arXiv AI
C3-UniMM: Causal Cycle-Consistent Unified Multimodal Modeling via Super Alignment and Shared Decoding Space
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Oct 1
Fusion Anything: A Generalized Multimodal Foundation Model
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.
arXiv AI
Jul 7
Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning
arXiv:2607. 02963v1 Announce Type: cross Abstract: Dense video captioning aims to generate temporally grounded descriptions of video events, benefiting both event-level video understanding and generation.
arXiv Machine Learning
Sep 22
Generalized Multimodal Foundation Model
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.
arXiv AI
Oct 5
Multimodal Representation Learning Conditioned on Semantic Relations
Multimodal representation learning has largely relied on contrastive models like CLIP that produce a single embedding per sample, which limits their ability to capture relation-dependent relevance. The proposed Relation-Conditioned Multimodal Learning (RCML) framework explicitly conditions embeddings on natural‑language relation descriptions, enabling the same sample to be represented differently under various relational contexts. RCML builds relation‑aware training pairs, incorporates a relation‑conditioned module, and uses a unified contrastive objective to jointly model cross‑modal alignment and relation‑induced structure, achieving superior performance on retrieval and classification tasks across zero‑shot, fine‑tuned, and out‑of‑domain settings.
arXiv Machine Learning
Jun 15
Context-aware Modality-Topology Co-Alignment for Multimodal Attributed Graphs
arXiv:2606. 14172v1 Announce Type: new Abstract: Multimodal Attributed Graphs (MAGs) model real-world entities by coupling graph topology with heterogeneous attributes such as text and images.
arXiv AI
Jul 14
PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging
arXiv:2604. 22823v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementary cross-modal alignment capabilities.