Search papers, labs, and topics across Lattice.
4
23
8
45
Credit-addressable reasoning boosts multimodal geometry accuracy by over 8 points, revealing the critical role of structured learning in complex tasks.
By rethinking RLHF, MicroCoder-GRPO enables smaller code generation models to rival larger counterparts, achieving significant performance gains and revealing 34 training insights.
Forget massive datasets – targeted training on a smaller, carefully curated dataset of challenging competitive programming problems yields 3x faster gains in code generation performance.
A 1-bit LLM can match the performance of full-precision models, promising huge gains in efficiency.
