Skip to content

PaperCodex

Subscribe

Autoregressive Modeling

HART: Generate 1024×1024 Images Faster and More Efficiently Than Diffusion Models

HART: Generate 1024×1024 Images Faster and More Efficiently Than Diffusion Models 635

For teams building AI-powered visual applications—whether in creative tools, digital content platforms, or rapid prototyping—the trade-off between image quality, speed,…

01/13/2026Autoregressive Modeling, High-resolution Synthesis, Image Generation
NextStep-1: High-Fidelity Autoregressive Image Generation Without Diffusion or Discrete Token Loss

NextStep-1: High-Fidelity Autoregressive Image Generation Without Diffusion or Discrete Token Loss 553

Autoregressive (AR) models have long dominated natural language generation, but applying the same step-by-step prediction approach to images has been…

01/09/2026Autoregressive Modeling, Image Editing, Text-to-Image Generation
MAGI-1: Autoregressive Video Generation at Scale with Constant Memory and Real-Time Streaming

MAGI-1: Autoregressive Video Generation at Scale with Constant Memory and Real-Time Streaming 530

MAGI-1 is a breakthrough world model designed for autoregressive video generation at scale. Unlike conventional video diffusion or transformer-based approaches…

01/05/2026Autoregressive Modeling, Image-to-video, Video Generation
Copyright © 2026 PaperCodex.
  • Facebook
  • YouTube
  • Twitter

PaperCodex