One-Step Next-Latent Prediction Is Not a World Model
stat.ML, cs.CV, cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- GPT-4 Technical Report
- Diffusion for World Modeling: Visual Details Matter in Atari
- Chronos: Learning the Language of Time Series
- Wasserstein GAN
- Masked Siamese Networks for Label-Efficient Learning
- Layer Normalization
- Learning Representations by Maximizing Mutual Information Across Views
- data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language
- Qwen Technical Report
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
- Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Genie: Generative Interactive Environments
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning
- Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
- Big Self-Supervised Models are Strong Semi-Supervised Learners
- Language Modeling Is Compression
- Unsupervised Visual Representation Learning by Context Prediction
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
- Online Conformal Prediction for Non-Exchangeable Panel Data
- Deep Time-Series Forecasting in 10 Years: A Survey