Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
0
3
6
OTQL boosts the success rates of robotic policies from 36% to 86% while slashing inference steps by 70%, revolutionizing flow policy optimization.
Even the most advanced VLMs like GPT-4o, GPT-5 and Gemini 2.5 Flash are outperformed in multi-actor human-robot interaction grounding by a system that selectively invokes VLMs based on a lightweight perception pipeline.