Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

MAGI-1: Autoregressive Video Generation at Scale

[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

[TMLR 2025🔥] A survey for the autoregressive models in vision.

[NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation

A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.

[ICLR 2025] Autoregressive Video Generation without Vector Quantization

Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in Pytorch

Scene Text Recognition with Permuted Autoregressive Sequence Models (ECCV 2022)