LINs-lab / ERWLinks
[Preprint] Efficient Generative Model Training via Embedded Representation Warmup
☆36Updated 5 months ago
Alternatives and similar repositories for ERW
Users that are interested in ERW are comparing it to the libraries listed below
Sorting:
- [CVPR 2025] Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis☆122Updated 4 months ago
- This repository includes the official implementation of our paper "Grouping First, Attending Smartly: Training-Free Acceleration for Diff…☆52Updated 4 months ago
- Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think!☆120Updated 7 months ago
- Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening☆66Updated 4 months ago
- [Preprint] GMem: A Modular Approach for Ultra-Efficient Generative Models☆39Updated 6 months ago
- UniDisc: A discrete diffusion model for joint multimodal generation, enabling controllable and efficient text-image synthesis, editing, a…☆126Updated 6 months ago
- the official repo for "D-AR: Diffusion via Autoregressive Models"☆114Updated 3 months ago
- [CVPR2025 Highlight] PAR: Parallelized Autoregressive Visual Generation. https://yuqingwang1029.github.io/PAR-project☆175Updated 6 months ago
- Autoregressive Image Generation with Randomized Parallel Decoding☆77Updated 6 months ago
- Official Implementation of Muddit [Meissonic II]: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model.☆90Updated 2 months ago
- [ICLR 2025] Implementation of Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding☆45Updated 5 months ago
- An Efficient Text-to-Image Generation Pretrain Pipeline☆116Updated 5 months ago
- [NeurIPS'25 Spotlight] Boosting Generative Image Modeling via Joint Image-Feature Synthesis☆72Updated 2 weeks ago
- [NeurIPS 2025] Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations☆174Updated 3 weeks ago
- PixNerd: Pixel Neural Field Diffusion☆121Updated 3 weeks ago
- [NeurIPS 2025] IEAP: Image Editing As Programs with Diffusion Models☆101Updated last week
- Vico: Compositional Video Generation as Flow Equalization☆58Updated 10 months ago
- Transition Models☆128Updated this week
- ☆59Updated last month
- The official implementation of "Neighboring Autoregressive Modeling for Efficient Visual Generation"☆57Updated 6 months ago
- DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space☆183Updated last week
- Official implementation of Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents (NeurIPS 2025)☆39Updated 2 weeks ago
- [NeurIPS 2025] HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation☆67Updated 3 weeks ago
- (ICCV 2025) "Principal Components" Enable A New Language of Images☆63Updated 2 months ago
- Official Implementation of "LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis"☆72Updated last month
- [CVPR 2025] CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient☆107Updated last week
- ☆119Updated last month
- Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection☆45Updated last month
- Codes accompanying the paper "Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment"☆36Updated 7 months ago
- [ICCV2025] The code of our work "Golden Noise for Diffusion Models: A Learning Framework".☆186Updated 2 months ago