facebookresearch / MMRB2Links
Data and sample evaluation codes for Multimodal Rewardbench 2
β133Updated last month
Alternatives and similar repositories for MMRB2
Users that are interested in MMRB2 are comparing it to the libraries listed below
Sorting:
- π¦ Yo'Chameleon: Your Personalized Chameleon (CVPR 2025)β150Updated 8 months ago
- Efficient DiT architecture for text2any tasks, ICLR2025β447Updated 8 months ago
- Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Betterβ186Updated this week
- β74Updated 10 months ago
- The official repository of SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimizationβ156Updated last week
- MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDEβ1,087Updated 3 months ago
- [ICCVβ25] Official implementation of paper "Towards Performance Consistency in Multi-Level Model Collaboration"β43Updated 3 months ago
- [Tutorial] Few-Step Distillation for Text-to-Image Generation: A Practical Guideβ337Updated last month
- Official repository of DARE: dLLM Alignment and Reinforcement Executorβ159Updated this week
- Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learningβ178Updated 3 months ago
- [NeurIPS'2025] Official repository for "LiveStar: Live Streaming Assistant for Real-World Online Video Understanding"β104Updated 2 months ago
- First Video Deep Research Benchmarkβ134Updated 2 weeks ago
- [Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics]: VisuoThink: Empowering LVLM Reasoning with Mulβ¦β101Updated 6 months ago
- Official implementation of "JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization"β313Updated last month
- **Deep Video Discovery (DVD)** is a deep-research style question answering agent designed for understanding extra-long videos.β346Updated 3 months ago
- A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.β706Updated 2 weeks ago
- [AAAI 2026 Oral] Official repository for InfiGUI-G1. We introduce Adaptive Exploration Policy Optimization (AEPO) to overcome semantic alβ¦β129Updated 2 months ago
- Evaluation of Text-to-Video Generation Models: A Dynamics Perspective[NeurIPS 2024].β274Updated last year
- Official repository of MMGenBenchβ120Updated 10 months ago
- [NeurIPS 2025π₯]Main source code of SRPO framework.β186Updated 2 months ago
- [NeurIPS 2025] More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Modelsβ215Updated 3 months ago
- [NeurIPS'24] Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategyβ73Updated last year
- [ICLR 2026] IVEBench - Benchmark for Instruction-Guided Video Editingβ67Updated last week
- Explain Before You Answer: A Survey on Compositional Visual Reasoningβ306Updated 3 months ago
- [NeurIPS2025 spotlightβ ] Official implementation for "RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Effβ¦β219Updated last month
- Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Viewsβ181Updated last month
- [CVPR 2025 Highlight] Official code for "Olympus: A Universal Task Router for Computer Vision Tasks"β428Updated 8 months ago
- Efficient controlnet for DiTsβ382Updated 8 months ago
- This repository contains the code of the paper "IC-World: In-Context Generation for Shared World Modeling".β123Updated 3 weeks ago
- The accepted paper for cvpr2025.β55Updated last month