{"total":87,"rows":[{"id":"2606.02800","title":"Cosmos 3: Omnimodal World Models for Physical AI","created":"2026-06-01","cited_by_count":165,"area":"wm"},{"id":"2601.10611","title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","created":"2026-01-15","cited_by_count":139,"area":"mllm"},{"id":"2601.18692","title":"A Pragmatic VLA Foundation Model","created":"2026-01-26","cited_by_count":103,"area":"vla"},{"id":"2603.22435","title":"CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation","created":"2026-03-23","cited_by_count":88,"area":"vla"},{"id":"2512.01031","title":"VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference","created":"2025-11-30","cited_by_count":58,"area":"vla"},{"id":"2512.10675","title":"Evaluating Gemini Robotics Policies in a Veo World Simulator","created":"2025-12-11","cited_by_count":51,"area":"wm"},{"id":"2605.02881","title":"MolmoAct2: Action Reasoning Models for Real-world Deployment","created":"2026-05-04","cited_by_count":50,"area":"lr"},{"id":"2603.04639","title":"RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies","created":"2026-03-04","cited_by_count":49,"area":"vla"},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2607.08448","title":"Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents","created":"2026-07-09","cited_by_count":47,"area":"agents"},{"id":"2512.23703","title":"Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation","created":"2025-12-29","cited_by_count":40,"area":"lr"},{"id":"2512.04797","title":"SIMA 2: A Generalist Embodied Agent for Virtual Worlds","created":"2025-12-04","cited_by_count":31,"area":"agents"},{"id":"2602.09849","title":"BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation","created":"2026-02-10","cited_by_count":30,"area":"vla"},{"id":"2601.09708","title":"Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning","created":"2026-01-14","cited_by_count":24,"area":"vla"},{"id":"2601.13029","title":"Think3D: Thinking with Space for Spatial Reasoning","created":"2026-01-19","cited_by_count":24,"area":"lr"},{"id":"2512.24426","title":"Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoning","created":"2025-12-30","cited_by_count":22,"area":"lr"},{"id":"2602.01067","title":"A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulation","created":"2026-02-01","cited_by_count":22,"area":"vla"},{"id":"2606.14409","title":"Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack","created":"2026-06-12","cited_by_count":22,"area":"vla"},{"id":"2606.19419","title":"Playful Agentic Robot Learning","created":"2026-06-17","cited_by_count":22,"area":"agents"},{"id":"2512.04069","title":"SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL","created":"2025-12-03","cited_by_count":21,"area":"lr"},{"id":"2603.19199","title":"FASTER: Rethinking Real-Time Flow VLAs","created":"2026-03-19","cited_by_count":21,"area":"vla"},{"id":"2609.10522","title":"Show-Harness: Just a VLM Agent Can Play Robots","created":"2026-09-09","cited_by_count":20,"area":"mllm"},{"id":"2512.11218","title":"Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policy","created":"2025-12-12","cited_by_count":18,"area":"mllm"},{"id":"2602.15010","title":"BPP: Long-Context Robot Imitation Learning by Focusing on Key History Frames","created":"2026-02-16","cited_by_count":18,"area":"offlinerl"},{"id":"2511.21690","title":"TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos","created":"2025-11-26","cited_by_count":15,"area":"wm"},{"id":"2512.12799","title":"DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning","created":"2025-12-14","cited_by_count":15,"area":"mllm"},{"id":"2603.28069","title":"MolmoPoint: Better Pointing for VLMs with Grounding Tokens","created":"2026-03-30","cited_by_count":15,"area":"mllm"},{"id":"2605.30117","title":"VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing","created":"2026-05-28","cited_by_count":13,"area":"vla"},{"id":"2512.13660","title":"Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics","created":"2025-12-15","cited_by_count":12,"area":"lr"},{"id":"2606.10267","title":"What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agents","created":"2026-06-09","cited_by_count":11,"area":"vla"},{"id":"2606.17046","title":"Geometric Action Model for Robot Policy