rongyaofang / PUMALinks
Empowering Unified MLLM with Multi-granular Visual Generation
☆130Updated 7 months ago
Alternatives and similar repositories for PUMA
Users that are interested in PUMA are comparing it to the libraries listed below
Sorting:
- [ICCV2025]Code Release of Harmonizing Visual Representations for Unified Multimodal Understanding and Generation☆162Updated 3 months ago
- WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation☆144Updated 3 weeks ago
- [ICLR 2025] AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark☆127Updated 3 months ago
- Official Repository of paper: Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing☆89Updated this week
- [NeurIPS 2024 D&B Track] Official Repo for "LVD-2M: A Long-take Video Dataset with Temporally Dense Captions"☆69Updated 11 months ago
- [ICLR'25] Reconstructive Visual Instruction Tuning☆114Updated 5 months ago
- The official implementation for "MonoFormer: One Transformer for Both Diffusion and Autoregression"☆86Updated 11 months ago
- GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning☆96Updated 3 months ago
- Official respository for ReasonGen-R1☆68Updated 2 months ago
- Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision☆114Updated last week
- Structured Video Comprehension of Real-World Shorts☆190Updated last month
- Code for MetaMorph Multimodal Understanding and Generation via Instruction Tuning☆209Updated 4 months ago
- official repo for "VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation" [EMNLP2024]☆96Updated 7 months ago
- ☆21Updated 7 months ago
- ☆50Updated 3 weeks ago
- Official repository of "GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing"☆283Updated 4 months ago
- Official Implementation of Paper Transfer between Modalities with MetaQueries☆228Updated last month
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆86Updated 6 months ago
- ☆152Updated 2 months ago
- Official Implementation of ICLR'24: Kosmos-G: Generating Images in Context with Multimodal Large Language Models☆73Updated last year
- Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations☆165Updated 2 weeks ago
- Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning.☆106Updated this week
- The code repository of UniRL☆40Updated 3 months ago
- Official Pytorch implementation for LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR 2025 Oral).☆90Updated 7 months ago
- Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning☆210Updated 3 months ago
- TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation☆206Updated 3 weeks ago
- ☆74Updated 2 months ago
- Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning☆114Updated 3 weeks ago
- [ICML2025] The code and data of Paper: Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation☆117Updated 10 months ago
- A collection of vision foundation models unifying understanding and generation.☆57Updated 8 months ago