5 papers
SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling
Haoran Xu, Hongyu Wang, Yifei Gao +3
On-policy distillation (OPD) trains a student on its own trajectories with dense per-token supervision from a stronger teacher, and often outperforms off-policy distillation and st…
Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning
Haoran Xu, Hongyu Wang, Yifei Gao +4
Visual reasoning requires integrating evidence distributed across regions, attributes, and relations, making single-chain reasoning prone to early perceptual commitment and halluci…
BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation
Hongyu Wang, Chuyan Xiong, Ruiping Wang +1
Deploying powerful Vision-Language-Action (VLA) models on edge devices is limited by their massive size. In this paper, we take a deployment-oriented view of VLA training: we targe…
MoTE: Mixture of Ternary Experts for Memory-efficient Large Multimodal Models
Hongyu Wang, Jiayu Xu, Ruiping Wang +5
Large multimodal Mixture-of-Experts (MoEs) effectively scale the model size to boost performance while maintaining fixed active parameters. However, previous works primarily utiliz…
Robotic Programmer: Video Instructed Policy Code Generation for Robotic Manipulation
Senwei Xie, Hongyu Wang, Zhanqi Xiao +2
Zero-shot generalization across various robots, tasks and environments remains a significant challenge in robotic manipulation. Policy code generation methods use executable code t…