← LEARN LLM · RESEARCH INDEX 1 ENTRY

Representation Learning

1 post tagged Representation Learning. All topics

2026

1 note
  1. 01
    Deep dive··17 min read

    Generative Modeling via Drifting: Training-Time Pushforward Evolution for One-Step Generation

    Mingyang Deng, He Li, Tianhong Li, Yilun Du, and Kaiming He (MIT & Harvard, arXiv:2602.04770) introduce Drifting Models, moving iterative distribution evolution from inference time to training time. Driven by a kernelized attraction-repulsion drifting field in self-supervised feature space, a single-pass DiT-L generator reaches 1.54 FID in latent space and 1.61 FID in pixel space on ImageNet 256×256 at 1-NFE, while matching 100-step Diffusion Policy on robotic control.