maps under similar geometric assumptions on their smoothness domains. We then obtain statistical learning rates for empirical risk minimization with hinge loss over the approximating ReLU neural network classes. For $N$ uniformly distributed samples, the predicted classifiers achieve expected misclassification error of order $N^{-m/(m+n-1)}$ up to an arbitrarily small polynomial loss.

math.LO · cs.LG · math.FA

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2506.06361

Tactile MNIST: Benchmarking Active Tactile Perception

Tim Schneider, Guillaume Duret, Cristiana de Farias, Roberto Calandra, Liming Chen, Jan Peters

原文摘要

Tactile perception has the potential to significantly enhance dexterous robotic manipulation by providing rich local information that can complement or substitute for other sensory modalities such as vision. However, tactile sensing is an inherently local sensor modality, providing information only at the points of contact. This strict locality necessitates the use of active perception techniques to acquire useful, task-relevant information from manipulated objects or the environment in general. Hence, the agent must actively guide sensors toward regions with more informative or significant features and integrate this information over time to understand a scene or complete a task. While active perception and tactile sensing methods have received significant attention recently, both fields lack standardized benchmarks. To bridge this gap, we introduce the Tactile MNIST Benchmark Suite, an open-source, Gymnasium-compatible benchmark specifically designed for active tactile perception tasks, including classification, localization, pose estimation, and volume estimation. Our benchmark suite offers diverse simulation scenarios, from simple toy environments to complex tactile perception tasks using vision-based tactile sensors. Furthermore, we offer a comprehensive dataset comprising 13,580 synthetic 3D MNIST digit models and 153,600 real-world tactile samples collected from 600 3D-printed digits. Using this dataset, we train a CycleGAN for realistic tactile simulation rendering. By providing standardized protocols and reproducible evaluation frameworks, our benchmark suite facilitates systematic progress in tactile sensing and active perception more broadly.

cs.RO · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09887

关于 ReLU 网络集合的（非）闭性

On the (non-)closedness of the set of ReLU networks

Eloi Martinet, Leon Bungert

AI 速读 基于摘要

作者证明单隐层 ReLU 网络集合在 Sobolev 空间中是弱闭的，而宽度有界的双隐层 ReLU 网络集合在 Sobolev 空间与连续函数空间中均不闭。

cs.LG · math.CA · math.FA · math.NA · math.OC

arXiv ↗PDF ↗
查看原文摘要

We prove that the set $\mathcal{N}_N$ of ReLU networks with one hidden layer and at most $N\in\mathbb N$ neurons is weakly closed in $W^{1,p}(Ω)$, for a bounded connected open set $Ω\subset\mathbb R^d$. Consequently, every coercive, weakly lower semicontinuous energy on this space attains its minimum over $\mathcal{N}_N$. This covers the Deep Ritz method with convex integrands, Sobolev training and Lipschitz learning. Moreover, as the weight decay parameter tends to zero, minimizers of the regularized problem converge, up to subsequences, to minimizers with minimal parameter norm. We also prove that the set of ReLU networks with two hidden layers of bounded widths is not closed in $W^{1,p}(Ω)$ or in $C(\overlineΩ)$. This disproves a conjecture of Petersen, Raslan and Voigtlaender.

新论文 · v1arXiv:2611.08857

STRIDE: Learning Humanoid Locomotion in Minutes with Acceleration-Based Rewards

Nico Bohlinger, Jan Peters

原文摘要

Learning locomotion directly on a humanoid robot is a promising direction to avoid the sim-to-real gap. However, locomotion rewards in Reinforcement Learning (RL) typically track the base velocity, which cannot be measured onboard without an external motion capture system or well-calibrated state estimator. This is why we introduce \method{}, which learns humanoid locomotion from minutes of samples with a reward that only requires the onboard Inertial Measurement Unit (IMU). Instead of tracking the base velocity, STRIDE rewards the robot for following a commanded acceleration profile. To learn efficiently from this reward, we use the off-policy RL algorithm XQC and combine a high gain setting for the joint position controllers with left-right symmetry augmentation. In simulation, STRIDE learns to walk on the Unitree G1 and Booster T1 humanoids within 14 minutes of samples. Compared to learning without these two components, it reduces the falls during training by 81%, while without them the robot learns only in over an hour.

cs.RO · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08814

It Takes Two to Tangram: Multi-Agent Object Centric Reinforcement Learning for Assembly

Paul Knaußt, Kay Pompetzki, Nico Bohlinger, Niklas Funk, Cristiana de Farias, Rolf Findeisen, Jan Peters

原文摘要

Geometric assembly requires fine spatiotemporal coordination to place parts without causing collisions or deadlocks under tight clearances. To address this, we present an object-centric reinforcement learning framework that treats each part as an agent and learns a shared policy for continuous assembly control. A graph neural network represents the pieces, their target poses, and their spatial relationships, and predicts translational and angular velocities for each component. Per-agent proximal policy optimization with a centralized graph critic directly learns motion and temporal coordination within a single feedback policy. We study this formulation through planar Tangram assembly, where pieces must slide and rotate into a given configuration while remaining on the assembly surface. Procedural generation of target configurations and randomized initial arrangements support training and evaluation across diverse assembly problems. Our experiments isolate the roles of relational structure and multi-agent optimization, and compare learned control with sampling-based planning. We demonstrate concurrent assembly in simulation and transfer the policy to sequential execution on a real robot, as our object-centric formulation decouples learned assembly coordination from low-level physical control. Project page: https://tangrambench.org/

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2601.21623

LAMP: Look-Ahead Mixed-Precision Inference of Large Language Models

Stanislav Budzinskiy, Marian Gloser, Tolunay Yilmaz, Ying Hong Tham, Yuanyi Lin, Wenyi Fang, Fan Wu, Philipp Petersen

原文摘要

Mixed-precision computations are a hallmark of the current stage of AI, driving the progress in large language models towards efficient, locally deployable solutions. This article addresses the floating-point computation of compositionally-rich functions, concentrating on transformer inference. Based on the rounding error analysis of a composition $f(g(\mathrm{x}))$, we provide an adaptive strategy that selects a small subset of components of $g(\mathrm{x})$ to be computed more accurately while all other computations can be carried out with lower accuracy. We then explain how this strategy can be applied to different compositions within a transformer and illustrate its overall effect on transformer inference. We study the effectiveness of this algorithm numerically on GPT-2 models and demonstrate that already very low recomputation rates allow for improvements of up to two orders of magnitude in accuracy.

cs.LG · math.NA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.16828

Prediction-Intervention Games and Invariant Sets

Linus Kühne, Felix Schur, Jonas Peters

原文摘要

We consider the following two-player game: using observational data, the leader chooses a prediction function for a response variable $Y$ from given covariates. The follower then reacts with an intervention on some covariates in the underlying structural causal model to maximize their own objective. The leader knows the intervention targets, but may have limited knowledge of the follower's objective. We call this setup a prediction-intervention game, a special case of a Stackelberg game. Finding an optimal strategy for the leader is generally difficult. To avoid severe performance loss, the leader may base their prediction on the causal parents of $Y$, or more generally on an invariant subset of covariates. We prove, for two common classes of follower objectives, that predictors based on the stable blanket, an invariant subset, are at least as good as those based on the causal parents. We further upper bound the leader's post-intervention risk by a worst-case risk over allowed interventions and strengthen existing distribution generalization results to analyze this bound: we give sufficient conditions under which stable-blanket predictors are worst-case optimal, and show by examples that these conditions cannot in general be dropped. Finally, we discuss practical strategies for settings with known and unknown graph, and test them on simulated and real-world data.

