AMAP-ML / USPLinks
USP: Unified Self-Supervised Pretraining for Image Generation and Understanding
☆83Updated last month
Alternatives and similar repositories for USP
Users that are interested in USP are comparing it to the libraries listed below
Sorting:
- [ICCV2025]Code Release of Harmonizing Visual Representations for Unified Multimodal Understanding and Generation☆151Updated 2 months ago
- ☆144Updated last month
- [ICCV 25] VMBench: A Benchmark for Perception-Aligned Video Motion Generation☆58Updated last week
- Official Repository of paper: Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing☆79Updated 3 weeks ago
- [CVPR 2025 (Oral)] Open implementation of "RandAR"☆182Updated 3 weeks ago
- WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation☆136Updated last month
- Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model.☆62Updated last month
- Implements VAR+CLIP for text-to-image (T2I) generation☆145Updated 6 months ago
- ☆101Updated last month
- TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation☆103Updated 2 months ago
- GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning☆94Updated 2 months ago
- [CVPR 2025] CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient☆105Updated 4 months ago
- Empowering Unified MLLM with Multi-granular Visual Generation☆129Updated 6 months ago
- Official respository for ReasonGen-R1☆57Updated last month
- This is the official implementation for ControlVAR.☆117Updated 7 months ago
- Code for: "Long-Context Autoregressive Video Modeling with Next-Frame Prediction"☆236Updated 3 months ago
- Autoregressive Image Generation with Randomized Parallel Decoding☆70Updated 4 months ago
- CAR: Controllable AutoRegressive Modeling for Visual Generation☆121Updated 8 months ago
- [CVPR2025 Highlight] PAR: Parallelized Autoregressive Visual Generation. https://yuqingwang1029.github.io/PAR-project☆169Updated 4 months ago
- [CVPRW 2025] UniToken is an auto-regressive generation model that combines discrete and continuous representations to process visual inpu…☆86Updated 3 months ago
- [CVPR 2025] 🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".☆366Updated this week
- [CVPR 25] A framework named B^2-DiffuRL for RL-based diffusion model fine-tuning.☆34Updated 4 months ago
- Official implementation of LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment.☆79Updated 3 months ago
- A collection of vision foundation models unifying understanding and generation.☆57Updated 7 months ago
- Official repository of "GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing"☆272Updated 3 months ago
- [CVPR 2025] DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention☆169Updated 5 months ago
- Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"☆394Updated last month
- [ICLR'25] Reconstructive Visual Instruction Tuning☆101Updated 4 months ago
- Official Pytorch implementation for LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR 2025 Oral).☆83Updated 5 months ago
- ☆84Updated 4 months ago