JEPAhead: From Inpainting to Causal Forecasting for Urban Driving
cs.CV, cs.AI
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- Revisiting Feature Prediction for Learning Visual Representations from Video
- Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- World Models
- Mastering Diverse Domains through World Models
- Model-Based Imitation Learning for Urban Driving
- GAIA-1: A Generative World Model for Autonomous Driving
- Enhancing End-to-End Autonomous Driving with Latent World Model
- Self-Supervised Representation Learning with Joint Embedding Predictive Architecture for Automotive LiDAR Object Detection
- Self-Supervised JEPA-based World Models for LiDAR Occupancy Completion and Forecasting
- Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving
- What Probing Reveals about Autonomous Driving: Linking Internal Prediction Errors to Ego Planning
- DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
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