Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Yanyan, Song, Chaoda, Singh, Vikash, Li, Xinpeng, Ye, Kai, Hu, Zhe, Pu, Zhongzhu, Yin, Yu, Chaudhary, Vipin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

DroneVLA: VLA based Aerial Manipulation
di: Mehboob, Fawad, et al.
Pubblicazione: (2026)

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