{"total":73,"rows":[{"id":"2603.19199","title":"FASTER: Rethinking Real-Time Flow VLAs","created":"2026-03-19","cited_by_count":21,"area":"vla"},{"id":"2605.21800","title":"stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation","created":"2026-05-20","cited_by_count":20,"area":"wm"},{"id":"2607.24008","title":"FutureRTC: Real-Time Robot Execution with Anticipatory-Conditioned Action Chunking","created":"2026-07-27","cited_by_count":10,"area":"vla"},{"id":"2605.29360","title":"MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models","created":"2026-05-28","cited_by_count":9,"area":"wm"},{"id":"2607.14183","title":"Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning","created":"2026-07-15","cited_by_count":8,"area":"wm"},{"id":"2603.10126","title":"AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models","created":"2026-03-10","cited_by_count":6,"area":"vla"},{"id":"2605.26820","title":"Can Vision-Language-Action Models Learn from Real-World Data Continually without Forgetting?","created":"2026-05-26","cited_by_count":6,"area":"vla"},{"id":"2609.02531","title":"Spatially Aware World Action Model via Geometric Latent Diffusion","created":"2026-09-02","cited_by_count":5,"area":"wm"},{"id":"2605.07288","title":"Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training","created":"2026-05-08","cited_by_count":4,"area":"wm"},{"id":"2606.18043","title":"Uncertainty Quantification for Flow-Based Vision-Language-Action Models","created":"2026-06-16","cited_by_count":4,"area":"vla"},{"id":"2603.08269","title":"SAIL: Test-Time Scaling for In-Context Imitation Learning with VLM","created":"2026-03-09","cited_by_count":3,"area":"lr"},{"id":"2606.12936","title":"Pipette: An Embodied Simulation Platform, Benchmark, and Data-Efficient Augmentation Framework for Wet-Lab Robotics","created":"2026-06-11","cited_by_count":3,"area":null},{"id":"2606.13769","title":"$\\mu_0$: A Scalable 3D Interaction-Trace World Model","created":"2026-06-11","cited_by_count":3,"area":"wm"},{"id":"2608.25864","title":"MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization","created":"2026-08-26","cited_by_count":3,"area":"vla"},{"id":"2606.08653","title":"FiberTune: Preserving Action-Fiber Visual Residuals in Vision-Language-Action Fine-Tuning","created":"2026-06-07","cited_by_count":2,"area":"vla"},{"id":"2608.04396","title":"CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention","created":"2026-08-05","cited_by_count":2,"area":"vla"},{"id":"2608.29078","title":"DREAM: Deployment-Time Demonstration Generation via Real-to-Sim for Scalable Policy Adaptation","created":"2026-08-29","cited_by_count":2,"area":"vla"},{"id":"2604.08544","title":"SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2604.17787","title":"AnchorRefine: Synergy-Manipulation Based on Trajectory Anchor and Residual Refinement for Vision-Language-Action Models","created":"2026-04-20","cited_by_count":1,"area":"vla"},{"id":"2605.07642","title":"EggHand: A Multimodal Foundation Model for Egocentric Hand Pose Forecasting","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.08638","title":"Geometry Guided Self-Consistency for Physical AI","created":"2026-05-09","cited_by_count":1,"area":"lr"},{"id":"2605.13276","title":"D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action Models","created":"2026-05-13","cited_by_count":1,"area":"vla"},{"id":"2605.28486","title":"Mag-VLA: Vision-Language-Action Model for Bimanual Magnetically Actuated Microrobot Manipulation","created":"2026-05-27","cited_by_count":1,"area":"vla"},{"id":"2606.05588","title":"Auditing Demonstration Curation Metrics: Action-Only Scorers Fail on the Structural Defects That Degrade Imitation Policies","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.09499","title":"Targeting World Models to Compromise Robot Learning