The paper investigates audio‑video diffusion models by examining the "attention triangle"—the cross‑attention links among text, audio, and video. It finds that the audio‑video edge is bidirectional and heavily influenced by model biases, leading to semantic leakage when prompts conflict with learned priors. The authors develop attention‑derived diagnostics and inference‑time interventions that improve semantic grounding without sacrificing generation quality.
By Sagi Polaczek, Noa Kraicer, Gal Metzer, Zhuo Ning, Ali Mahdavi-Amiri, Daniel Cohen-Or, Raja Giryes
arXiv:2602. 03570v2 Announce Type: replace Abstract: Audio-visual joint representation learning under Cross-Modal Generalization (CMG) aims to transfer knowledge from a labeled source modality to an unlabeled target modality through a unified discrete representation space.
By Bixing Wu, Yuhong Zhao, Zongli Ye, Jiachen Lian, Xiangyu Yue, Gopala Anumanchipalli
Video-HolmesV2 is a new benchmark that tests multimodal large language models on their ability to reason with spatio‑temporal audio‑visual evidence in long videos. It requires models to justify answers with precise evidence, uses a multi‑model cross‑verification pipeline and a spatio‑temporal evidence‑aware metric, and introduces an audio‑text guided token compression framework to reduce long‑context noise. In evaluations, even strong proprietary models score below 60% while the proposed approach outperforms comparable open‑source omni‑models.
By Zhaoyang Wei, Zipeng Wang, Yushe Cao, Chenhui Qiang, Shuaibing Cheng, Xuesong Yang, Sen Nie, Bowen Jiang, Wenchao Ding, Yanchao Hao, Zheng Wei, Xuehui Yu, Zhenjun Han
arXiv:2609.36798v1 Announce Type: cross
Abstract: Omni-modal large language models (LLMs) are expected to answer a question using the modality it explicitly refers to. However, existing training para...
By Yueran Ma, Ronghao Lin
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 c...
arXiv:2607. 03738v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) generate responses autoregressively, integrating visual and linguistic information in an evolving context.
By Varun Gupta, Vineet Gandhi, Makarand Tapaswi