Long chain-of-thought reasoning improves vision-language models (VLMs), but it also exposes a temporal grounding failure: as generation unfolds, models may drift from image evidence while reinforcement learning still provides only a final-answer reward. We study this gap through visual revisit, a temporally localized r...
Zhaolu Kang, Tai-Long Luo, Chen-Xin Li et al.· 0 citations
Ambiguity is a central feature of natural communication: a sentence, image, or sound may remain underspecified until evidence from the other channels is considered. Yet current multimodal benchmarks mostly test perception, recognition, or reasoning over already determinate inputs, leaving unclear whether omni-modal lar...
Zhaolu Kang, Yi-Di Wang, Yi-Le Li et al.· 0 citations
Video multimodal large language models (MLLMs) keep climbing video question answering benchmarks, yet shuffling the frames, masking the segment that supports the answer, or occluding the target object barely changes their predictions. The accuracy rests on appearance and language priors, not on the temporal evidence th...
Zhaolu Kang, Shi-Yu Liu, Tai-Long Luo et al.· 0 citations
A new multimodal ICL framework is proposed that combines contrastive demonstration modeling with the self-refinement capability of MLLMs and consistently improves MLLM performance, with particularly notable gains on visual question answering (VQA).
Ming-Bo Yang, Wen-Qiang Wang, Zhaolu Kang et al.· 1 citation
SCEval (Structure-Corruption Evaluation) a diagnostic evaluation protocol that keeps the question, answer space, and modality channels fixed while applying controlled structural corruptions to text, vision, and audio individually and jointly is introduced.
Zhaolu Kang, Mei-Xin Wu, Yu Xue et al.· 1 citation
COMET is a temporally grounded framework that systematically strengthens video MLLMs through explicit temporal representation, appearance-motion fusion, and direction-aware optimization and achieves consistent overall improvements with a pronounced motion-temporal bias.
Cheng-Hua Zhu, Zhaolu Kang, Qifan Shi et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.