{"total":103,"rows":[{"id":"2602.10098","title":"VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model","created":"2026-02-10","cited_by_count":118,"area":"wm"},{"id":"2604.05014","title":"StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing","created":"2026-04-06","cited_by_count":112,"area":"wm"},{"id":"2605.00078","title":"Being-H0.7: A Latent World-Action Model from Egocentric Videos","created":"2026-04-30","cited_by_count":75,"area":"wm"},{"id":"2603.03596","title":"MEM: Multi-Scale Embodied Memory for Vision Language Action Models","created":"2026-03-04","cited_by_count":61,"area":"vla"},{"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":"2605.00080","title":"World Model for Robot Learning: A Comprehensive Survey","created":"2026-04-30","cited_by_count":46,"area":"wm"},{"id":"2605.30280","title":"Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments","created":"2026-05-28","cited_by_count":44,"area":"vla"},{"id":"2607.04434","title":"RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies","created":"2026-07-05","cited_by_count":40,"area":null},{"id":"2606.19531","title":"ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?","created":"2026-06-17","cited_by_count":38,"area":"wm"},{"id":"2607.08639","title":"Native Video-Action Pretraining for Generalizable Robot Control","created":"2026-07-09","cited_by_count":36,"area":null},{"id":"2604.11757","title":"StarVLA-$\\alpha$: Reducing Complexity in Vision-Language-Action Systems","created":"2026-04-13","cited_by_count":31,"area":"vla"},{"id":"2603.23376","title":"ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment","created":"2026-03-24","cited_by_count":29,"area":"wm"},{"id":"2607.15330","title":"Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories","created":"2026-07-16","cited_by_count":29,"area":"vla"},{"id":"2607.06403","title":"From Foundation to Application: Improving VLA Models in Practice","created":"2026-07-07","cited_by_count":26,"area":"vla"},{"id":"2602.12062","title":"HoloBrain-0 Technical Report","created":"2026-02-12","cited_by_count":21,"area":"vla"},{"id":"2603.19199","title":"FASTER: Rethinking Real-Time Flow VLAs","created":"2026-03-19","cited_by_count":21,"area":"vla"},{"id":"2606.10040","title":"Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination","created":"2026-06-08","cited_by_count":18,"area":"wm"},{"id":"2608.11739","title":"G0.5: One Autoregressive Stream for Robot Reasoning and Action","created":"2026-08-12","cited_by_count":18,"area":"vla"},{"id":"2606.01955","title":"WALL-WM: Carving World Action Modeling at the Event Joints","created":"2026-06-01","cited_by_count":17,"area":"wm"},{"id":"2605.14950","title":"Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model","created":"2026-05-14","cited_by_count":16,"area":"vla"},{"id":"2606.13515","title":"MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models","created":"2026-06-11","cited_by_count":16,"area":"wm"},{"id":"2604.16391","title":"Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining","created":"2026-03-27","cited_by_count":14,"area":"vla"},{"id":"2605.30877","title":"Wall-OSS-0.5 Technical Report","created":"2026-05-29","cited_by_count":12,"area":"vla"},{"id":"2604.13942","title":"Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection","created":"2026-04-15","cited_by_count":11,"area":"vla"},{"id":"2605.06747","title":"HumanNet: Scaling Human-centric Video Learning to One Million Hours","created":"2026-05-07","cited_by_count":11,"area":null},{"id":"2607.13960","title":"GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch","created":"2026-07-15","cited_by_count":11,"area":"wm"},{"id":"2606.17200","title":"ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining","created":"2026-06-15","cited_by_count":10,"area":"vla"},{"id":"2607.27205","title":"TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM","created":"2026-07-29","cited_by_count":10,"area":"vla"},{"id":"2602.09765","title":"NavDreamer: Video Models as Zero-Shot 3D Navigators","created":"2026-02-10","cited_by_count":9,"area":"vla"},{"id":"2604.21924","title":"Long-Horizon Manipulation via Trace-Conditioned VLA Planning","created":"2026-04-23","cited_by_count":9,"area":"vla"},{"id":"2604.27472","title":"PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations","created":"2026-04-30","cited_by_count":9,"area":"vla"},{"id":"2605.31286","title":"DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulation","created":"2026-05-29","cited_by_count":9,"area":"vla"},{"id":"2606.16533","title":"Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI","created":"2026-06-15","cited_by_count":9,"area":"wm"},{"id":"2605.13403","title":"RotVLA: Rotational Latent Action for Vision-Language-Action Model","created":"2026-05-13","cited_by_count":8,"area":"vla"},{"id":"2605.15153","title":"Pelican-Unify 