Yilun Du's banner
Yilun Du's profile picture

Yilun Du

@du_yilun • 11,820 subscribers

Assistant Professor at Harvard @KempnerInst + CS. PhD @MIT_CSAIL, BS MIT. Generative Models, Compositionality, Embodied Agents, Robot Learning.

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

Sharing our work at NeurIPS Conference on reasoning with EBMs! We learn an EBM over simple subproblems and combine EBMs at test-time to solve complex reasoning problems (3-SAT, graph coloring, crosswords). Generalizes well to complex 3-SAT / graph coloring/ N-queens problems.
0:57
du_yilun's profile picture

Sharing our work at NeurIPS Conference on reasoning with EBMs! We learn an EBM over simple subproblems and combine EBMs at test-time to solve complex reasoning problems (3-SAT, graph coloring, crosswords). Generalizes well to complex 3-SAT / graph coloring/ N-queens problems.

Yilun Du

47,478 görüntüleme • 8 ay önce

Introducing an approach to directly ground video generation models to policy execution without needing any action labels! Our approach uses a generic goal-conditioned exploration procedure to learn a policy that works across robots / embodiments!
1:09
du_yilun's profile picture

Introducing an approach to directly ground video generation models to policy execution without needing any action labels! Our approach uses a generic goal-conditioned exploration procedure to learn a policy that works across robots / embodiments!

Yilun Du

21,392 görüntüleme • 1 yıl önce

Introducing a way to convert synthesized robot videos to robot execution without using any action labels! We also release a codebase (with pretrained models) for text-to-video generation. Train your own models for robot control in only 1 day with 4 GPUs!
1:51
du_yilun's profile picture

Introducing a way to convert synthesized robot videos to robot execution without using any action labels! We also release a codebase (with pretrained models) for text-to-video generation. Train your own models for robot control in only 1 day with 4 GPUs!

Yilun Du

20,949 görüntüleme • 2 yıl önce

Daha fazla içerik yok.