Search papers, labs, and topics across Lattice.
4
0
6
3
SCOPE's structured feedback mechanism boosts code generation accuracy, achieving a notable 39.4% pass rate on LiveCodeBench V6鈥攐utperforming existing methods by a significant margin.
Fixing label errors in RVL-CDIP can enhance model performance by over 8 percentage points, but removing test-train duplicates may paradoxically hurt accuracy.
VERITAS reveals that incorporating verifier feedback can boost theorem proving success rates by over 10%, challenging the efficacy of traditional binary pass/fail approaches.
LLMs can now reliably fix decompiled code, but only if you make them *execute* it.
