Search papers, labs, and topics across Lattice.
3
0
5
3
A 7B parameter model, guided by a novel RL framework, can now generate multi-page websites that rival the functionality of a 671B parameter model, while surpassing it in visual appeal.
Forget parallel corpora: CodePivot shows you can train a 7B model to beat behemoth LLMs at multilingual code transpilation by pivoting through Python and using a clever RL reward.
Forget external debuggers: ReflexiCoder teaches LLMs to self-reflect and self-correct code, rivaling GPT-5.1 in performance while slashing inference costs by 40%.
