Search papers, labs, and topics across Lattice.
6
0
5
8
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.
AdaQ enables MLLMs to achieve superior long video understanding with just 64 frames, outperforming state-of-the-art methods by a striking margin.
Forget bolting vision onto language models – truly powerful multimodal AI demands rethinking architectures from the ground up.
Leaderboard-topping video models are still surprisingly brittle, failing on basic video reasoning tasks unless given the right textual cues.
Ditch autoregressive MLLMs: Omni-Diffusion proves that mask-based discrete diffusion models can unify multimodal understanding and generation across text, speech, and images with competitive performance.
