{"total":58,"rows":[{"id":"2601.21998","title":"Causal World Modeling for Robot Control","created":"2026-01-29","cited_by_count":321,"area":"wm"},{"id":"2512.05964","title":"Training-Time Action Conditioning for Efficient Real-Time Chunking","created":"2025-12-05","cited_by_count":64,"area":"vla"},{"id":"2602.12684","title":"Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution","created":"2026-02-13","cited_by_count":45,"area":"vla"},{"id":"2601.22153","title":"DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation","created":"2026-01-29","cited_by_count":34,"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":"2603.19199","title":"FASTER: Rethinking Real-Time Flow VLAs","created":"2026-03-19","cited_by_count":21,"area":"vla"},{"id":"2512.24673","title":"VLA-RAIL: A Real-Time Asynchronous Inference Linker for VLA Models and Robots","created":"2025-12-31","cited_by_count":19,"area":"vla"},{"id":"2602.18397","title":"How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf","created":"2026-02-20","cited_by_count":19,"area":"vla"},{"id":"2602.09021","title":"$\\chi_{0}$: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies","created":"2026-02-09","cited_by_count":12,"area":null},{"id":"2602.13476","title":"AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edge","created":"2026-02-13","cited_by_count":10,"area":null},{"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":"2606.02486","title":"Intercepting the Future: Latent-Space Predictive World Model for Dynamic VLA Manipulation","created":"2026-06-01","cited_by_count":9,"area":"wm"},{"id":"2603.28565","title":"StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation","created":"2026-03-30","cited_by_count":6,"area":"vla"},{"id":"2606.12105","title":"DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model","created":"2026-06-10","cited_by_count":6,"area":"mllm"},{"id":"2601.14945","title":"TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Control","created":"2026-01-21","cited_by_count":5,"area":"vla"},{"id":"2604.25050","title":"DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors","created":"2026-04-27","cited_by_count":4,"area":"diffusion"},{"id":"2605.08168","title":"Understanding Asynchronous Inference Methods for Vision-Language-Action Models","created":"2026-05-04","cited_by_count":4,"area":"vla"},{"id":"2605.11817","title":"See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model","created":"2026-05-12","cited_by_count":4,"area":"vla"},{"id":"2607.26055","title":"$\\pi\\mathbf{R}^2$: Reactive Real-time Flow Policies","created":"2026-07-28","cited_by_count":4,"area":null},{"id":"2608.27384","title":"FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference","created":"2026-08-27","cited_by_count":4,"area":"vla"},{"id":"2603.20658","title":"Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation","created":"2026-03-21","cited_by_count":3,"area":"wm"},{"id":"2607.12659","title":"Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference","created":"2026-07-14","cited_by_count":3,"area":"vla"},{"id":"2607.14695","title":"Reflex: Real-Time VLA Control through Streaming Inference","created":"2026-07-16","cited_by_count":3,"area":"vla"},{"id":"2607.29235","title":"FBFM: A Training-Free Asynchronous Feedback Mechanism for Flow-Matching in World-Action Models Execution","created":"2026-07-31","cited_by_count":3,"area":"wm"},{"id":"2603.18284","title":"Offload or Overload: A Platform Measurement Study of Mobile Robotic Manipulation Workloads","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2604.24086","title":"AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation","created":"2026-04-27","cited_by_count":2,"area":null},{"id":"2606.15285","title":"Acting While Understanding: Asynchronous Semantic-Action Decoupling for Real-Time Vision-Language-Action Models","created":"2026-06-13","cited_by_count":2,"area":"vla"},{"id":"2606.18589","title":"DREAM-Chunk: Reactive Action Chunking with Latent World Model","created":"2026-06-17","cited_by_count":2,"area":"wm"},{"id":"2606.25985","title":"Action ControlNet: A Lightweight Delay-Aware Adapter for Smooth Asynchronous Control in Vision-Language-Action Models","created":"2026-06-24","cited_by_count":2,"area":"vla"},{"id":"2608.00391","title":"The Gate, Not the Cache: Gate Provenance Bounds the Closed-Loop Reliability of Training-Free VLA Token