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.
☆343Updated 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☆151Updated last week
- [ICCV2025]Code Release of Harmonizing Visual Representations for Unified Multimodal Understanding and Generation☆184Updated 7 months ago
- Official repository of "GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing"☆300Updated 3 months ago
- WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation☆177Updated 2 months ago
- ☆170Updated 6 months ago
- VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning☆269Updated 8 months ago
- [NeurIPS 2025] Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations☆192Updated 3 months ago
- [CVPR2025 Highlight] PAR: Parallelized Autoregressive Visual Generation. https://yuqingwang1029.github.io/PAR-project☆184Updated 9 months ago
- Official implementation for What matters for Representation Alignment: Global Information or Spatial Structure?☆174Updated 3 weeks ago
- Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"☆424Updated 6 months ago
- GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning☆101Updated 7 months ago
- Official Implementation of Paper Transfer between Modalities with MetaQueries☆287Updated 3 months ago
- Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning☆233Updated 7 months ago
- [CVPR 2025] T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation☆103Updated 2 months ago
- [NeurIPS 2025 DB] OneIG-Bench is a meticulously designed comprehensive benchmark framework for fine-grained evaluation of T2I models acro…☆95Updated this week
- [NeurIPS 2025 Oral] Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think☆237Updated 3 months ago
- ☆123Updated 4 months ago
- Code for: "Long-Context Autoregressive Video Modeling with Next-Frame Prediction"☆288Updated 8 months ago
- EARL: Editing with Autoregression and RL☆40Updated last month
- Towards Scalable Pre-training of Visual Tokenizers for Generation☆413Updated 3 weeks ago
- [NeurIPS 2025 D&B🔥] ImgEdit: A Unified Image Editing Dataset and Benchmark☆263Updated 2 months ago
- Official respository for ReasonGen-R1☆74Updated 6 months ago
- [CVPR 2025] 🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".☆419Updated 5 months ago
- [ICML2025] The code and data of Paper: Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation☆143Updated last year
- Official implementation of Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning☆196Updated last week
- Official repository for the UAE paper, unified-GRPO, and unified-Bench☆152Updated 4 months ago
- [CVPR 2025 (Oral)] Open implementation of "RandAR"☆204Updated 5 months ago
- [NIPS 25'] Evaluation code of paper "KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models"☆36Updated 2 months ago
- Code for MetaMorph Multimodal Understanding and Generation via Instruction Tuning☆231Updated 8 months ago
- 【CVPR 2025 Oral】Official Repo for Paper "AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea"☆211Updated 9 months ago