8 papers
Model-Based Online Decision Making via Generative Trajectory Planning
Haldun Balim, Yilun Du, Na Li
Online decision-making faces a tension between efficient inference and long-horizon reasoning. Value-based methods rely on short-horizon bootstrapping that limits the propagation o…
SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators
Yuncong Yang, Zhengtao Han, Furkan Ozyurt +6
World models are increasingly used as policy-in-the-loop imagination environments, where reliable rollouts require fine-grained controllability with respect to low-level robot acti…
Hierarchical Policy Learning via Spectral Decomposition
Shuxin Cao, Liquan Wang, Walker Byrnes +3
In this paper, we identify a semantic decomposition in robot action sequences, separating task-level motion intent from execution-level refinements. By analyzing actions in the spe…
Model-Based Diffusion Sampling for Predictive Control in Offline Decision Making
Haldun Balim, Na Li, Yilun Du
Offline decision-making via diffusion models often produces trajectories that are misaligned with system dynamics, limiting their reliability for control. We propose Model Predicti…
MoTVLA: A Vision-Language-Action Model with Unified Fast-Slow Reasoning
Wenhui Huang, Changhe Chen, Han Qi +3
Integrating visual-language instructions into visuomotor policies is gaining momentum in robot learning for enhancing open-world generalization. Despite promising advances, existin…
Flexible Locomotion Learning with Diffusion Model Predictive Control
Runhan Huang, Haldun Balim, Heng Yang +1
Legged locomotion demands controllers that are both robust and adaptable, while remaining compatible with task and safety considerations. However, model-free reinforcement learning…
SPIE: Semantic and Structural Post-Training of Image Editing Diffusion Models with AI feedback
Elior Benarous, Yilun Du, Heng Yang
This paper presents SPIE: a novel approach for semantic and structural post-training of instruction-based image editing diffusion models, addressing key challenges in alignment wit…
MoE-Loco: Mixture of Experts for Multitask Locomotion
Runhan Huang, Shaoting Zhu, Yilun Du +1
We present MoE-Loco, a Mixture of Experts (MoE) framework for multitask locomotion for legged robots. Our method enables a single policy to handle diverse terrains, including bars,…