JEDI is the first online end-to-end latent diffusion world model that trains latents from denoising loss rather than reconstruction, achieving competitive Atari100k results with 43% less VRAM and over 3x faster sampling than pixel diffusion baselines.
Diffusion hyperfeatures: Searching through time and space for semantic correspondence.Advances in Neural Information Processing Systems, 36:47500–47510, 2023
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
A new evaluation framework using latent diffusion on frozen vision backbones shows video-pretrained models consistently outperform image-based ones in forecasting entire trajectories across abstraction levels.
DiT-ST converts complete-text captions into split-text primitives via LLMs and injects them hierarchically across denoising stages to reduce semantic confusion in DiT-based text-to-image generation.
citing papers explorer
-
JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning
JEDI is the first online end-to-end latent diffusion world model that trains latents from denoising loss rather than reconstruction, achieving competitive Atari100k results with 43% less VRAM and over 3x faster sampling than pixel diffusion baselines.
-
Frozen Forecasting: A Unified Evaluation
A new evaluation framework using latent diffusion on frozen vision backbones shows video-pretrained models consistently outperform image-based ones in forecasting entire trajectories across abstraction levels.
-
Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning
DiT-ST converts complete-text captions into split-text primitives via LLMs and injects them hierarchically across denoising stages to reduce semantic confusion in DiT-based text-to-image generation.