Search papers, labs, and topics across Lattice.
3
0
5
2
Multi-hop reasoning accuracy improves dramatically when LLMs dynamically assess and refine their reasoning paths instead of relying on static knowledge.
FlowCTS-OPD boosts performance metrics by over 3% while solving the temporal supervision mismatch that plagues traditional methods.
Reasoning with LLMs just got a whole lot faster: MemoSight cuts KV cache footprint by 66% and speeds up inference by 1.56x without sacrificing CoT performance.
