Search papers, labs, and topics across Lattice.
MBZUAI
3
0
6
Achieve robust multimodal generalization with few labels by exploiting both consensus and disagreement among modalities, even when some modalities are missing.
Deepfake detectors can be tricked into "reasoning" without visual grounding, but DeepfakeJudge offers a way to bootstrap MLLMs to generate faithful explanations and improve detection accuracy.
Geospatial agents can now reason more effectively about satellite imagery thanks to a new framework that aligns models with verified multi-step tool interactions and explicit reasoning traces.