Pipelines","created":"2026-06-08","cited_by_count":1,"area":"wm"},{"id":"2606.10229","title":"What Demonstration Curation Metrics Do to Your Policy","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.25591","title":"WOLF-VLA: Whole-Body Humanoid Optimal Locomotion Framework for Vision-Language-Action Learning","created":"2026-06-24","cited_by_count":1,"area":"vla"},{"id":"2606.28529","title":"The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2607.09590","title":"PAC-ACT: Post-training Actor-Critic for Action Chunking Transformers","created":"2026-07-10","cited_by_count":1,"area":"deeprl"},{"id":"2607.14698","title":"Lights, Camera, Malfunction: When Illumination Robustness Leaves VLA Models Blind to Color","created":"2026-07-16","cited_by_count":1,"area":"vla"},{"id":"2608.03682","title":"PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloud","created":"2026-08-04","cited_by_count":1,"area":"deeprl"},{"id":"2608.15285","title":"PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies","created":"2026-08-15","cited_by_count":1,"area":"vla"},{"id":"2608.15707","title":"GAINS: Leveraging Inconsistent Human Intervention Signals in Reinforcement Learning","created":"2026-08-16","cited_by_count":1,"area":"deeprl"},{"id":"2608.18433","title":"The Embodiment Gap in Robot Foundation Models","created":"2026-08-19","cited_by_count":1,"area":"vla"},{"id":"2609.05178","title":"LIBERO-RECOVER: Beyond Task Success Towards Failure Recovery in Robotic Manipulation Models","created":"2026-09-04","cited_by_count":1,"area":"vla"},{"id":"2609.09155","title":"SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators","created":"2026-09-08","cited_by_count":1,"area":"wm"},{"id":"2609.17210","title":"FluxVLA Engine: A One-Stop VLA Engineering Platform for Embodied Intelligence","created":"2026-09-15","cited_by_count":1,"area":"wm"},{"id":"2609.25562","title":"IndustrialVLA-Bench: A Traceable Multi-Axis Evaluation of Open Robot Policy Models","created":"2026-09-22","cited_by_count":1,"area":"wm"},{"id":"2609.27780","title":"Task-Prototype Guided Flow Matching for Few-Shot Generalization in Vision-Language Robot Manipulation","created":"2026-08-18","cited_by_count":1,"area":"diffusion"},{"id":"2609.31394","title":"InternW0-$Δ$: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data","created":"2026-09-25","cited_by_count":1,"area":"wm"},{"id":"2603.20659","title":"StageCraft: Execution Aware Mitigation of Distractor and Obstruction Failures in VLA Models","created":"2026-03-21","cited_by_count":0,"area":"vla"},{"id":"2605.28736","title":"Imitation Learning for Robot Assistance in Open Surgery: A Multi-Policy Evaluation on Suture Following","created":"2026-05-27","cited_by_count":0,"area":"offlinerl"},{"id":"2606.00089","title":"Can Predicted Dynamics Exist in the Physical World?","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.00090","title":"Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems","created":"2026-05-23","cited_by_count":0,"area":"wm"},{"id":"2606.00253","title":"Per-Group Error, Not Total MSE: Fine-Tuning Vision-Language-Action Models for 11-DoF Mobile Manipulation","created":"2026-05-29","cited_by_count":0,"area":"vla"},{"id":"2606.03134","title":"How Visible Are Silent Manipulation Failures? An Observability Study of False-Success Detection in Simulated Robot Episodes","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.03312","title":"RobotValues: Evaluating Household Robots When Human Values Conflict","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.08765","title":"Tac2Pix: Image-Space Visuo-Tactile Fusion for Dexterous Manipulation","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.12978","title":"Trajectory-Level Redirection Attacks on Vision-Language-Action Models","created":"2026-06-11","cited_by_count":0,"area":"vla"},{"id":"2606.14561","title":"ORCA: A Platform for Open-Source Dexterity