Search papers, labs, and topics across Lattice.
5
0
5
11
Mirror-Fusion Attention reveals that lightweight geometric priors can significantly enhance self-supervised learning performance without the need for extensive model redesigns.
Benchmark scores for coding agents may mislead progress assessments, with only 39% of GSO tasks passing validity checks across machines.
Dockerless achieves a 14.3 AUC point improvement in program verification without the overhead of Docker environments, revolutionizing efficiency in training coding agents.
Integrating visual graphs with text interfaces allows LLM agents to reduce token consumption by 26% while enhancing their issue-resolution accuracy.
FastContext cuts coding agent token usage by 60% while boosting resolution rates by 5.5% by decoupling code exploration from task-solving.
