Search papers, labs, and topics across Lattice.
3
0
6
Achieve up to 52.5% compression in LLM chain-of-thought reasoning *while improving* accuracy by dynamically calibrating CoT length.
A principled framework for General World Models reveals the limitations of current systems and the architectural requirements for future progress.
Visual reasoning gets a boost: forcing models to "draft" their reasoning in code and render visual proofs dramatically improves performance by bridging the gap between perception and logical structure.
