Large multimodal models are shown to rely on prior knowledge and text cues rather than video order under temporal inconsistency, and a benchmark plus preference-optimization method partially correct this.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency
Large multimodal models are shown to rely on prior knowledge and text cues rather than video order under temporal inconsistency, and a benchmark plus preference-optimization method partially correct this.