Cover Image

From Noise to Intent: Anchoring Generative VLA Policies with Residual Bridges

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhong, Yiming, He, Yaoyu, Yang, Zemin, Tian, Pengfei, Huang, Yifan, Huang, Qingqiu, Zhu, Xinge, Ma, Yuexin
Format:	Preprint
Published:	2026
Subjects:	Robotics Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry
by: Yang, Zemin, et al.
Published: (2026)

FastGrasp: Learning-based Whole-body Control method for Fast Dexterous Grasping with Mobile Manipulators
by: Tao, Heng, et al.
Published: (2026)

FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens
by: Zhong, Yiming, et al.
Published: (2025)

ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Driving
by: Lu, Yuhang, et al.
Published: (2025)

Agile-VLA: Few-Shot Industrial Pose Rectification via Implicit Affordance Anchoring
by: Yan, Teng, et al.
Published: (2026)

VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation
by: Zhong, Zhide, et al.
Published: (2026)

AnchorVLA: Anchored Diffusion for Efficient End-to-End Mobile Manipulation
by: Lim, Jia Syuen, et al.
Published: (2026)

EvolvingGrasp: Evolutionary Grasp Generation via Efficient Preference Alignment
by: Zhu, Yufei, et al.
Published: (2025)

Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model
by: Wang, Hanqing, et al.
Published: (2025)

Registration between Point Cloud Streams and Sequential Bounding Boxes via Gradient Descent
by: Li, Xuesong, et al.
Published: (2024)

BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models
by: Chen, Zhongxi, et al.
Published: (2026)

Learning Based MPC for Autonomous Driving Using a Low Dimensional Residual Model
by: Li, Yaoyu, et al.
Published: (2024)

IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation
by: Lian, Shijie, et al.
Published: (2026)

FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy
by: He, Qian, et al.
Published: (2026)

DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awareness
by: Zhong, Yiming, et al.
Published: (2025)

Critic in the Loop: A Tri-System VLA Framework for Robust Long-Horizon Manipulation
by: Yi, Pengfei, et al.
Published: (2026)

Action Emergence from Streaming Intent
by: Jing, Pengfei, et al.
Published: (2026)

Unified Noise Steering for Efficient Human-Guided VLA Adaptation
by: Lu, Junjie, et al.
Published: (2026)

Driving Intents Amplify Planning-Oriented Reinforcement Learning
by: Lu, Hengtong, et al.
Published: (2026)

DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping
by: Zhong, Yifan, et al.
Published: (2025)

TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies
by: Zheng, Ruijie, et al.
Published: (2024)

Towards Precise Intent-Aligned VLA Aerial Navigation via Expert-Guided GRPO
by: Chen, Tianyang, et al.
Published: (2026)

Refined Policy Distillation: From VLA Generalists to RL Experts
by: Jülg, Tobias, et al.
Published: (2025)

World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy
by: Liu, Xiaokang, et al.
Published: (2026)

ManualVLA: A Unified VLA Model for Chain-of-Thought Manual Generation and Robotic Manipulation
by: Gu, Chenyang, et al.
Published: (2025)

BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
by: Li, Peiyan, et al.
Published: (2025)

RuN: Residual Policy for Natural Humanoid Locomotion
by: Li, Qingpeng, et al.
Published: (2025)

SPLIT: Sparse Incremental Learning of Error Dynamics for Control-Oriented Modeling in Autonomous Vehicles
by: Li, Yaoyu, et al.
Published: (2026)

InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulation
by: Cai, Junhao, et al.
Published: (2026)

STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation
by: Wang, Jiamin, et al.
Published: (2025)

TacMamba: A Tactile History Compression Adapter Bridging Fast Reflexes and Slow VLA Reasoning
by: Wang, Zhenan, et al.
Published: (2026)

VLAgents: A Policy Server for Efficient VLA Inference
by: Jülg, Tobias, et al.
Published: (2026)

HiLMa-Res: A General Hierarchical Framework via Residual RL for Combining Quadrupedal Locomotion and Manipulation
by: Huang, Xiaoyu, et al.
Published: (2024)

MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving
by: Huang, Yuzhou, et al.
Published: (2026)

Tactile-VLA: Unlocking Vision-Language-Action Model's Physical Knowledge for Tactile Generalization
by: Huang, Jialei, et al.
Published: (2025)

Mimic Intent, Not Just Trajectories
by: Huang, Renming, et al.
Published: (2026)

MOSAIC: Bridging the Sim-to-Real Gap in Generalist Humanoid Motion Tracking and Teleoperation with Rapid Residual Adaptation
by: Sun, Zhenguo, et al.
Published: (2026)

End-to-End Dexterous Arm-Hand VLA Policies via Shared Autonomy: VR Teleoperation Augmented by Autonomous Hand VLA Policy for Efficient Data Collection
by: Cui, Yu, et al.
Published: (2025)

RoVLA: Multi-Consistency Constraints for Robust Vision-Language-Action Models
by: Luo, Jingzhou, et al.
Published: (2026)

ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot Manipulation
by: Wu, You, et al.
Published: (2026)