Search papers, labs, and topics across Lattice.
4
0
6
6
Current MLLMs falter in following complex video instructions, revealing a significant oversight in their evaluation metrics.
FIRM-Video reveals that a checklist-driven approach can significantly enhance the reliability of text-to-video reward modeling, achieving state-of-the-art performance in evaluation metrics.
Leaderboard-topping video models are still surprisingly brittle, failing on basic video reasoning tasks unless given the right textual cues.
A billion-scale SAR foundation model closes the domain generalization gap in SAR imagery by 10% mIoU, thanks to a physics-guided MoE architecture.