Learning","created":"2026-06-15","cited_by_count":11,"area":"wm"},{"id":"2511.00108","title":"Pelican-VL 1.0: A Foundation Brain Model for Embodied Intelligence","created":"2025-10-30","cited_by_count":10,"area":null},{"id":"2511.00917","title":"Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robots","created":"2025-11-02","cited_by_count":9,"area":"mllm"},{"id":"2604.21017","title":"Open-H-Embodiment: A Large-Scale Dataset for Enabling Foundation Models in Medical Robotics","created":"2026-04-22","cited_by_count":8,"area":"wm"},{"id":"2606.30552","title":"Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision","created":"2026-06-29","cited_by_count":8,"area":"lr"},{"id":"2602.05765","title":"RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training","created":"2026-02-05","cited_by_count":7,"area":"vla"},{"id":"2604.07774","title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","created":"2026-04-09","cited_by_count":7,"area":null},{"id":"2605.10925","title":"PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models","created":"2026-05-11","cited_by_count":7,"area":"vla"},{"id":"2606.03784","title":"Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation","created":"2026-06-02","cited_by_count":7,"area":"lr"},{"id":"2602.01662","title":"PLanAR: Planning-Language-Grounded Agentic Reasoning for Robot Manipulation","created":"2026-02-02","cited_by_count":6,"area":"lr"},{"id":"2603.10052","title":"OmniGuide: Universal Guidance Fields for Enhancing Generalist Robot Policies","created":"2026-03-09","cited_by_count":6,"area":"vla"},{"id":"2603.14367","title":"HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task","created":"2026-03-15","cited_by_count":5,"area":"mllm"},{"id":"2606.20905","title":"Vesta: A Generalist Embodied Reasoning Model","created":"2026-06-18","cited_by_count":5,"area":"lr"},{"id":"2512.11362","title":"An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges","created":"2025-12-12","cited_by_count":4,"area":"vla"},{"id":"2602.09017","title":"Contact-Anchored Policies: Contact Conditioning Creates Strong Robot Utility Models","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2603.07530","title":"ICLR: In-Context Imitation Learning with Visual Reasoning","created":"2026-03-08","cited_by_count":4,"area":"lr"},{"id":"2603.23607","title":"Reasoning models do not yet follow their reasoning in autonomous driving: The KITScenes LongTail Dataset","created":"2026-03-24","cited_by_count":4,"area":"lr"},{"id":"2609.27308","title":"EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics","created":"2026-09-23","cited_by_count":4,"area":"agents"},{"id":"2511.16602","title":"Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2602.08167","title":"Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2512.15940","title":"R4: Retrieval-Augmented Reasoning for Vision-Language Models in 4D Spatio-Temporal Space","created":"2025-12-17","cited_by_count":2,"area":"lr"},{"id":"2602.20323","title":"PhysMem: Scaling Test-Time Memory for Embodied Physical Reasoning","created":"2026-02-23","cited_by_count":2,"area":"lr"},{"id":"2603.11426","title":"Grounding Robot Generalization in Training Data via Retrieval-Augmented VLMs","created":"2026-03-12","cited_by_count":2,"area":"rag"},{"id":"2606.20867","title":"FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation","created":"2026-06-18","cited_by_count":2,"area":"vla"},{"id":"2606.30613","title":"Sequential Planning via Anchored Robotic Keypoints","created":"2026-06-29","cited_by_count":2,"area":"vla"},{"id":"2607.02501","title":"Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots","created":"2026-07-02","cited_by_count":2,"area":"wm"},{"id":"2609.18207","title":"Reinforcement Learning for Real-Time Vision-Language-Action Policies","created":"2026-09-16","cited_by_count":2,"area":"vla"},{"id":"2610.12424","title":"RoboRSI: Stable, efficient, and reusable robot self-evolution in complex real-world environments","created":"2026-10-08","cited_by_count":2,"area":null},{"id":"2511.23186","title":"Obstruction reasoning for robotic grasping","created":"2025-11-28","cited_by_count":1,"area":"lr"},{"id":"2603.27967","title":"Learning Multi-View Spatial Reasoning from Cross-View