Audio-Contrastive Preference Optimization (ACPO) mitigates audio hallucination in AVLMs via output-contrastive and input-contrastive objectives that enforce faithful audio grounding.
Advances in neural information processing systems33, 1877–1901 (2020) 1
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.
citing papers explorer
-
Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models
Audio-Contrastive Preference Optimization (ACPO) mitigates audio hallucination in AVLMs via output-contrastive and input-contrastive objectives that enforce faithful audio grounding.
-
How Far Are Video Models from True Multimodal Reasoning?
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.