Multimodal Large Language Models have demonstrated impressive video understanding, yet their ability to reason over long-form narratives is often masked by visual-centric evaluations and inefficient context processing. Existing benchmarks over-rely on visual heuristics while marginalizing auditory cues, effectively reducing models to"silent observers"that bypass genuine cross-modal reasoning. Moreover, standard dense sampling creates an evidence-context trade-off: increasing frames to capture evidence inevitably leads to attention distraction and token explosion. To bridge these gaps, we present Video-HolmesV2, a novel benchmark designed for Deep Audio-Visual Coupling. Unlike previous works, it enforces an Evidence-Based Evaluation, requiring models to justify answers with precise spatio-temporal audio-visual evidence, thereby reducing confounding effects of guessing and hallucinated evidence. To support this, we introduce: (1) a Multi-Model Cross-Verification pipeline to ensure task rigor; (2) a Spatio-temporal Evidence-Aware Metric for fine-grained calibration. Furthermore, we propose an Audio-Text Guided Token Compression framework. By fusing task intent with auditory anchors, our method distills high-value reasoning cues to mitigate long-context noise. In our evaluation, even strong proprietary models achieve below 60% accuracy, while our approach outperforms comparable open-source omni-models.
Zhao-Yang Wei, Zipeng Wang, Yu-She Cao et al.· 0 citations
LaP-Forensics is presented, a multimodal framework that augments RGB semantics with reconstruction-based forensic evidence that supports the utility of the residual stream under the evaluated settings, while free-form textual faithfulness and reliability under post-processing remain open limitations.
Can Wang, Yuhao Wang, Yu-She Cao et al.· arXiv.org· 1 citation
UniVVT is presented, a unified end-to-end framework that reframes VVT as semantically conditioned video generation, eliminating mask, pose, and warping modules at inference and validating implicit semantic guidance as a simple and effective alternative to fragile geometric preprocessing for end-to-end virtual try-on.
Yushe Cao, Shikun Feng, Fei Shen et al.· 0 citations
LiveVVT is introduced, a rolling streaming diffusion framework that preserves bounded bidirectional modeling within causal recurrent generation, and a progressive distillation framework integrating bidirectional VVT learning, teacher-trajectory regression for causal few-step adaptation, and Collaborative Matching Distillation, which couples teacher-distribution matching with rolling flow matching on real videos to align optimization with recurrent inference.
Yu-She Cao, Shikun Feng, Ru-Xiang Duan et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
