From the 2 of 13 linked papers with an AI index.
13 papers
ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow
Dongxiu Liu, Haoyi Niu, Peng Cheng +5
The paper presents ODEWorld, a continuous-time latent world model that learns a physical-time flow using ODEs to predict future states at arbitrary temporal resolutions, improving…
Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models
Yufeng Ji, Wenhao Tang, Haoyi Niu +3
The paper introduces Action QFormer, a query-based interface that reorganizes multimodal information into action-focused representations to improve vision-language-action models, e…
xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing
Haoyi Niu, Qimao Chen, Tenglong Liu +5
Reusing pre-collected data from different domains is an appealing solution for decision-making tasks, especially when data in the target domain are limited. Existing cross-domain p…
When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning
Haoyi Niu, Shubham Sharma, Yiwen Qiu +4
Learning effective reinforcement learning (RL) policies to solve real-world complex tasks can be quite challenging without a high-fidelity simulation environment. In most cases, we…
A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models
Yilin Wang, Shangzhe Li, Haoyi Niu +3
We are interested in solving the problem of imitation learning with a limited amount of real-world expert data. Existing offline imitation methods often struggle with poor data cov…
PhysiAgent: An Embodied Agent Framework in Physical World
Zhihao Wang, Jianxiong Li, Jinliang Zheng +6
Vision-Language-Action (VLA) models have achieved notable success but often struggle with limited generalizations. To address this, integrating generalized Vision-Language Models (…