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
OmniHallu is a unified framework for detecting hallucinations in multimodal large language models across both comprehension and generation tasks involving image, video, and audio modalities. It introduces OmniHallu-Bench, a 10,000-sample benchmark with claim-level human annotations for six cross-modal tasks (I2T, V2T, A2T, T2I, T2V, T2A). The system uses a multi‑agent architecture that decomposes outputs into atomic claims, verifies them with modality‑specific experts, and aggregates evidence through structured reasoning, while a preference‑optimized verifier reduces expert calls by 66% with minimal performance loss.
By Jianjiang Yang, Peihang Li, Shanqing Xu, Mengchen Qian, Lu Zhang, Meng Luo
arXiv:2607. 10299v1 Announce Type: new Abstract: Recent advances in large-scale multimodal models have drivenremarkable progress in vision-language tasks; however, comprehensiveomni-modal understanding remains under-explored, largely due to thescarcity of datasets with rich, explicitly aligned auditory cues.
By Kaiying Yan, Luoyi Sun, Xiao Zhou, Weidi Xie
arXiv:2608. 04902v1 Announce Type: cross Abstract: Video-to-audio (V2A) generation extends image-to-audio generation (I2A) by introducing consecutive frames that provide essential temporal cues for audio synthesis.
By Zehua Chen, Junyou Wang, Yuxuan Jiang, Zhenying Fang, Yusheng Dai, Jianfei Chen, Ziwei Liu, Jun Zhu
ViSSFlow is a unified flow‑matching framework that jointly tackles Video‑to‑Sound (V2S) and Visual Text‑to‑Speech (VisualTTS) generation. It incorporates a Diffusion Transformer with a disentangled condition aggregation mechanism, using cross‑attention for semantic cues and self‑attention for dense visual information. The authors also introduce a feature‑level data synthesis strategy to compensate for limited joint training data, and demonstrate that a single model can be trained end‑to‑end without sacrificing performance on either task.
By Xin Cheng, Yuyue Wang, Xihua Wang, Yihan Wu, Kaisi Guan, Yijing Chen, Peng Zhang, Xiaojiang Liu, Meng Cao, Ruihua Song
arXiv:2603. 15685v2 Announce Type: replace-cross Abstract: Omnimodal large language models (OmniLLMs) jointly process audio and visual streams, but the resulting long multimodal token sequences make inference prohibitively expensive.
By Bingzhou Li, Tao Huang
arXiv:2607. 24017v1 Announce Type: cross Abstract: The empirical success of attention mechanism in Multimodal Large Language Models (MLLMs) often obscures its inherent, subtle flaws.
By Pengkun Jiao, Bin Zhu, Jingjing Chen, Yu-gang Jiang