multimodal learning
Learning strategies that integrate information across various types of data (e.g., text, images, audio) to improve task performance and broaden model applicability.
- A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity
- Balancing Multimodal Training Through Game-Theoretic Regularization
- CMoB: Modality Valuation via Causal Effect for Balanced Multimodal Learning
- Lyapunov-Stable Adaptive Control for Multimodal Concept Drift
- MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series
- MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning
- Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning
- Multimodal Negative Learning
- Rethinking Multimodal Learning from the Perspective of Mitigating Classification Ability Disproportion
- Rethinking Multimodal Learning from the Perspective of Mitigating Classification Ability Disproportion
- TRIDENT: Tri-Modal Molecular Representation Learning with Taxonomic Annotations and Local Correspondence
- TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation