Search papers, labs, and topics across Lattice.
3
0
7
2
Visual transition reasoning, not just diverse data, unlocks significant multimodal LLM improvements, with just 2,000 examples boosting 22 benchmarks.
This paper proposes World Model RL (WMRL), which replaces environment execution with a world model to remove this bottleneck and accelerates training by 3-4x on various tasks at different agent scales, while exceeding the performance of standard RL baselines.