stat.ML · cs.AI · cs.LG · stat.ME

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.06233

Anchor PCA

Benedikt Seiter, Anya Fries, Julius von Kügelgen, Jonas Peters

原文摘要

Principal component analysis (PCA) is one of the most widely used unsupervised dimension reduction techniques. We study PCA for data from multiple related domains. Since principal components generally differ across domains, one way to obtain a shared low-rank embedding is to perform PCA on the pooled data. However, this approach can focus on spurious directions that exhibit high variation in only a few domains. To find a robust embedding that still explains most variance in unseen but similar domains, we propose instead to focus on shared directions of variation. To this end, we introduce Anchor PCA which trades off overall explained variance with agreement between the shared and domain-specific low-rank embeddings. Anchor PCA amounts to PCA on a modified target matrix and thus can be solved efficiently. Moreover, we show that Anchor PCA recovers a maximal invariant subspace and admits a minimax reconstruction interpretation under bounded domain-specific covariance inflations. On simulated and real-world data with temporal distribution shift, we demonstrate, respectively, that Anchor PCA recovers the maximal invariant subspace and yields embeddings that explain more variance on unseen domains than the pooling baseline and a worst-case alternative. Taken together, these findings establish Anchor PCA as a promising approach to robust unsupervised dimension reduction from multi-domain data.

stat.ML · cs.LG · stat.ME

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.02194

Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards

Christian Scherer, Joe Watson, Theo Gruner, Daniel Palenicek, Ingmar Posner, Jan Peters

原文摘要

Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation. Reinforcement learning (RL) can be used as a means to finetune these policies further using additional experience. An open question is whether RL is more sample-efficient than collecting more expert demonstrations. Prior work has finetuned large pretrained policies in a scalable fashion by applying RL to a smaller residual policy that corrects the pretrained model. However, for typical sparse reward tasks, RL algorithms can struggle to optimize the behavior in a sample-efficient manner. We explore inverse reinforcement learning, where a dense reward function is learned from expert demonstrations, potentially reducing the challenge of RL finetuning. We specifically consider coherent imitation learning, an IRL method that facilitates improvement of the BC policy by using a specific learned reward formulation with theoretical guarantees for imitation learning. We show that our IRL method maintains or improves the performance of pi-0.5 on all six sparse manipulation tasks and achieves a $\geq 90\%$ success rate on five out of six complex manipulation tasks, outperforming RL-based baselines using sparse rewards. We also demonstrate real-world learning on a robot manipulation task, finetuning pi-0.5 to success with less than 30 minutes of environment interaction time. By ensuring our initial pretrained finetuning policy is optimal for our initial reward and critic, our method circumvents the initial drop commonly seen in RL finetuning and enables faster improvement.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.26341

Scaling Nonlinear Optimization: Many Problems One GPU

John Viljoen, Johanna Haffner, Lasse Peters, Masayoshi Tomizuka, Negar Mehr

原文摘要

Modern GPUs and software frameworks have made sampling-based methods, such as reinforcement learning and model predictive path integral control, increasingly popular in robotics. However, the logic these methods can execute per sample is limited to what has been implemented on the GPU. Nonlinear programs (NLPs) are one of the most expressive tools in robotics, reliably minimizing a cost while exactly enforcing general constraints. NLP optimizers were among the field's main workhorses, but were not designed for modern GPU hardware. Embedding NLPs such as trajectory optimization and inverse kinematics directly within each sample would be highly valuable, yet the only current option is to call a CPU solver per sample, possibly in parallel on a multi-core CPU. This bottlenecks the CPU, requires GPU-to-CPU-to-GPU transfers when the rest of the pipeline resides on the GPU, and leaves the GPU intermittently idle. To address this issue, in this work we present jaxipm, the first GPU-batched solver for generally constrained nonlinear optimization problems. Our approach is a JAX implementation of the battle-tested IPOPT algorithm, facilitated by eliminating control flow through heterogeneous iteration fusion, and minimizing GPU idle time through iteration-level batching. Our implementation enables solving hundreds of NLPs in parallel on a single GPU. We validate jaxipm on a range of quadrotor nonlinear model predictive control benchmarks, where on a single GPU we achieve between 30.7% and 69.9% of the throughput of 64 IPOPT instances running in parallel on a 64-core CPU. open-source codebase: https://github.com/johnviljoen/jaxipm