Skipping","created":"2026-08-01","cited_by_count":2,"area":null},{"id":"2608.00569","title":"Latency-Tolerant Cloud-Edge Collaborative Vision-Language-Action Models via Emergent Representational Specialization","created":"2026-08-01","cited_by_count":2,"area":"vla"},{"id":"2608.01452","title":"DynamicManip: Enabling Dynamic Manipulation from a Single Static Demonstration","created":"2026-08-02","cited_by_count":2,"area":null},{"id":"2609.18207","title":"Reinforcement Learning for Real-Time Vision-Language-Action Policies","created":"2026-09-16","cited_by_count":2,"area":"vla"},{"id":"2606.14375","title":"Elastic Queries Reinforcement Learning: Self-Aware Policy Execution for VLA Models","created":"2026-06-12","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":"2607.12287","title":"Reducing Temporal Redundancy for Efficient Vision-Language-Action Inference","created":"2026-07-14","cited_by_count":1,"area":"vla"},{"id":"2608.14379","title":"Reflex: Enabling Fast and Predictive Vision-Language-Action Models for Reaction-Critical Manipulation","created":"2026-08-14","cited_by_count":1,"area":"vla"},{"id":"2608.15502","title":"EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints","created":"2026-08-16","cited_by_count":1,"area":"vla"},{"id":"2608.29768","title":"SmoothRL: Online Reinforcement Learning During Asynchronous Execution","created":"2026-08-30","cited_by_count":1,"area":"deeprl"},{"id":"2609.16864","title":"TEMPO: Learning Temporal Context for Dynamic Robot Manipulation","created":"2026-09-15","cited_by_count":1,"area":"vla"},{"id":"2609.28927","title":"Streaming-WAM: Action-Conditioned World-Action Model for Asynchronous Robot Manipulation","created":"2026-09-24","cited_by_count":1,"area":"wm"},{"id":"2606.09615","title":"DexPIE: Stable Dexterous Policy Improvement from Real-World Experience","created":"2026-06-08","cited_by_count":0,"area":"offlinerl"},{"id":"2606.13355","title":"Real-Time Execution with Autoregressive Policies","created":"2026-06-11","cited_by_count":0,"area":"vla"},{"id":"2606.17982","title":"LAGO Policy: Latency-Aware Asynchronous Diffusion Policies with Goal-Directed Collision-Free Planning for Smooth Manipulation","created":"2026-06-16","cited_by_count":0,"area":"diffusion"},{"id":"2608.15924","title":"RAPAC-DP: Response-Aligned Pending-Action Compensation for Diffusion Policies under Delayed Execution","created":"2026-08-16","cited_by_count":0,"area":"diffusion"},{"id":"2609.21022","title":"Catch Me If You Can: Real-Time Feedback Denoising for Responsive VLAs","created":"2026-09-17","cited_by_count":0,"area":"mllm"},{"id":"2609.22335","title":"KerColle: Unlocking Fine-Grained GPU Concurrency in Vision-Language-Action Models","created":"2026-09-16","cited_by_count":0,"area":"vla"},{"id":"2609.22587","title":"React When You Need To: Event-Triggered Asynchronous Inference for VLA Policies","created":"2026-09-18","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":"2609.35231","title":"Zero-Shot Reactive Obstacle Avoidance for Generative Robot Policies","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"id":"2609.36540","title":"Reactive Real-Time Flow Policies via Asynchronous Distribution Alignment","created":"2026-09-29","cited_by_count":0,"area":"vla"},{"id":"2609.39198","title":"DSDyn-VLA: A Dual-Stream Dynamic Manipulation Framework with Motion Perception, Future Awareness, and Realtime Correction","created":"2026-09-30","cited_by_count":0,"area":"vla"},{"id":"2609.39822","title":"Toward Real-Time VLAs: Stage-Aware Two-Step Flow Denoising and System-Level Evaluation","created":"2026-09-30","cited_by_count":0,"area":"vla"},{"id":"2610.05062","title":"Beyond LLM Serving: Characterizing Vision-Language-Action Workloads for Embodied AI System Design","created":"2026-10-04","cited_by_count":0,"area":"vla"},{"id":"2610.06617","title":"RealtimeWAM: One-Step Asynchronous World Action Models","created":"2026-10-05","cited_by_count":0,"area":"wm"},{"id":"2610.09294","title":"RT-Safe: Benchmarking Agent Safety in Real-Time Embodied Environment","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.12007","title":"REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models","created":"2026-10-08","cited_by_count":0,"area":"vla"},{"id":"2610.13929","title":"Chronos Policy: Learning Robot Policies on Physical Time","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}