HorizonWind2004 / reconstruction-alignmentLinks
Official repo of paper "Reconstruction Alignment Improves Unified Multimodal Models". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning.
☆263Updated this week
Alternatives and similar repositories for reconstruction-alignment
Users that are interested in reconstruction-alignment are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2025] VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models☆61Updated last week
- VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning☆264Updated 5 months ago
- [NeurIPS 2025] Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations☆174Updated 2 weeks ago
- WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation☆151Updated this week
- Official repository of "GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing"☆289Updated this week
- DiffusionNFT: Online Diffusion Reinforcement with Forward Process☆190Updated last week
- [CVPR2025 Highlight] PAR: Parallelized Autoregressive Visual Generation. https://yuqingwang1029.github.io/PAR-project☆175Updated 6 months ago
- [ICCV2025]Code Release of Harmonizing Visual Representations for Unified Multimodal Understanding and Generation☆169Updated 4 months ago
- ☆156Updated 3 months ago
- ☆119Updated last month
- GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning☆96Updated 4 months ago
- [NeurIPS 2024] The official implement of research paper "FreeLong : Training-Free Long Video Generation with SpectralBlend Temporal Atten…☆56Updated 3 months ago
- Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"☆409Updated 3 months ago
- [NeurIPS 2025 DB] OneIG-Bench is a meticulously designed comprehensive benchmark framework for fine-grained evaluation of T2I models acro…☆71Updated 2 weeks ago
- Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning☆219Updated 4 months ago
- [CVPR 2025] Science-T2I: Addressing Scientific Illusions in Image Synthesis☆61Updated 5 months ago
- Official repository for the UAE paper, unified-GRPO, and unified-Bench☆130Updated 3 weeks ago
- [CVPR 2025] T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation☆91Updated 4 months ago
- official code repo of CVPR 2025 paper PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation☆44Updated 2 months ago
- Implementation of "S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models"☆139Updated 2 weeks ago
- Official respository for ReasonGen-R1☆69Updated 3 months ago
- Official implementation of LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment.☆83Updated 5 months ago
- Code for: "Long-Context Autoregressive Video Modeling with Next-Frame Prediction"☆261Updated 5 months ago
- 【CVPR 2025 Oral】Official Repo for Paper "AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea"☆188Updated 6 months ago
- [Neurips 2025 NextVid Workshop Oral✨] Official Implementation of VideoGen-of-Thought: Step-by-step generating multi-shot video with minim…☆45Updated last week
- [ICCV 2025] Official repo for "GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation"☆187Updated 3 months ago
- Code release for "PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop" (ICML 2025)☆41Updated 4 months ago
- LongLive: Real-time Interactive Long Video Generation☆442Updated this week
- Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics☆147Updated 4 months ago
- [NeurIPS 2025 D&B🔥] ImgEdit: A Unified Image Editing Dataset and Benchmark☆189Updated 3 weeks ago