Search papers, labs, and topics across Lattice.
4
0
6
0
AgentGUI cuts the time to analyze AI agent performance by 38% and boosts task completion rates by up to 34 percentage points, making human oversight of AI agents more efficient than ever.
Transforming textual skills into adaptable parameters at test time boosts LLM performance by over 6 points in complex software engineering tasks.
Evolving generative models in residual space reveals a powerful balance between local refinement and global exploration, enhancing data editing capabilities.
Offline RL can now refine trajectories conservatively without risking extrapolation, thanks to a novel framework that leverages local preference pairs for targeted improvements.
