DuoJEPA: Cross-Modal Translation Between Unaligned Self-Supervised Embedding Spaces
cs.CV, cs.AI
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formats
- VL-JEPA: Joint Embedding Predictive Architecture for Vision-language
- TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation
- CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders
- Should We Skip Diffusion?
- Cutting the Skip: Training Residual-Free Transformers
- LeVLJEPA: End-to-End Vision-Language Pretraining Without Negatives
- Non-Contrastive Vision-Language Learning with Predictive Embedding Alignment
- Exploiting Similarities among Languages for Machine Translation
- Representation Learning with Contrastive Predictive Coding
- Towards a Unified Copernicus Foundation Model for Earth Vision
- Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs