Search papers, labs, and topics across Lattice.
2
0
3
4
GPU kernel optimization agents can regress by up to 19% when transferring distilled knowledge across DSLs, revealing that source attempt quality, not just success, dictates transfer efficacy.
Real-world coding tasks, reverse-engineered from actual commits and scenarios, make Tencent WorkBuddy Bench a game-changer in contamination-resistant evaluation for coding agents.
