Tencent-Hunyuan / MixGRPOLinks
MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
☆1,060Updated last month
Alternatives and similar repositories for MixGRPO
Users that are interested in MixGRPO are comparing it to the libraries listed below
Sorting:
- Efficient DiT architecture for text2any tasks, ICLR2025☆450Updated 6 months ago
- Lumina-DiMOO - An Open-Sourced Multi-Modal Large Diffusion Language Model☆898Updated last week
- Official implementation of "JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization"☆292Updated last month
- A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.☆661Updated this week
- Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning☆162Updated last month
- 🦎 Yo'Chameleon: Your Personalized Chameleon (CVPR 2025)☆148Updated 6 months ago
- [NeurIPS 2025 Spotlight] Towards Understanding Camera Motions in Any Video☆248Updated last week
- ☆74Updated 8 months ago
- Unified Multimodal Model for image generation/editing/understanding☆811Updated 2 months ago
- ☆142Updated 5 months ago
- Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better☆183Updated 5 months ago
- OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation☆239Updated 2 months ago
- ✨ WithAnyone is capable of generating high-quality, controllable, and ID consistent images☆520Updated last month
- Implementation of paper: Flux Already Knows – Activating Subject-Driven Image Generation without Training☆138Updated 2 months ago
- [CVPR 2025] A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation☆297Updated 9 months ago
- CVPR 2025 Highlight☆38Updated 3 months ago
- [NeurIPS'24] Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy☆73Updated 10 months ago
- ☆541Updated last week
- ☆100Updated last year
- Wan2.1 with Controlnet☆177Updated 8 months ago
- The official repository of SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization☆141Updated last month
- **Deep Video Discovery (DVD)** is a deep-research style question answering agent designed for understanding extra-long videos.☆313Updated last month
- Evaluation of Text-to-Video Generation Models: A Dynamics Perspective[NeurIPS 2024].☆276Updated last year
- [AAAI 2026 🔥] Official implementation of "NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representation"☆174Updated 3 months ago
- Official Implementation of "UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation"☆124Updated last month
- Official Repository of OmniCaptioner☆166Updated 7 months ago
- [CVPR 2024] Official code for "Text-Driven Image Editing via Learnable Regions"☆226Updated last year
- 4DNeX: Feed-Forward 4D Generative Modeling Made Easy☆789Updated 2 months ago
- ☆415Updated 8 months ago
- Efficient controlnet for DiTs☆382Updated 6 months ago