stepfun-ai / Step3-VL-10BLinks
Step3-VL-10B: A compact yet frontier multimodal model achieving SOTA performance at the 10B scale, matching open-source models 10-20x its size.
☆152Updated this week
Alternatives and similar repositories for Step3-VL-10B
Users that are interested in Step3-VL-10B are comparing it to the libraries listed below
Sorting:
- ☆141Updated 3 months ago
- This is an early exploration to introduce Interleaving Reasoning to Text-to-image Generation field and achieve the SoTA benchmark perform…☆84Updated 4 months ago
- Implementation for "The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer"☆76Updated 2 months ago
- [ICLR 2025] AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark☆138Updated 7 months ago
- ☆35Updated last month
- Official implementation of "Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence"☆128Updated last month
- Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"☆76Updated last month
- ☆96Updated 6 months ago
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆94Updated 10 months ago
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?☆85Updated 6 months ago
- https://huggingface.co/datasets/multimodal-reasoning-lab/Zebra-CoT☆114Updated 2 months ago
- Official Implementation of LaViDa: :A Large Diffusion Language Model for Multimodal Understanding☆187Updated last month
- [NeurIPS 2025] HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation☆73Updated 4 months ago
- Official implementation of Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning☆208Updated last week
- Quick Long Video Understanding [TMLR2025]☆73Updated 2 months ago
- An official implementation of "CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning"☆175Updated 3 weeks ago
- