Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
3
Unfrozen video-language models implicitly know when they've seen enough evidence, a signal that can be extracted and used to boost answer accuracy by nearly 10% without retraining.
Get GPT-4o-level long-video QA performance with 10x fewer FLOPs by using a hierarchical, training-free frame selector that combines multimodal experts and fuzzy logic.
