Search papers, labs, and topics across Lattice.
4
0
9
8
LLMs can now automatically evolve and optimize GPU kernels to beat hand-tuned and proprietary models like Gemini and Claude.
Pretraining isn't just about scaling data volume; daVinci-LLM's ablations reveal that data processing depth, domain-specific strategies, and compositional balance are equally critical for unlocking LLM capabilities.
Forget benchmarks: AI can now learn "scientific taste" and propose research ideas with higher potential impact than humans, thanks to a novel reinforcement learning approach using citation data.
A 4B-parameter model, InternVL-U, outperforms 14B-parameter models in multimodal generation and editing, proving that size isn't everything.
