Search papers, labs, and topics across Lattice.
3
0
6
Structured scene graphs can dramatically enhance MLLMs' reasoning capabilities, leading to substantial performance gains on complex visual tasks.
By fusing CLIP with a diffusion model, DiCLIP unlocks surprisingly strong weakly supervised segmentation, outperforming prior methods and slashing training costs.
LLMs can generate high-quality, explainable fake news detection even when relying solely on unverified reports, by decomposing claims and modeling dependencies in a graph.
