6 papers
Drift is a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic Planning
Kewei Chen, Yayu Long, Mingsheng Shang
Despite rapid progress in Vision-Language-Action (VLA) models for robotic control, instruction drift remains a persistent failure mode in long-horizon tasks. This paper reconceptua…
ElasticFlow: One-Step Physics-Consistent Policy with Elastic Time Horizons for Language-Guided Manipulation
Kewei Chen, Yayu Long, Shuai Li +1
Diffusion policies have demonstrated exceptional performance in embodied AI. However, their iterative denoising process results in high latency, and existing acceleration methods o…
ATAAT: Adaptive Threat-Aware Adversarial Tuning Framework against Backdoor Attacks on Vision-Language-Action Models
Kewei Chen, Yayu Long, Shuai Li +1
Addressing the escalating security vulnerabilities in Vision-Language-Action (VLA) models, this study investigates backdoor attacks targeting the visual pathway. We identify a core…
DRAE: Dynamic Retrieval-Augmented Expert Networks for Lifelong Learning and Task Adaptation in Robotics
Yayu Long, Kewei Chen, Long Jin +1
We introduce Dynamic Retrieval-Augmented Expert Networks (DRAE), a groundbreaking architecture that addresses the challenges of lifelong learning, catastrophic forgetting, and task…
FT-NCFM: An Influence-Aware Data Distillation Framework for Efficient VLA Models
Kewei Chen, Yayu Long, Shuai Li +1
The powerful generalization of Vision-Language-Action (VLA) models is bottlenecked by their heavy reliance on massive, redundant, and unevenly valued datasets, hindering their wide…
PIPHEN: Physical Interaction Prediction with Hamiltonian Energy Networks
Kewei Chen, Yayu Long, Mingsheng Shang
Multi-robot systems in complex physical collaborations face a "shared brain dilemma": transmitting high-dimensional multimedia data (e.g., video streams at ~30MB/s) creates severe…