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action","created":"2026-05-14","cited_by_count":8,"area":null},{"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":"2607.04927","title":"DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation","created":"2026-07-06","cited_by_count":8,"area":"wm"},{"id":"2608.04996","title":"DreamWAM: Beyond RGB Future Prediction for World Action Models","created":"2026-08-05","cited_by_count":8,"area":"wm"},{"id":"2606.14752","title":"X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining","created":"2026-06-07","cited_by_count":7,"area":"vla"},{"id":"2604.09330","title":"VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis","created":"2026-04-10","cited_by_count":6,"area":"wm"},{"id":"2605.28548","title":"GEM: Generative Supervision Helps Embodied Intelligence","created":"2026-05-27","cited_by_count":6,"area":"mllm"},{"id":"2607.18840","title":"WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory and In-Context Learning","created":"2026-07-21","cited_by_count":6,"area":"wm"},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2608.10232","title":"FACT: Failure-Aware Causal Training for World-Action Models","created":"2026-08-10","cited_by_count":6,"area":"wm"},{"id":"2608.27550","title":"Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models","created":"2026-08-27","cited_by_count":6,"area":"vla"},{"id":"2603.08122","title":"Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLA","created":"2026-03-09","cited_by_count":5,"area":"vla"},{"id":"2604.16592","title":"Human Cognition in Machines: A Unified Perspective of World Models","created":"2026-04-17","cited_by_count":5,"area":"wm"},{"id":"2606.12366","title":"APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies","created":"2026-06-10","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":"2607.09661","title":"PanoWorld: Real-World Panoramic Generation","created":"2026-07-10","cited_by_count":5,"area":"wm"},{"id":"2602.05513","title":"DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adapter","created":"2026-02-05","cited_by_count":4,"area":"diffusion"},{"id":"2607.25895","title":"HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone","created":"2026-07-28","cited_by_count":4,"area":null},{"id":"2608.27033","title":"Riemann-1.0: An Embodied World Action Model for Physical AI","created":"2026-08-27","cited_by_count":4,"area":"wm"},{"id":"2610.01939","title":"Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens","created":"2026-10-01","cited_by_count":4,"area":"mllm"},{"id":"2606.20521","title":"HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining","created":"2026-06-18","cited_by_count":3,"area":null},{"id":"2606.27153","title":"DMuon: Efficient Distributed Muon Training with Near-Adam Overhead","created":"2026-06-25","cited_by_count":3,"area":null},{"id":"2606.27755","title":"Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?","created":"2026-06-26","cited_by_count":3,"area":"vla"},{"id":"2607.26657","title":"Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control","created":"2026-07-29","cited_by_count":3,"area":"wm"},{"id":"2603.24935","title":"SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models","created":"2026-03-26","cited_by_count":2,"area":"vla"},{"id":"2606.08602","title":"Reinforcement Learning for Flow-Matching Policies with Density Transport","created":"2026-06-07","cited_by_count":2,"area":"diffusion"},{"id":"2606.14218","title":"Universal Manipulation Exoskeleton: Learning Compliant Whole-body Policies with Real-time Torque Feedback","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2606.17598","title":"MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulation","created":"2026-06-16","cited_by_count":2,"area":"vla"},{"id":"2606.29941","title":"Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2607.01586","title":"VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment","created":"2026-07-02","cited_by_count":2,"area":"vla"},{"id":"2607.02195","title":"Bridge-WA: Predicting Where and How the World Changes for Robotic Action","created":"2026-07-02","cited_by_count":2,"area":"wm"},{"id":"2607.14187","title":"RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination","created":"2026-07-15","cited_by_count":2,"area":"lr"},{"id":"2604.05484","title":"CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment","created":"2026-04-07","cited_by_count":1,"area":"agents"},{"id":"2605.08879","title":"Preserving Foundational Capabilities in Flow-Matching VLAs through Conservative SFT","created":"2026-05-09","cited_by_count":1,"area":"vla"},{"id":"2605.11564","title":"RIO: Flexible Real-Time Robot I/O for Cross-Embodiment Robot Learning","created":"2026-05-12","cited_by_count":1,"area":"vla"},{"id":"2606.16208","title":"ATHENA: Accelerated Multi-Task Heterogeneous Influence Functions