Cover Image

Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yanyan, Song, Chaoda, Singh, Vikash, Li, Xinpeng, Ye, Kai, Hu, Zhe, Pu, Zhongzhu, Yin, Yu, Chaudhary, Vipin
Format:	Preprint
Published:	2026
Subjects:	Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers
by: Yang, Wang, et al.
Published: (2026)

HSC-VLA: Hierarchical Scene-Clearing for Robust Bimanual Manipulation in Dense Clutter
by: Liu, Zhen, et al.
Published: (2026)

NEBULA: Do We Evaluate Vision-Language-Action Agents Correctly?
by: Peng, Jierui, et al.
Published: (2025)

Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation
by: Wang, Shouren, et al.
Published: (2026)

HugRAG: Hierarchical Causal Knowledge Graph Design for RAG
by: Wang, Nengbo, et al.
Published: (2026)

Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery
by: Li, Wenhao, et al.
Published: (2026)

STEAM: A Training-Free Congestion-Aware Enhancement Framework for Decentralized Multi-Agent Path Finding
by: Feng, Mingyang, et al.
Published: (2026)

Overcoming Blind Spots: Occlusion Considerations for Improved Autonomous Driving Safety
by: Moller, Korbinian, et al.
Published: (2024)

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

Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection
by: Liu, Zhen, et al.
Published: (2026)

TGM-VLA: Task-Guided Mixup for Sampling-Efficient and Robust Robotic Manipulation
by: Pu, Fanqi, et al.
Published: (2026)

FrameSkip: Learning from Fewer but More Informative Frames in VLA Training
by: Yu, Bin, et al.
Published: (2026)

MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training
by: Li, Haoyun, et al.
Published: (2025)

ST4VLA: Spatially Guided Training for Vision-Language-Action Models
by: Ye, Jinhui, et al.
Published: (2026)

FPC-VLA: A Vision-Language-Action Framework with a Supervisor for Failure Prediction and Correction
by: Yang, Yifan, et al.
Published: (2025)

Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization
by: Kachaev, Nikita, et al.
Published: (2025)

SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead
by: Ni, Chaojun, et al.
Published: (2025)

VLA Model Post-Training via Action-Chunked PPO and Self Behavior Cloning
by: Wang, Si-Cheng, et al.
Published: (2025)

CycleVLA: Proactive Self-Correcting Vision-Language-Action Models via Subtask Backtracking and Minimum Bayes Risk Decoding
by: Ma, Chenyang, et al.
Published: (2026)

Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration
by: Zhang, Ninghao, et al.
Published: (2026)

TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments
by: Huang, Zhiyu, et al.
Published: (2026)

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
by: Li, Haozhan, et al.
Published: (2025)

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

How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf
by: Jiang, Wenqi, et al.
Published: (2026)

RoboNurse-VLA: Robotic Scrub Nurse System based on Vision-Language-Action Model
by: Li, Shunlei, et al.
Published: (2024)

JEPA-VLA: Video Predictive Embedding is Needed for VLA Models
by: Miao, Shangchen, et al.
Published: (2026)

BioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory Manipulation
by: Du, Zhaohui, et al.
Published: (2026)

From Knowing to Doing Precisely: A General Self-Correction and Termination Framework for VLA models
by: Zhang, Wentao, et al.
Published: (2026)

CoFreeVLA: Collision-Free Dual-Arm Manipulation via Vision-Language-Action Model and Risk Estimation
by: Zhai, Xuanran, et al.
Published: (2026)

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

Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models
by: Shi, Liangzhi, et al.
Published: (2026)

Beyond Human Demonstrations: Diffusion-Based Reinforcement Learning to Generate Data for VLA Training
by: Yang, Rushuai, et al.
Published: (2025)

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

RationalVLA: A Rational Vision-Language-Action Model with Dual System
by: Song, Wenxuan, et al.
Published: (2025)

BlockVLA: Accelerating Autoregressive VLA via Block Diffusion Finetuning
by: Wang, Ruiheng, et al.
Published: (2026)

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

Safety-critical Locomotion of Biped Robots in Infeasible Paths: Overcoming Obstacles during Navigation toward Destination
by: Lee, Jaemin, et al.
Published: (2024)

AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models
by: Sun, Xiaoquan, et al.
Published: (2026)

DroneVLA: VLA based Aerial Manipulation
by: Mehboob, Fawad, et al.
Published: (2026)

VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts
by: Jiang, Yuhua, et al.
Published: (2026)