4 papers
FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space
Michael Murray, Daphne Chen, Simran Bagaria +7
Pretrained generative robot policies based on flow matching and diffusion have achieved impressive results across a wide range of manipulation tasks. Yet real-world deployments rou…
Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learning
Patrick Yin, Tyler Westenbroek, Zhengyu Zhang +9
Reinforcement learning in massively parallel physics simulations has driven major progress in sim-to-real robot learning. However, current approaches remain brittle and task-specif…
Benchmarking Affordance Generalization with BusyBox
Dean Fortier, Timothy Adamson, Tess Hellebrekers +5
Vision-Language-Action (VLA) models have been attracting the attention of researchers and practitioners thanks to their promise of generalization. Although single-task policies sti…
LoLA: Long Horizon Latent Action Learning for General Robot Manipulation
Xiaofan Wang, Xingyu Gao, Jianlong Fu +5
The capability of performing long-horizon, language-guided robotic manipulation tasks critically relies on leveraging historical information and generating coherent action sequence…