for Robot Data Curation","created":"2026-06-15","cited_by_count":1,"area":"vla"},{"id":"2606.16826","title":"ATOM-Bench: A Real-World Benchmark for Atomic Skills and Compositional Generalization in Manipulation Policies","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2606.25215","title":"Reflective VLA: In-Context Action Consequences Make VLAs Generalize","created":"2026-06-23","cited_by_count":1,"area":"vla"},{"id":"2606.28133","title":"Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2608.01265","title":"Hermite Curves as Trajectory Priors for Vision-Language-Action Models","created":"2026-08-02","cited_by_count":1,"area":"vla"},{"id":"2609.24526","title":"ME-VLM: A Unified VLM for Embodied Cognition and Agent Coordination","created":"2026-09-21","cited_by_count":1,"area":"agents"},{"id":"2609.25636","title":"RoboFollow: Unveiling the Instruction Following Mirage in Embodied Agents","created":"2026-09-22","cited_by_count":1,"area":"agents"},{"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":"2609.38163","title":"Rethinking Representations for World-Action Modeling","created":"2026-09-29","cited_by_count":1,"area":"wm"},{"id":"2610.12369","title":"Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement","created":"2026-10-08","cited_by_count":1,"area":"synth"},{"id":"2606.07383","title":"RhinoVLA Technical Report","created":"2026-06-05","cited_by_count":0,"area":"vla"},{"id":"2606.23371","title":"TSD: A Physics-Inspired Trajectory Saliency Detector for Efficient Imitation Learning","created":"2026-06-22","cited_by_count":0,"area":"offlinerl"},{"id":"2608.25308","title":"V-Link: Recovering Lost Visual Representations in Action DiT for Vision-Language-Action Models","created":"2026-08-26","cited_by_count":0,"area":"vla"},{"id":"2608.26058","title":"One Policy, Many Embodiments: Unified Camera-Centric Action Geometry Pre-training for Heterogeneous Embodied Manipulation","created":"2026-08-26","cited_by_count":0,"area":"vla"},{"id":"2608.26067","title":"StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models","created":"2026-08-26","cited_by_count":0,"area":"vla"},{"id":"2609.09941","title":"HaWMPO: Hallucination-Aware World Model-based Policy Optimization for Generalist Robot Policy","created":"2026-09-09","cited_by_count":0,"area":"wm"},{"id":"2609.18514","title":"ActiveScale: Scaling Active Perception for Robots across Model, Data, and Hardware","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.21228","title":"FOCAL-VLA: Subtask-Guided Geometry Distillation and Implicit World Modeling for Vision-Language-Action Models","created":"2026-09-18","cited_by_count":0,"area":"wm"},{"id":"2609.22684","title":"StateMem: Single-State Residual Memory with Adaptive Inference for Vision-Language-Action Policies","created":"2026-09-19","cited_by_count":0,"area":"vla"},{"id":"2609.22895","title":"H-VLA: Hierarchical Vision-Language-Action Model with Key-Action Reasoning and Motion Planning in a Unified Action Space","created":"2026-09-19","cited_by_count":0,"area":"lr"},{"id":"2609.23275","title":"SCULPT-VLA: Learning Structured Control through Staged Action Grounding","created":"2026-09-20","cited_by_count":0,"area":"vla"},{"id":"2609.34170","title":"RAVEL: Asynchronous Rolling Inference for Flow-Based Vision-Language-Action Models","created":"2026-09-28","cited_by_count":0,"area":"vla"},{"id":"2609.34362","title":"FutureDuet: Decoupling Observation Access from Future Supervision in World Action Models","created":"2026-09-28","cited_by_count":0,"area":"wm"},{"id":"2609.36413","title":"One from Infinity: Actualizing Futures from Pretrained World Models into Robot Actions","created":"2026-09-29","cited_by_count":0,"area":"wm"},{"id":"2609.36808","title":"Spotter: Let the Embodied Model Lead, and the VLM Reflect for It","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38057","title":"EVO-WAM: Evolving World Action Models through Video-Action Verification","created":"2026-09-29","cited_by_count":0,"area":"wm"},{"id":"2609.38059","title":"WorldLine: Action-Driven Visual Simulation for Robotic Manipulation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38164","title":"Rho: A Foundation for Efficiently Adaptable VLA Models","created":"2026-09-29","cited_by_count":0,"area":"vla"},{"id":"2609.39973","title":"EWAM: Emergent Depth-Wise Specialization in a Unified Embodied Model -- From Semantic Understanding through Visual Foresight to Action","created":"2026-09-30","cited_by_count":0,"area":"wm"},{"id":"2610.02832","title":"FastOPD: On-Policy Distillation for Lightweight VLA Deployment","created":"2026-10-02","cited_by_count":0,"area":"vla"},{"id":"2610.07652","title":"SMART: Zero-Shot Sim-to-Real Articulated Object Manipulation via Large-Scale Synthetic Pretraining","created":"2026-10-06","cited_by_count":0,"area":"vla"}],"next_cursor":"100"}