Search papers, labs, and topics across Lattice.
3
0
6
0
Variable-length action chunks can boost LLM agent performance by up to 31% while slashing decision-making time by nearly 79%.
Current vision-language models falter in ultra-resolution reasoning, with errors primarily stemming from evidence grounding and local perception.
VLMs get a 24% performance boost and run 56% faster on robot manipulation tasks by explicitly modeling action advantages and exploring multiple future paths, instead of relying on noisy foresight predictions.