Research","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.16515","title":"Direction-Conditioned Policies via Compositional Subgoal Scoring for Online Goal-Conditioned Reinforcement Learning","created":"2026-06-15","cited_by_count":0,"area":"deeprl"},{"id":"2606.21372","title":"NAC: Neural Action Codec for Vision-Language-Action Models","created":"2026-06-19","cited_by_count":0,"area":"vla"},{"id":"2607.00020","title":"EmbodimentSemantic: A Spatial Scene-Graph Dataset and Benchmark for Vision-Language Models on Embodied Manipulation Trajectories","created":"2026-06-06","cited_by_count":0,"area":"mllm"},{"id":"2607.02646","title":"EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.03283","title":"Embodied Operators and Benchmarking: Toward Reusable and Deployable Embodied Intelligence Systems","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.04162","title":"ACE: Agentic Control for Embodied Manipulation via Zero-shot Workflow Reasoning","created":"2026-07-05","cited_by_count":0,"area":"agents"},{"id":"2608.03938","title":"Bimanual Manipulation Within an 8 GB Budget: Zero-Copy Sensing and Quantized ACT on an Entry-Level Jetson","created":"2026-08-04","cited_by_count":0,"area":"diffusion"},{"id":"2608.19066","title":"GS-VLA: Plug-and-Play Viewpoint Canonicalization for Frozen VLA Policies via Gaussian Splatting","created":"2026-08-19","cited_by_count":0,"area":"vla"},{"id":"2608.19589","title":"OrthoSkillVLA: Continual Skill Learning via Gradient-Informed Skill Subspace Adaptation","created":"2026-08-20","cited_by_count":0,"area":"vla"},{"id":"2608.23320","title":"ROS2SmolVLA: Enabling Small Vision-Language-Action Models for Integration into Industrial-Grade Lightweight Robots","created":"2026-08-24","cited_by_count":0,"area":"vla"},{"id":"2609.06221","title":"RefGuard: Identity-Aware Language-Guided Robot Manipulation via Joint Target-Anchor-Frame Grounding","created":"2026-09-05","cited_by_count":0,"area":"vla"},{"id":"2609.10915","title":"IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies","created":"2026-09-10","cited_by_count":0,"area":"vla"},{"id":"2609.17843","title":"RoboVAD: A Large Cross-Domain Evaluation Benchmark for Anomaly Detection in Robotic Arm Manipulation Videos","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.19040","title":"Learning to Stack: Cube-Stacking Imitation Learning from Virtual Reality Demonstrations","created":"2026-07-20","cited_by_count":0,"area":"offlinerl"},{"id":"2609.21817","title":"A Sim-to-Real Integration Pipeline for Training and Deployment of Chunk-Based VLA Manipulation Policies","created":"2026-09-18","cited_by_count":0,"area":"vla"},{"id":"2609.23614","title":"CompVLA: A Variable Compliance Vision-Language-Action Model for Contact-rich Manipulation","created":"2026-09-20","cited_by_count":0,"area":"vla"},{"id":"2609.24274","title":"vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.29382","title":"Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs","created":"2026-09-24","cited_by_count":0,"area":"mllm"},{"id":"2609.36416","title":"FineART: Fine-Grained Annotated Robotic Trajectory Dataset and Vision-Language-Action Model for Bimanual Manipulation","created":"2026-09-29","cited_by_count":0,"area":"vla"},{"id":"2609.37772","title":"Urgent Actions Go First: Urgency-Aware Denoising for Real-Time VLA Control","created":"2026-09-29","cited_by_count":0,"area":"vla"},{"id":"2610.01794","title":"Continuous Conditioning of VLAs with Augmenting EMG and Visual Task Descriptors","created":"2026-10-01","cited_by_count":0,"area":"vla"},{"id":"2610.12818","title":"LeWAM: End-to-End World and Action Modeling with JEPAs","created":"2026-10-08","cited_by_count":0,"area":"wm"},{"id":"2610.18872","title":"EgoExplorer: A Vision-Motion-Touch Observatory for Human Loco-Manipulation In Situ","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}