6 papers
Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility
Yiheng Li, Feng Liang, Dan Kondratyuk +3
The substantial training cost of diffusion models hinders their deployment. Immiscible Diffusion recently showed that reducing diffusion trajectory mixing in the noise space via li…
DADP: Domain Adaptive Diffusion Policy
Pengcheng Wang, Qinghang Liu, Haotian Lin +4
Learning domain adaptive policies that can generalize to unseen transition dynamics, remains a fundamental challenge in learning-based control. Substantial progress has been made t…
AdaMEM: Test-Time Adaptive Memory for Language Agents
Yunxiang Zhang, Yiheng Li, Ali Payani +1
A central challenge for language agents is utilizing past experience to adapt to dynamic test-time conditions. While recent work demonstrates the promise of agentic memory mechanis…
Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation
Guojian Zhan, Letian Tao, Pengcheng Wang +6
Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling com…
WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving
Yiheng Li, Cunxin Fan, Chongjian Ge +9
Language models uncover unprecedented abilities in analyzing driving scenarios, owing to their limitless knowledge accumulated from text-based pre-training. Naturally, they should…
Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
Yiheng Li, Heyang Jiang, Akio Kodaira +3
In this paper, we point out that suboptimal noise-data mapping leads to slow training of diffusion models. During diffusion training, current methods diffuse each image across the…