Search papers, labs, and topics across Lattice.
Affiliation:
3
0
0
Small language models can now master complex tool use by learning from teachers without inheriting their biases or forgetting their own exploration gains.
Asynchronous execution fundamentally alters action semantics for world-model controllers, causing planning models to hallucinate future actions and recurrent models to misattribute transitions.
Uncertainty-aware querying can significantly stabilize policy updates in offline reinforcement learning, leading to improved performance without additional environment interaction.
