Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
0
5
0
Stop wasting money on inefficient LLM agent pipelines: AgentOpt finds model combinations that can slash costs by 13-32x without sacrificing accuracy.
LLMs represent meaning more abstractly than previously thought: changing the script of a sentence (Latin vs. Cyrillic) causes less representational divergence than paraphrasing it within the same script.