Imagen de Portada

RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liufu, Weijia, Guo, Xiaoyu, Chen, Ruiyi, Liu, Jingzhi, Zhang, Kaidong, Liang, Xiwen, Lin, Jianqi, Sun, Dawei, Wang, Yuze, Xu, Rongtao, Lin, Bingqian, Yang, Bowen, Cao, Tongtong, Peng, Bowen, Zhang, Dongyu, Wang, Guangrun, Wang, Min, Lin, Liang, Liang, Xiaodan
Formato:	Preprint
Publicado:	2026
Materias:	Robotics Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

EchoVLA: Synergistic Declarative Memory for VLA-Driven Mobile Manipulation
por: Lin, Min, et al.
Publicado: (2025)

RoBridge: A Hierarchical Architecture Bridging Cognition and Execution for General Robotic Manipulation
por: Zhang, Kaidong, et al.
Publicado: (2025)

Structured Preference Optimization for Vision-Language Long-Horizon Task Planning
por: Liang, Xiwen, et al.
Publicado: (2025)

VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial Modeling
por: Li, Weiqi, et al.
Publicado: (2025)

PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation
por: Zhang, Kaidong, et al.
Publicado: (2024)

Actional Atomic-Concept Learning for Demystifying Vision-Language Navigation
por: Lin, Bingqian, et al.
Publicado: (2023)

OOWM: Structuring Embodied Reasoning and Planning via Object-Oriented Programmatic World Modeling
por: Chen, Hongyu, et al.
Publicado: (2026)

PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly
por: Ma, Liang, et al.
Publicado: (2025)

ACD: Direct Conditional Control for Video Diffusion Models via Attention Supervision
por: Li, Weiqi, et al.
Publicado: (2025)

HumanGenesis: Agent-Based Geometric and Generative Modeling for Synthetic Human Dynamics
por: Li, Weiqi, et al.
Publicado: (2025)

ActionSink: Toward Precise Robot Manipulation with Dynamic Integration of Action Flow
por: Guo, Shanshan, et al.
Publicado: (2025)

DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions
por: Wang, Guangrun, et al.
Publicado: (2024)

RePO: Replay-Enhanced Policy Optimization
por: Li, Siheng, et al.
Publicado: (2025)

Bridging the Discrete-Continuous Gap: Unified Multimodal Generation via Coupled Manifold Discrete Absorbing Diffusion
por: Xu, Yuanfeng, et al.
Publicado: (2026)

GS: Generative Segmentation via Label Diffusion
por: Chen, Yuhao, et al.
Publicado: (2025)

RePO: Understanding Preference Learning Through ReLU-Based Optimization
por: Wu, Junkang, et al.
Publicado: (2025)

Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning
por: Lin, Bingqian, et al.
Publicado: (2024)

A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model
por: Zhang, Kaidong, et al.
Publicado: (2026)

InfiniteWorld: A Unified Scalable Simulation Framework for General Visual-Language Robot Interaction
por: Ren, Pengzhen, et al.
Publicado: (2024)

AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis
por: Tang, Tao, et al.
Publicado: (2024)

Making Large Language Models Better Planners with Reasoning-Decision Alignment
por: Huang, Zhijian, et al.
Publicado: (2024)

In-Situ Tweedie Discrete Diffusion Models
por: Li, Xiao, et al.
Publicado: (2025)

Learning Spatial-Temporal Coherent Correlations for Speech-Preserving Facial Expression Manipulation
por: Chen, Tianshui, et al.
Publicado: (2026)

Human-Centric Open-Future Task Discovery: Formulation, Benchmark, and Scalable Tree-Based Search
por: Song, Zijian, et al.
Publicado: (2025)

SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks
por: Song, Zijian, et al.
Publicado: (2025)

EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning
por: Lin, Bingqian, et al.
Publicado: (2025)

Physical Autoregressive Model for Robotic Manipulation without Action Pretraining
por: Song, Zijian, et al.
Publicado: (2025)

One Model for All: Unified Try-On and Try-Off in Any Pose via LLM-Inspired Bidirectional Tweedie Diffusion
por: Liu, Jinxi, et al.
Publicado: (2025)

RePO: Bridging On-Policy Learning and Off-Policy Knowledge through Rephrasing Policy Optimization
por: Xia, Linxuan, et al.
Publicado: (2026)

Affordances-Oriented Planning using Foundation Models for Continuous Vision-Language Navigation
por: Chen, Jiaqi, et al.
Publicado: (2024)

ReaLM: Reflection-Enhanced Autonomous Reasoning with Small Language Models
por: Xu, Yuanfeng, et al.
Publicado: (2025)

E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion
por: Zhan, Zhihao, et al.
Publicado: (2025)

Synergistic Regulation of Interfacial Charge Redistribution and Charge Transfer via Built‐In Electric Field in Heterojunctions for High‐Performance Lithium–Sulfur Batteries
por: Li Zhang, et al.
Publicado: (2026)

MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents
por: Wei, Ziming, et al.
Publicado: (2025)

Complementary Information Guided Occupancy Prediction via Multi-Level Representation Fusion
por: Xu, Rongtao, et al.
Publicado: (2025)

Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs
por: Lou, Siyu, et al.
Publicado: (2024)

A0: An Affordance-Aware Hierarchical Model for General Robotic Manipulation
por: Xu, Rongtao, et al.
Publicado: (2025)

AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robots
por: Zhang, Likui, et al.
Publicado: (2026)

Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation
por: Wei, Ziming, et al.
Publicado: (2025)

MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigation
por: Chen, Jiaqi, et al.
Publicado: (2024)