[ICLR 2025] Official Implementation of Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
-
Updated
Jul 15, 2026 - Python
[ICLR 2025] Official Implementation of Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
A fast speech-to-speech & speech-to-text translation model that supports simultaneous decoding and offers 28× speedup.
Official repository for our NeurIPS 2024 paper: DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation
Fine-tuned Laya model that triages GitHub issues in a single CPU forward pass — training data, held-out benchmarks, and a ready-to-use GitHub Action.
To associate your repository with the non-autoregressive-transformers topic, visit your repo's landing page and select "manage topics."