Search papers, labs, and topics across Lattice.
5
9
8
5
State-aware tokenization can double the success rate in robotic manipulation tasks by adapting actions to the robot's current state.
LLMs struggle to grasp the nuances of cross-cultural aesthetic stylistics, often mistaking surface-level linguistic features for genuine cultural understanding.
Decoupling high-level VLM planning from low-level diffusion-based control lets robots reason like foundation models *and* execute precisely, outperforming end-to-end approaches in complex manipulation tasks.
LLMs can learn to anticipate their opponents' moves and make better decisions in strategic games by explicitly modeling the other player's behavior during training.
LLMs are surprisingly bad at keeping up with how people's minds change over time, lagging humans by 45% on a new benchmark designed to test this crucial social skill.
