Search papers, labs, and topics across Lattice.
3
0
8
3
Scaling up robot data and closing the loop with state decoding and automated reward scoring allows a 2B parameter video world simulator to outperform larger, dedicated robotic world models in real-world policy transfer.
LLM agents can learn to use tools more efficiently and accurately by explicitly learning when *not* to use them, leading to a 25% increase in tool productivity.
Forget manual skill annotation: Ctx2Skill lets language models teach themselves to master complex contexts, unlocking better reasoning without human intervention.