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02681

HistoTx: Early fusion of H&E images and spatial transcriptomics at varying spatial transcriptomics resolution with self-supervised learning

Alice Driessen, Emil Malmsten, Steffen Wolf, Bernd Illing, Isinsu Katircioglu, Adriano Martinelli, Rolf Stahel, Solange Peters 等 14 位作者

原文摘要

Spatial transcriptomics maps gene expression across tissue sections and, when integrated with whole slide images, jointly captures both morphological architecture and molecular activity to provide a rich, multimodal view of tissue biology. ML approaches combining spatial transcriptomics and WSIs typically learn a mapping from morphological features to molecular profiles via contrastive alignment or supervised fine-tuning of pathology foundation models. In both cases, transcriptomics serves as a training signal rather than a true input modality, leaving inference fundamentally image-driven. We propose an early-fusion vision transformer architecture in which transcript tokens are constructed at arbitrary spatial resolution, merged with image patch tokens, and jointly processed through a shared transformer stack for deep cross-modal interaction. Starting from a pretrained vision-only pathology foundation model, we train HistoTx by continuing self-supervised pretraining on paired image and spatial transcriptomics data and demonstrate that: 1) at inference with image only, performance remains on par with the baseline on most tasks while improving on tasks that inherently benefit from molecular knowledge, such as gene expression prediction; 2) when both modalities are available at inference, jointly providing image and transcript inputs outperforms either modality alone.

cs.LG · cs.AI · q-bio.GN · q-bio.QM

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.18465

GeoCond: A Conditioning-Aware Reliability Adapter for Feed-Forward 3D Reconstruction

David Ahmedt-Aristizabal, Mohammad Ali Armin, Russell Tsuchida, Lars Petersson

原文摘要

Feed-forward 3D foundation models such as VGGT predict cameras, depth, and point maps in a single pass, but can fail silently under low overlap, low parallax, and extreme relative rotation. Stratified analyses over these factors show that these failures are governed by geometric conditioning and are poorly captured by native aleatoric confidence. We introduce GeoCond, a lightweight reliability adapter for frozen feed-forward 3D backbones. GeoCond reads geometric conditioning cues and the backbone's own stability signals and outputs pose-level uncertainty and a refinement gate. During training, it can be supervised by frame-permutation orbit variance, ground-truth pose error when labels are available, or cycle residuals from unlabelled independent pose graphs. At inference, the default head requires only one backbone pass and a small MLP. On VGGT, GeoCond improves out-of-distribution (OOD) AUSE (area under the sparsification-error curve; lower is better) from $0.32$ to $0.20$ over native confidence on held-out outdoor scenes (and to $0.21$ when trained on indoor data only) and avoids the collapse caused by applying bundle adjustment uniformly, without improving on feed-forward poses there. For three of six backbones, cycle-distilled variants provide a ground-truth-free adaptation route, including cases where permutation variance vanishes on equivariant models. The same reliability signal supports gated refinement, pose-graph weighting, calibration, curation, and capture decisions. Reliable feed-forward 3D reconstruction requires not only predicting geometry, but also knowing when that geometry should be trusted.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39073

Certified Access: Test-Time Compute on Conservative Physics-Structured AI Memory

Pratik Jawahar, Riccardo Maggioni, Jonas Petersen, Matteo Cozzi, Gian-Alessandro Lombardi, Marek Gajewski, Camilla Mazzoleni, Federico Martelli

