Search papers, labs, and topics across Lattice.
Affiliation:
5
0
7
3
HIL-UMI is introduced, a policy-guided Universal Manipulation Interface (UMI) framework for robot-free human-in-the-loop VLA post-training that preserves the iterative and policy-aware nature of human-in-the-loop learning while decoupling data collection from robot deployment.
Dataset representation in NLP is alarmingly uneven, with geographic blind spots that could skew AI development and policy.
AgentSpec slashes response times for LLM agents by addressing high rejection rates and optimizing token budgets, outperforming existing methods.
A novel data synthesis approach enables a lightweight model to outperform state-of-the-art planning systems by over 10x in household appliance manipulation tasks.
Selective test-time scaling can boost robot control success rates while minimizing unnecessary computation, achieving up to 82.5% success in complex environments.
