Search papers, labs, and topics across Lattice.
SII
2
0
6
Forget difficulty-based heuristics: InSight leverages weighted mutual information to select RL training data, boosting LLM reasoning and alignment with up to 2.2x speedup.
Forget end-to-end VLAs: GigaBrain-0.5M* leverages world models and reinforcement learning to achieve a 30% performance boost on complex robotic manipulation tasks, showcasing reliable long-horizon execution.