The paper introduces MEQ, a mutual feedback architecture that iteratively refines two multimodal inputs into coupled embeddings, each embedding incorporating information from the other. By continuously exchanging information between the modalities, the model converges to a fixed point that improves representation quality. Experiments on classification and visual grounding tasks show that MEQ achieves competitive or superior performance compared to concatenation-based baselines, and qualitatively enhances visual grounding when paired with complementary modalities.
By Ho-min Park, Byungkon Kang
arXiv:2606. 11614v1 Announce Type: cross Abstract: Multimodal learning hinges on capturing redundant, unique, and synergistic information across modalities, which collectively constitute multimodal interactions.
By Zequn Yang, Yake Wei, Haotian Ni, Zhihao Xu, Di Hu
arXiv:2505. 19614v2 Announce Type: replace Abstract: Multimodal learning has seen remarkable progress, particularly with large-scale pre-training across various modalities.
By Sanghyuk Chun, Olga Russakovsky
arXiv:2607. 16789v1 Announce Type: new Abstract: Real-world perception and decision making are inherently multimodal, integrating complementary signals across modalities.
By Sana Tonekaboni, Viktoria Schuster, Caroline Uhler
arXiv:2606. 05109v1 Announce Type: new Abstract: To leverage the full potential of multimodal data, we need representations that go beyond the state-of-the-art alignment and fusion approaches and exploit all cross-modal interactions without sacrificing modality-specific information.
By Vasiliki Rizou, Pascal Frossard, Dorina Thanou
arXiv:2610.00576v1 Announce Type: new
Abstract: In this paper, we propose Gestalt, a new paradigm of large multimodal model built around multimodal interplay. Despite rapid advances, large multimodal...
By Zequn Yang, Yu Miao, Haotian Ni, Ziheng Chen, Chengxiang Huang, Dongzhan Zhou, Kai Chen, Qi Zhang, Ji-Rong Wen, Yake Wei, Di Hu
To leverage the full potential of multimodal data, we need representations that go beyond the state-of-the-art alignment and fusion approaches and exploit all cross-modal interactions without sacrificing modality-specific information. Learning disentangled representations is a principled way to identify these underlying shared and unique factors that are hidden in observational data.
arXiv:2508. 12466v2 Announce Type: replace-cross Abstract: Traditional multimodal learning approaches rely on alignment pre-training to bridge vision and language modalities, typically by projecting visual features into discrete text token spaces using large-scale image--text data.
By Xuhui Zhan, Tyler Derr
arXiv:2609.37225v1 Announce Type: cross
Abstract: Multimodal large language models (MLLMs) have shown strong potential for universal multimodal representation learning. However, existing methods eith...
By Zijing Cai, Yuzhe Wang, Jingxian Zhu, Fengbin Zhu, Richang Hong
The paper investigates image tokenizers as the visual language of unified multimodal models by creating a controlled autoregressive testbed that tracks task‑specific validation losses during multimodal continual pretraining across text, image, text‑to‑image, and image‑to‑text predictions. It shows that losses must be analyzed by task, that the loss–performance relationship varies with the token space, and that better reconstruction does not always lead to stronger downstream performance. The study also demonstrates how tokenizer design choices—such as discriminator use, semantic supervision, and vocabulary size—affect joint modeling and downstream results.
UVU is a vision-language unified autoregressive framework that integrates visual supervision directly into the pre-training stage of multimodal large language models. By using continuous visual encoding and a large-scale iterative hierarchical clustering algorithm to build a pixel-level visual codebook, UVU enables lossless representation of visual inputs and autoregressive generation of pixel-level image tokens alongside textual tokens. This approach synergizes pixel-level visual perception with semantic-level visual understanding, allowing models to internalize visual reconstruction capabilities and improve multimodal understanding performance.
By Zhehan Kan, Xinghua Jiang, Yubo Zhu, Yanlin Liu, Xiaochen Yang, Zhixiang Wei, Shifeng Liu, Qingmin Liao, Wenming Yang, Xin Li, Yinsong Liu, Deqiang Jiang, Xing Sun
arXiv:2609.40362v1 Announce Type: new
Abstract: We present Multimodal Flow, a fully continuous generative model of language and vision. Most unified multimodal models either model both language and q...
By Hongyuan Tao, Xinggang Wang, Lianghui Zhu, Yongkang Li, Yunchao Wei, Bin Feng, Shaoyu Chen, Qian Zhang, Chang Huang, Kai Yu