Search papers, labs, and topics across Lattice.
4
0
7
3
GPT-Policy is introduced, a general-agent framework for in-context robot learning that integrates a context compiler that preserves task-relevant visual transitions, a VLM that proposes robot-tool actions, and a constrained controller that verifies and executes each action and reports its outcome.
Stochastic modality masking during training can boost bimanual robotic manipulation success rates by over 30% without complex architectural changes.
Light-WAM achieves high-performance robot manipulation with just 0.44B parameters, revolutionizing the efficiency of World Action Models.
Forget fine-tuning every LLM: ReQueR trains a single, RL-powered query refiner that coaxes hidden reasoning abilities out of diverse, frozen models at inference time.
