Cover Image

VLA Model Post-Training via Action-Chunked PPO and Self Behavior Cloning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Si-Cheng, Xiang, Tian-Yu, Zhou, Xiao-Hu, Gui, Mei-Jiang, Xie, Xiao-Liang, Liu, Shi-Qi, Wang, Shuang-Yi, Jin, Ao-Qun, Hou, Zeng-Guang
Format:	Preprint
Published:	2025
Subjects:	Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends
by: Xiang, Tian-Yu, et al.
Published: (2025)

VLA Model-Expert Collaboration for Bi-directional Manipulation Learning
by: Xiang, Tian-Yu, et al.
Published: (2025)

Understanding Multimodal Failure in Action-Chunking Behavioral Cloning
by: Mazza, Lorenzo, et al.
Published: (2026)

Learning Novel Skills from Language-Generated Demonstrations
by: Jin, Ao-Qun, et al.
Published: (2024)

Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking
by: So, Junhyuk, et al.
Published: (2025)

Online Adaptation via Dual-Stage Alignment and Self-Supervision for Fast-Calibration Brain-Computer Interfaces
by: Duan, Sheng-Bin, et al.
Published: (2025)

CAS-GAN for Contrast-free Angiography Synthesis
by: Huang, De-Xing, et al.
Published: (2024)

Understanding Behavior Cloning with Action Quantization
by: Cao, Haoqun, et al.
Published: (2026)

Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Control
by: Zhang, Thomas T., et al.
Published: (2025)

VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel Segmentation
by: Huang, De-Xing, et al.
Published: (2025)

RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models
by: Zhang, Hongyin, et al.
Published: (2025)

PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding
by: Song, Wenxuan, et al.
Published: (2025)

DOMAIN: MilDly COnservative Model-BAsed OfflINe Reinforcement Learning
by: Liu, Xiao-Yin, et al.
Published: (2023)

Leave No Observation Behind: Real-time Correction for VLA Action Chunks
by: Sendai, Kohei, et al.
Published: (2025)

CROP: Conservative Reward for Model-based Offline Policy Optimization
by: Li, Hao, et al.
Published: (2023)

REASON: Probability map-guided dual-branch fusion framework for gastric content assessment
by: Xiao, Nu-Fnag, et al.
Published: (2025)

SPIRONet: Spatial-Frequency Learning and Topological Channel Interaction Network for Vessel Segmentation
by: Huang, De-Xing, et al.
Published: (2024)

EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control
by: Zhang, Chushan, et al.
Published: (2026)

MOSformer: Momentum encoder-based inter-slice fusion transformer for medical image segmentation
by: Huang, De-Xing, et al.
Published: (2024)

QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models
by: Zhang, Jingxuan, et al.
Published: (2026)

Temporal Action Selection for Action Chunking
by: Weng, Yueyang, et al.
Published: (2025)

Learning from Mistakes: Post-Training for Driving VLA with Takeover Data
by: Gao, Yinfeng, et al.
Published: (2026)

Quantifying and Characterizing Clones of Self-Admitted Technical Debt in Build Systems
by: Xiao, Tao, et al.
Published: (2024)

Task-Oriented Learning for Automatic EEG Denoising
by: Xiang, Tian-Yu, et al.
Published: (2025)

StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation
by: Shi, Yiran, et al.
Published: (2026)

Continuous Vision-Language-Action Co-Learning with Semantic-Physical Alignment for Behavioral Cloning
by: Qi, Xiuxiu, et al.
Published: (2025)

World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
by: Xiao, Junjin, et al.
Published: (2025)

Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policy
by: Wu, Pengyuan, et al.
Published: (2026)

Constrained Behavior Cloning for Robotic Learning
by: Liang, Wensheng, et al.
Published: (2024)

MICRO: Model-Based Offline Reinforcement Learning with a Conservative Bellman Operator
by: Liu, Xiao-Yin, et al.
Published: (2023)

AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models
by: Jiang, Yuhua, et al.
Published: (2025)

ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning
by: Yang, Yandan, et al.
Published: (2026)

Mixture of Horizons in Action Chunking
by: Jing, Dong, et al.
Published: (2025)

Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models
by: Zhang, Hongyin, et al.
Published: (2025)

LLM App Squatting and Cloning
by: Xie, Yinglin, et al.
Published: (2024)

SELF-VLA: A Skill Enhanced Agentic Vision-Language-Action Framework for Contact-Rich Disassembly
by: Liu, Chang, et al.
Published: (2026)

Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models
by: Günther, Michael, et al.
Published: (2024)

Training-Time Action Conditioning for Efficient Real-Time Chunking
by: Black, Kevin, et al.
Published: (2025)

SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
by: Wang, Hanzhen, et al.
Published: (2025)

CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models
by: Liu, Zhi
Published: (2026)