Search papers, labs, and topics across Lattice.
3
0
6
EvoThink reduces inference-time token usage by pruning redundant reasoning steps while boosting LRM performance through the optimization of valuable failed attempts.
LLMs struggle with code migration when APIs evolve, but KCoEvo's knowledge graph augmentation boosts migration accuracy and execution success.
Chain-of-Thought prompting doesn't always improve LLMs' ability to solve discrete optimization problems, and surprisingly, "disordered" datasets can sometimes boost performance on simpler tasks.
