Search papers, labs, and topics across Lattice.
4
0
7
Frontier search agent performance does not require complex multi-agent swarms or test-time search verifiers: a single ReAct policy trained via iterative SFT-RL climbing hits 56.4% on Humanity's Last Exam and 92.9% on DeepSearchQA.
MoNO achieves unprecedented per-prompt diversity in diffusion sampling while eliminating the need for auxiliary quality-control objectives.
Change detection in remote sensing just got smarter: JL1-CC&QA not only identifies what changed but also explains why it matters through interactive questioning.
Achieve superior control over the distortion-perception tradeoff in diffusion-based inverse problems by decoupling MAP estimation and posterior sampling into distinct stages.
