Search papers, labs, and topics across Lattice.
Tsinghua University, Beijing National Research Center for Information Science and Technology
Tsinghua AI2
0
5
Counterfactual controllability in video generation could be the key to creating self-evolving world models that understand and adapt to their actions.
LLMs can achieve massive performance gains on reasoning and knowledge-intensive tasks simply by iteratively refining their answers using pseudo-labels derived from unlabeled data.
