Introduces VidPair-Halluc benchmark of 1K background-controlled adversarial video pairs and 11K QA pairs generated via PairFlow pipeline to evaluate hallucination in LVMs.
mdpo: Conditional preference optimization for multimodal large language models,
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
P²-DPO generates on-policy preference pairs targeting focus-and-enhance perception and visual robustness, combined with a calibration loss, to reduce hallucinations in LVLMs more effectively than human-feedback baselines.
TLVS mitigates hallucinations in LVLMs via token-level extraction and visual-sensitivity-adaptive steering applied only at critical decoding steps.
Adaptive selection among a library of audio perturbations in contrastive decoding produces task-dependent accuracy gains, including +4.3% on an existence task via a hidden-state selector.
A roadmap that defines architectural nativity for multimodal models and categorizes them into Multi-to-Text, Multi-to-Target, and Multi-to-Multi types while outlining an industrial pipeline toward unified transformer-based native multimodal modeling.
citing papers explorer
-
Toward Native Multimodal Modeling: A Roadmap
A roadmap that defines architectural nativity for multimodal models and categorizes them into Multi-to-Text, Multi-to-Target, and Multi-to-Multi types while outlining an industrial pipeline toward unified transformer-based native multimodal modeling.