[CVPR 2026] Fine-Grained GRPO for Precise Preference Alignment in Flow Models
☆50Feb 21, 2026Updated last week
Alternatives and similar repositories for Granular-GRPO
Users that are interested in Granular-GRPO are comparing it to the libraries listed below
Sorting:
- Siggraph 2025 Journal track☆23Aug 13, 2025Updated 6 months ago
- ☆54May 6, 2025Updated 10 months ago
- [ICLR 2026] NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics☆121Jan 26, 2026Updated last month
- Official implementation of Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning☆236Feb 10, 2026Updated 3 weeks ago
- PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation☆53Jan 5, 2026Updated 2 months ago
- A unified framework for controllable caption generation across images, videos, and audio. Supports multi-modal inputs and customizable ca…☆52Jul 24, 2025Updated 7 months ago
- Collection of forcing related autoregressive video Gen☆86Feb 27, 2026Updated last week
- [NeurIPS'25] Official implementation of "Emergent Temporal Correspondences from Video Diffusion Models"☆95Dec 3, 2025Updated 3 months ago
- An official implementation of Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching☆66Sep 11, 2025Updated 5 months ago
- UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture☆94Feb 5, 2026Updated last month
- ☆11Apr 12, 2022Updated 3 years ago
- [CVPR 2026] A training-free, mask-free framework for 3D shape editing.☆25Dec 12, 2025Updated 2 months ago
- Official implementation of LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment.☆85May 4, 2025Updated 10 months ago
- [ICCV 2025 Workshop Outstanding Paper Award] VChain: Chain-of-Visual-Thought for Reasoning in Video Generation☆115Oct 7, 2025Updated 4 months ago
- [CVPR 2026] Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"☆84Feb 13, 2026Updated 3 weeks ago
- Benchmark dataset and code of MSRVTT-Personalization☆52Nov 10, 2025Updated 3 months ago
- ☆20Sep 5, 2025Updated 6 months ago
- A stable & generalizable GRPO method for AR image generation☆31Oct 1, 2025Updated 5 months ago
- Least-squares Reverse Time Migration using 1D scalar wave equation. Very simple and for demonstration purposes only.☆10Sep 4, 2017Updated 8 years ago
- Reimplementation of NeRF (Neural Radiance Fields) (ECCV2020)☆10May 4, 2023Updated 2 years ago
- ☆43Dec 1, 2025Updated 3 months ago
- Download Web-10K data by querying Bing Image Search☆10Feb 1, 2022Updated 4 years ago
- [RecSys] 네이버 부스트캠프 AI Tech 3기 / 가진 옷 기반 패션 아이템 추천 서비스 - 유쾌한발상팀☆13Jun 13, 2022Updated 3 years ago
- Not All Patches Are Equal: Hierarchical Dataset Condensation for Single Image Super-Resolution☆10May 7, 2024Updated last year
- Provide customized diffusers training and inference code for different needs☆12Jan 16, 2024Updated 2 years ago
- Official code repository for the paper titled "Efficient Molecular Conformer Generation with SO(3) Averaged Flow-Matching and Reflow" (IC…☆13Jan 8, 2026Updated last month
- ☆15Dec 2, 2025Updated 3 months ago
- Support code for controlnet diffuser step of "A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis", EGSR…☆12Sep 20, 2024Updated last year
- The official code of "Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling"☆47Feb 26, 2026Updated last week
- A PyTorch implementation of the paper "MMoT: Mixture-of-Modality-Tokens Transformer for Composed Multimodal Conditional Image Synthesis".☆12Jan 16, 2023Updated 3 years ago
- An efficient distillation method for flow matching models☆22Feb 1, 2026Updated last month
- Official repository for the ICCV 25 paper: QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generati…☆21Jul 29, 2025Updated 7 months ago
- official code for "3D Question Answering via only 2D Vision-Language Models"☆23Updated this week
- Official implementation of "Towards One-Step Causal Video Generation via Adversarial Self-Distillation" (arXiv 2025). A novel framework f…☆25Nov 4, 2025Updated 4 months ago
- [ICCV 2025] CHORDS: Diffusion Sampling Accelerator with Multi-core Hierarchical ODE Solvers☆13Updated this week
- [Siggraph Asia 25] SS4D: Native 4D Generative Model via Structured Spacetime Latents☆33Dec 17, 2025Updated 2 months ago
- yolo1 yolo2 yolo3☆12Nov 22, 2022Updated 3 years ago
- Here we proposed two novel algorithms, the Direct Subsequence Dynamic Time Warping for nanopore raw signal search (DSDTWnano) and the con…☆10Jul 13, 2020Updated 5 years ago
- Localize to Binauralize: Audio Spatialization from Visual Sound Source Localization (ICCV 2021)☆10Oct 11, 2021Updated 4 years ago