Search papers, labs, and topics across Lattice.
3
0
6
2
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.
LLMs can be fine-tuned more efficiently by adapting experts in the frequency domain, leading to better performance with fewer parameters.
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%.
