Publications (9)
Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs
Junhao Shi, Siyin Wang, Xiaopeng Yu +3
Vision-Language-Action (VLA) models are fundamentally bottlenecked by the scarcity of expert demonstrations -- triplets of observations, instructions, and actions that are costly t…
VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks
Shiduo Zhang, Zhe Xu, Peiju Liu +8
General-purposed embodied agents are designed to understand the users' natural instructions or intentions and act precisely to complete universal tasks. Recently, methods based on…
FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization
Yicheng Liu, Shiduo Zhang, Zibin Dong +12
Autoregressive vision-language-action (VLA) models have recently demonstrated strong capabilities in robotic manipulation. However, their core process of action tokenization often…
Model-Based Opponent Modeling
Xiaopeng Yu, Jiechuan Jiang, Wanpeng Zhang +2
When one agent interacts with a multi-agent environment, it is challenging to deal with various opponents unseen before. Modeling the behaviors, goals, or beliefs of opponents coul…
WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning
Senyu Fei, Xiaopeng Yu, Siyin Wang +3
Reinforcement learning (RL) post-training of Vision-Language-Action (VLA) models has shown strong promise for robotic manipulation. Among RL methods, critic-based approaches rely o…
Time-reversed photoacoustic guided time-reversed ultrasonically encoded optical focusing
Juze Zhang, Zijian Gao, Xiaopeng Yu +3
Deep-tissue optical imaging is a longstanding challenge limited by scattering. Both optical imaging and treatment can benefit from focusing light in deep tissue beyond one transpor…
HiMe: Hierarchical Embodied Memory for Long-Horizon Vision-Language-Action Control
Li Ji, Siyin Wang, Pengfang Qian +5
Current Vision-Language-Action (VLA) models excel at robotic manipulation but often struggle with non-Markovian tasks requiring long-term memory and reasoning due to their reliance…
Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models
Jinhao Wu, Shiduo Zhang, Yicheng Liu +9
Most vision-language-action (VLA) models map observations directly to actions without explicit intermediate planning, which limits performance on long-horizon tasks where early mis…
Predicting the Output Structure of Sparse Matrix Multiplication with Sampled Compression Ratio
Zhaoyang Du, Yijin Guan, Tianchan Guan +7
Sparse general matrix multiplication (SpGEMM) is a fundamental building block in numerous scientific applications. One critical task of SpGEMM is to compute or predict the structur…