Relations","created":"2026-03-30","cited_by_count":1,"area":"lr"},{"id":"2605.17070","title":"EPIC-Bench: A Perception-Centric Benchmark for Fine-Grained Embodied Visual Grounding in Vision-Language Models","created":"2026-05-16","cited_by_count":1,"area":"mllm"},{"id":"2605.20085","title":"Spatially Prompted Visual Trajectory Prediction for Egocentric Manipulation","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2606.07436","title":"Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning","created":"2026-06-05","cited_by_count":1,"area":"lr"},{"id":"2606.12402","title":"DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?","created":"2026-06-10","cited_by_count":1,"area":"lr"},{"id":"2606.20246","title":"Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think","created":"2026-06-18","cited_by_count":1,"area":"vla"},{"id":"2606.24815","title":"MANGO: Automated Multi-Agent Test Oracle Generation for Vision-Language-Action Models","created":"2026-06-23","cited_by_count":1,"area":"vla"},{"id":"2607.00148","title":"3D Point World Models: Point Completion Enables More Accurate Dynamics Learning","created":"2026-06-30","cited_by_count":1,"area":"wm"},{"id":"2607.12892","title":"UR-VC: Unsupervised Robotic Value Correction for Time-Derived Progress Proxies","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2609.20791","title":"StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation","created":"2026-09-17","cited_by_count":1,"area":"agents"},{"id":"2601.18963","title":"Fauna Sprout: A lightweight, approachable, developer-ready humanoid robot","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2602.14910","title":"Position: Introspective Experience from Conversational Environments as a Path to Better Learning","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2603.05511","title":"An Embodied Companion for Visual Storytelling","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2605.11479","title":"Offline Policy Evaluation for Manipulation Policies via Discounted Liveness Formulation","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.00616","title":"Pause and Think: A Dataset and Benchmark for Video-Grounded Assistive Action Suggestion","created":"2026-05-30","cited_by_count":0,"area":"lr"},{"id":"2606.12586","title":"Beyond Attack Success Rate: Examining Trigger Leakage in Vision-Language Agentic Systems","created":"2026-06-10","cited_by_count":0,"area":"agents"},{"id":"2606.19340","title":"ZeroDex: Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning","created":"2026-06-17","cited_by_count":0,"area":"lr"},{"id":"2607.02604","title":"DynaWM: A Base-VLA-Guided World Foundation Model for Moving-Object Manipulation","created":"2026-07-01","cited_by_count":0,"area":"vla"},{"id":"2607.10350","title":"ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory","created":"2026-07-11","cited_by_count":0,"area":"agents"},{"id":"2607.18062","title":"UniETP: Unifying Environments for Generalizable Embodied Task Planning","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.06756","title":"Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence","created":"2026-08-07","cited_by_count":0,"area":"mllm"},{"id":"2608.19490","title":"Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulation","created":"2026-08-19","cited_by_count":0,"area":"vla"},{"id":"2609.06823","title":"Generalist Open-World Temporal Perception","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.15870","title":"WLA$^3$: World Latent Action Modeling for Semantics, Dynamics, and Kinematics","created":"2026-09-14","cited_by_count":0,"area":"vla"},{"id":"2609.21358","title":"FAN: Foresight Action Normalization for Continual Adaptation of Vision-Language-Action Models","created":"2026-09-18","cited_by_count":0,"area":"vla"},{"id":"2609.36872","title":"PreferenceFlow: Test-Time Guidance of Flow-Matching Robot Policies from Human Interventions","created":"2026-09-29","cited_by_count":0,"area":"diffusion"},{"id":"2610.02161","title":"DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication","created":"2026-10-01","cited_by_count":0,"area":"mllm"},{"id":"2610.06235","title":"Encoded but Not in Control: Revealing the Grounding Gap in Vision-Language Robot Policies","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}