A training-free test-time feedback loop, using attention drift to select key frames, improves video MLLM accuracy, with the largest gains on knowledge-heavy VideoMMMU.
On the importance of being emergent.Constructivist Foundations, 5(2):89, March 2010
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
CyberV: Cybernetics for Test-time Scaling in Video Understanding
A training-free test-time feedback loop, using attention drift to select key frames, improves video MLLM accuracy, with the largest gains on knowledge-heavy VideoMMMU.