LEF-JEPA: Denoising-Trained Latent Energy Fields for Spatial Representation Learning
cs.CV, cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- Application of Quantum Annealing to Training of Deep Neural Networks
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- Introduction to Latent Variable Energy-Based Models: A Path Towards Autonomous Machine Intelligence
- Vision Pretraining for Dense Spatial Perception
- LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics
- Neural Boltzmann Machines
- V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
- A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures
- VISReg: Variance-Invariance-Sketching Regularization for JEPA training
- Kaiwu-PyTorch-Plugin: Bridging Deep Learning and Photonic Quantum Computing for Energy-Based Models and Active Sample Selection
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