原文摘要

Test-time compute mechanisms, such as retries, confidence-based escalation and non-local routing, are conventionally deployed as black-box additions to trained models. They typically add forward passes or halting heads, but give no structural account of what the extra compute buys or what it costs against the model's stability guarantees. We therefore propose a theoretical and empirical framework for test-time compute on a Latent Dynamics Model used as the memory. When an encoder's latent state $(q,p)$ is advanced by a damped symplectic (velocity-Verlet) step of a learned Hamiltonian, every mechanism that expands access has an exact phase-volume Jacobian, a bounded energy change and an exact latch-transport law. We split reachability failures into escape failures and reach failures. A Lorentz squeeze resolves escape failures by injecting bounded, re-absorbable energy. A gated canonical translation (a one-step channel across $C_T$) resolves reach failures at $\detJ=1$ exactly. We verify this certificate stack on a designed analytic testbed. Reaching just beyond $C_T$ with the squeeze requires energy that grows quadratically in the excess distance. The gated channel's energy cost equals the potential difference between its endpoints, which is zero on the matched channel measured here, and so does not grow with distance in this testbed. An untrained state-replacing map annihilates phase volume and erases stored charge, while the gated channel transports it. On a learned physics-structured memory, we show calibrated compute rationing and evaluate the scaling limits of non-local routing against a physics-free baseline. The main contribution is the formalization and verification of the certificate stack, not benchmark performance.

cs.AI · hep-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38993

Open-World Object Motion Anticipation via Meta-Learned Semantic Adaptation

Mason Peterson, Gage MacLin, Camilla Tabasso, Jonathan P. How, Joshua Migdal, Tye Brady, Taskin Padir

原文摘要

Anticipating the motion of nearby objects is critical for safe and efficient robot navigation. Without a proper understanding of what may move, a robot may plan overly conservative, inefficient trajectories to guarantee safety, or it may be overly risky, resulting in unacceptable collisions. While tracking and predicting the motion of known objects has seen significant progress, little research addresses how a robot should adapt online to novel objects, including anticipating how one object may move another (e.g., a person operating a forklift to move a pallet). To enable this capability, we propose a meta-learned graph neural network that leverages a semantic, geometric, and relational history of objects to accurately predict, from a few online observations, when objects will begin to move in new environments. We demonstrate that our method, which is trained only in simulation, accurately anticipates the motion of objects unseen at training time, transfers to hardware without any fine-tuning, and outperforms a vision-language model and a class-frequency baseline in both simulation and hardware experiments. Our method's accurate prediction enables collision-free traversals in a closed-loop navigation simulation, while remaining within four seconds of the fastest, collision-prone planner.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37965

Meta-Initialization of Implicit Neural Representations to Accelerate Deformable Medical Image Registration

Marat O. Zinovev, Dmitry V. Sorokin

原文摘要

Implicit neural representation (INR) methods for deformable medical image registration require the network parameters to be optimized for each new image pair, making adaptation speed a practical limitation. This work investigates whether early adaptation can be accelerated using an initialization learned from a collection of previously solved registration tasks. We examine two schemes: Reptile meta-initialization and STRAINER transfer of the shared component of a coordinate network. KAN-IDIR is used as the base INR displacement-field model. Experiments are conducted on OASIS-1, with 364 consecutive pairs used for training and 49 pairs for test-time adaptation. Registration quality is evaluated using mean Dice and HD95, together with the fraction of voxels with a negative Jacobian determinant at iteration 1500. In the configurations studied, both schemes yield higher Dice and lower HD95 at early iterations than random initialization. Reptile numerically outperforms STRAINER under a small iteration budget, although their pretraining budgets are not matched. As the number of iterations increases, the differences between the schemes shrink. STRAINER pretraining takes 39-40 minutes, compared with 44.98 hours for Reptile.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37215

Retrieve to Act: Motion Primitive Graph Retrieval for Robust VLA Execution

Pham Tri Quang, Bao-Ngoc Dao, Minh Duc Nguyen, Duc-Duy Nguyen, Hung T. Ho, Linh Dang Le, Trong-Bao Ho, Thien-Loc Ha 等 18 位作者

原文摘要

Vision-Language-Action (VLA) policies demonstrate remarkable semantic generalization, yet remain highly vulnerable to out-of-distribution (OOD) visual shifts during execution. While existing test-time methods attempt to suppress spurious visual cues, they fundamentally overlook the rich, uncorrupted kinematic priors embedded in the policy's own training experience. We introduce Retrieve to Act (R2A), a test-time scaling framework that formulates OOD robustness purely as a geometric motion primitive retrieval problem. R2A bypasses fragile visual features by structuring successful training demonstrations into an offline spatiotemporal motion primitive graph. During inference, a query-dependent Graph Neural Network dynamically localizes the robot's ongoing execution within this graph, retrieving structurally compatible future motion primitives. These retrieved geometric priors are then seamlessly harmonized with the frozen VLA's predicted actions via a learned, dimension-wise gating mechanism, adaptively rectifying erroneous spatial trajectories while preserving the policy's local reactivity. Extensive experiments across three state-of-the-art VLA architectures, GR00T N1.7, $π_{0.5}$, and StableVLA, demonstrate that R2A consistently and significantly enhances robustness against diverse contextual perturbations. R2A achieves absolute success rate improvements of up to +12% in simulation benchmarks (LIBERO-Plus, RoboTwin2.0-Plus) and +40% in real-world deployments, without requiring any finetuning of the base policies. Project page: https://retrieve2act.github.io/r2a/

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37203

Remember Where You Walk: Learning Spatial Memory for End-to-End Legged Robot Exploration

Leon Magnus, Nico Bohlinger, Jan Peters, Oleg Arenz

原文摘要

Humanoids and other legged robots operating in complex environments must remember information that leaves their field of view and only becomes relevant much later. Reinforcement learning policies address this using memory networks such as LSTMs that are trained end-to-end with the policy to memorize such task-relevant aspects. Yet, such architectures often fail to preserve sufficient information over long horizons. In this work, we propose a network architecture based on Hadamard memory that specifically targets robot navigation. Our Local Spatial Matrix Memory (LSMM) enables RL agents to store generic task-relevant information at specific, position-based memory cells, enabling flexible and spatially grounded memorization. We evaluate LSMM on the task of autonomous maze exploration, where it matches the maze coverage of strong recurrent and finite-history baselines while being the only architecture that remembers the maze layout, reducing the reconstruction error threefold.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2505.13231

Investigating Active Sampling for Hardness Classification with Vision-Based Tactile Sensors

Junyi Chen, Frederik Heller, Mario Gómez Andreu, Boris Belousov, Tim Schneider, Lisa P. Y. Lin, Katja Doerschner, Knut Drewing 等 10 位作者

原文摘要

Hardness is one of the most important object properties that humans and robots perceive through touch. This paper investigates active sampling strategies for sample-efficient hardness classification with vision-based tactile sensors (VBTS), using information-theoretic measures of model uncertainty. We evaluated three probabilistic classifier models and two active sampling strategies and a random sampling baseline on a hardness classification task, with our own dataset of VBTS samples collected by a robot and a previously published dataset. In addition, we conducted a human study on the hardness classification task with the same objects as our dataset. Our findings indicate that the active sampling approaches, driven by variance and entropy as measures of model uncertainty, perform best with accuracy reaching 90%, compared to human accuracy of 48%, demonstrating the effectiveness of using VBTS for hardness classification. More information can be found at: https://fheller1.github.io/ActiveHardness

cs.RO · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36452

Whole-Body Humanoid Control via Stochastic Motion Tokenization

Michael Drolet, Oleg Arenz, Jan Peters

原文摘要

While velocity-commanded RL policies are effective for controlling quadrupeds, they are a limited interface for humanoids that need to perform complex whole-body motions. Furthermore, RL tracking policies for whole-body motions typically have limited information about the desired future motion, preventing them from performing controlled deviations to achieve long-term task success; such information is particularly relevant when a controller must prepare for transitions between behaviors. We address these challenges using concise motion representations that can be generated by a high-level controller, given a behavior label or text command. These representations can be fed directly into a tracking policy to provide a detailed motion reference. Our method exhibits a high degree of flexibility in performing real-world robot motions such as dancing, fighting, or walking based on conditional information. At matched capacity, our adopted stochastic motion tokenizer reconstructs motions from the Unitree G1 at a level that exceeds state-of-the-art approaches such as finite scalar quantization (FSQ) and the vector-quantized autoencoder (VQ-VAE). The resulting discrete interface conditions whole-body tracking policies that execute generated dance, fight, and walk motions lasting 16.8 s each and a 35 s fight-to-dance sequence on a physical Unitree G1.

cs.RO · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35670

Continuous-Time Safe Planning and Control for Agile Quadrupeds

Gage MacLin, Mason Peterson, Camilla Tabasso, Venanzio Cichella, Joshua Migdal, Tye Brady, Taskin Padir

原文摘要

Agile quadruped navigation in dynamic environments demands trajectories that are both dynamically feasible and provably collision-free. Most real-time planners achieve tractability through a convex reduction that requires simplified kinematic models, discarding motion that the robot can readily execute, and certify safety only at discretization points, leaving open possible inter-sample collisions with moving obstacles. We present a real-time motion planning framework that retains the fully-actuated $SE(2)$ model of a quadruped, with its anisotropic, heading-coupled velocity bounds, and accepts the resulting nonconvexity. By parameterizing trajectories as composite Bernstein polynomials, we exploit the convex hull property to certify collision avoidance and the input bounds over the entirety of each planning horizon. Solved at online replanning rates, the optimization runs in closed loop, commanding body velocities to the locomotion controller. We validate the approach in simulation against ablations and external baselines, and in hardware experiments on a quadruped navigating among unknown moving obstacles, recovering both lateral and heading-coupled motion that simplified models exclude.

cs.RO

查看论文
arXiv ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:1cb333f0af2d7c952fdb31eddc443480CVF · CVPR 2026

General Process Reward Modeling for Robotic Reinforcement Learning

Tan, Huajie, Chen, Sixiang, Xu, Yijie, Wang, Zixiao, Chi, Cheng, Ji, Yuheng, Lyu, Yaoxu, Zhao, Zhongxia 等 15 位作者

原文摘要

The primary obstacle for applying reinforcement learning (RL) to real-world robotics is the design of effective reward functions. While recently learning-based Process Reward Models (PRMs) are a promising direction, they are often hindered by two fundamental limitations: their reward models lack step-aware understanding and rely on single-view perception, leading to unreliable assessments of fine-grained manipulation progress; and their reward shaping procedures are theoretically unsound, often inducing a semantic trap that misguides policy optimization. To address these, we introduce Dopamine-Reward, a novel reward modeling method for learning a general-purpose, step-aware process reward model from multi-view inputs. At its core is our General Reward Model (GRM), trained on a vast 3,400+ hour dataset, which leverages Step-wise Reward Discretization for structural understanding and Multi-Perspective Reward Fusion to overcome perceptual limitations. Building upon Dopamine-Reward, we propose Dopamine-RL, a robust policy learning framework that employs a theoretically-sound Policy-Invariant Reward Shaping method, which enables the agent to leverage dense rewards for efficient self-improvement without altering the optimal policy, thereby fundamentally avoiding the semantic trap. Extensive experiments across diverse simulated and real-world tasks validate our approach. GRM achieves state-of-the-art accuracy in reward assessment, and Dopamine-RL built on GRM significantly improves policy learning efficiency. For instance, after GRM is adapted to a new task in a one-shot manner from a single expert trajectory, the resulting reward model enables Dopamine-RL to improve the policy from near-zero to 95% success with only 150 online rollouts (approximately 1 hour of real robot interaction), while retaining strong generalization across tasks.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:444feda5930d2c4699d458b20bae8a25CVF · CVPR 2026

Action-Sketcher: From Reasoning to Action via Visual Sketches for Robotic Manipulation

Tan, Huajie, Co, Peterson, Xu, Yijie, Rong, Shanyu, Ji, Yuheng, Chi, Cheng, Chen, Xiansheng, Zhao, Zhongxia 等 11 位作者

原文摘要

Long-horizon robotic manipulation is increasingly important for real-world deployment, requiring spatial disambiguation in complex layouts and temporal resilience under dynamic interaction. However, existing end-to-end and hierarchical Vision-Language-Action (VLA) policies often rely on text-only cues while keeping plan intent latent, which undermines referential grounding in cluttered or underspecified scenes, impedes effective task decomposition of long-horizon goals with close-loop interaction, and limits causal explanation by obscuring the rationale behind action choices. To address these issues, we first introduce Visual Sketch, an implausible visual intermediate that renders points, boxes, arrows, and typed relations in the robot's current views to externalize spatial intent, connect language to scene geometry, and provide a human-verifiable bridge between high-level reasoning and low-level control. Building on Visual Sketch, we present Action-Sketcher, a VLA framework that operates in a cyclic See -> Think -> Sketch -> Act workflow coordinated by adaptive token-gated strategy for reasoning triggers, sketch revision, and action issuance, thereby supporting reactive corrections and human interaction while preserving real-time action prediction. To enable scalable training and evaluation, we curate diverse corpus with interleaved images, text, Visual Sketch supervision, and action sequences, and train Action-Sketcher with a multi-stage curriculum recipe that combines interleaved sequence alignment for modality unification, language-to-sketch consistency for precise linguistic grounding, and imitation learning augmented with sketch-to-action reinforcement for robustness. Extensive experiments on cluttered scenes and multi-object tasks, in simulation and on real-world tasks, show improved long-horizon success, stronger robustness to dynamic scene changes, and enhanced interpretability via editable sketches and step-wise plans.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:862a21fe5b65ab967d907d1e448ec05eCVF · CVPR 2026

Breaking the 3D Dataset Bottleneck: Fast Scalable Generation of Aligned 3D Assets from Scratch for Category 6D Pose Estimation and Robotic Grasping

Guillaume, Duret, Mazurak, Danylo, Zara, Florence, Peters, Jan, Chen, Liming

原文摘要

While 2D vision has been revolutionized by large-scale datasets like ImageNet, 3D vision remains constrained by the scarcity of high-quality, canonically aligned data. We introduce the first scalable, automated framework that generates complete category-level 6D pose datasets directly from text prompts, bypassing the need for existing 3D assets. Our method overcomes key challenges by: (1) ensuring reliable, scalable asset generation via a controlled text-to-image-to-3D pipeline; (2) enforcing built-in canonical alignment through depth-conditioned generation, achieving a 96% pose consistency rate; and (3) enabling large-scale 6D annotation via mixed reality rendering. The pipeline produces high-quality, aligned 3D meshes in under 3 minutes per object--a 5-20x speedup over traditional scanning. We generate over 1,000 instances for each of the 153 categories in the Omni6Dpose benchmark, culminating in 153,000 aligned meshes--a >40x increase in instances per category over previous aligned real-world datasets. Extensive evaluation demonstrates competitive zero-shot sim2real transfer on the NOCS 6D pose benchmark and superior robotic grasping performance in both simulation and real-world zero-shot transfer, where aligned meshes prove essential for success. We release the largest publicly available aligned 3D mesh dataset, largest category-level 6D pose dataset, grasping simulation environments, and open-source pipeline, providing a critical step toward foundation models for 3D understanding and enabling efficient, unlimited generation of task-specific 3D data from scratch. The code and datasets can be found at https://genomni3d.github.io/

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