Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
0
Variable-length action chunks can boost LLM agent performance by up to 31% while slashing decision-making time by nearly 79%.
Pruning irrelevant visual tokens can boost medical reasoning performance by over 100%, transforming how VLMs approach sparse medical images.
Automated evaluation-driven skill evolution could redefine how we build and assess agentic systems, making them more reliable and efficient.
