Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
0
5
10
SWE-bench leaderboards mask a massive real-world distribution shift: casual, under-specified user prompts drop agent resolution rates by 6.4 percentage points and reveal that reproduction steps provide zero measurable utility compared to explicit user intent.
DARD achieves a remarkable 2.71× speedup in dLLM inference while enhancing output quality by 4.35 points on CIDEr, redefining the efficiency landscape for large language models.