Search papers, labs, and topics across Lattice.
College of Computer Science and Software Engineering, Shenzhen University, China, Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), China
4
0
8
4
Forget RLHF and massive datasets: SAGE co-evolves reasoning abilities in LLMs using only a small seed set and a clever quartet of self-improving agents.
LLM win rates in multi-agent games can nearly double (from 25% to 50%) simply by optimizing the context provided during inference.
Ditch the likelihood approximations: LFPO directly optimizes denoising logits in diffusion LMs via contrastive updates, leading to faster inference and better code/reasoning performance.
LLMs learn faster and perform better when you optimize prompts and weights together, boosting performance by 30% and cutting interaction turns by 40%.
