[ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incentivize reasoning capability.
Repository Index
132,241 visible repositories in the index
1–8 of 8 · Most stars
Repo for SeedVR2 (ICLR2026) & SeedVR (CVPR2025 Highlight)
- diffusion-transformer
- image-restoration
- one-step-diffusion-model
- video-restoration
[ICLR2026] Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
[ICLR2026] SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
- diffusion-transformer
- one-step-diffusion-model
- video-generation
- video-restoration
[ICLR2026] codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004)
HoloPart: Generative 3D Part Amodal Segmentation
- generative-3d
- iclr2026
- part-segmentation
- tripo
(ICLR2026) ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation
- 3d
- 3d-generation
- 3d-reconstruction
- image-to-3d
Official implementation of our serial spatial intelligence robotc foundation model (SLA & Spatial Forcing[ICLR2026]).
- embodied-ai
- robot-learning