Search papers, labs, and topics across Lattice.
Peking University
5
0
8
Motion-aligned latent dynamics enable robots to learn actionable behaviors from human videos without losing visual fidelity across different embodiments.
Long-horizon LLM agents can achieve 96.9% task success by learning to adapt their external execution support through trainable harness policies.
The evolution of Color Fundus Photography shows that integrating multimodal datasets with advanced preprocessing can transform clinical reasoning in ophthalmology.
Achieving efficient uncertainty quantification in multi-modal regression could redefine the landscape of trustworthy large-scale learning.
Selective teacher intervention in multi-turn training can boost agent performance by over 13% by mitigating the impact of early errors.
