arXiv:2606. 25225v1 Announce Type: cross Abstract: Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual representation learning.
By Revant Teotia, Adrien Bardes, Michael Rabbat, Sumit Chopra, Matthew J. Muckley, Nicolas Ballas
The paper introduces a generalized multimodal foundation model that can handle arbitrary combinations of modalities and prediction tasks. It trains on large-scale synthetic multimodal datasets with diverse causal structures to learn transferable multimodal correlations. Experiments on 18 real-world datasets across 12 modalities and 11 tasks show competitive performance compared to specialized models without task-specific adaptation.
By Huizi Cui, Zongbo Han, Chenggong Ding, Naichuan Xiao, Jialong Yang, Jingdong Chen, Guangyu Wang, Qinghua Hu, Changqing Zhang
The paper introduces Fusion Anything Model (FAM), a foundation model designed for generalized multimodal data fusion that can handle arbitrary modality combinations and prediction tasks. FAM is trained on large-scale synthetic multimodal datasets generated via Structural Multimodal Causal Models (SMCMs), enabling it to encode transferable multimodal correlations. Experiments on 18 real-world datasets across 12 modalities and 11 tasks show that FAM performs competitively with specialized models without requiring task-specific adaptation.
By Huizi Cui, Zongbo Han, Chenggong Ding, Naichuan Xiao, Jialong Yang, Jingdong Chen, Guangyu Wang, Qinghua Hu, Changqing Zhang
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
TokenSwap introduces a method to benchmark and reduce the modality gap in multimodal large language models (MLLMs) by interleaving semantically aligned images with text tokens. By transforming text-only benchmarks like MMLU into image‑interleaved versions (TokenSwap‑Bench), the authors reveal a pervasive performance drop—averaging 19.6%—across 42 MLLMs, with reasoning models showing smaller gaps. Training with TokenSwap mitigates this gap while maintaining strong text‑only and vision‑language performance.
By Andong Hua, Colton Bishop, Igor Mordatch, Arian Hosseini, Jindong Gu, Aleksandra Faust, Rebecca Roelofs, Yao Qin
Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual representation learning. Since audio and visual streams naturally co-occur in video data, extending this success to jointly learn from both modalities is a natural next step, yet it remains challenging.