Asymmetric Multimodal Learning with Decomposed JEPAs
cs.LG, cs.CV
Submitted: 2026-11-12
Updated: 2026-11-12
Code: https://github.com/Vixel2006/D-JEPA
Terminology
Sources
- VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
- Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
- CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
- Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning
- Learning Transferable Visual Models From Natural Language Supervision
- Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality
- Nonnegative Decomposition of Multivariate Information
- Barlow Twins: Self-Supervised Learning via Redundancy Reduction
- Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis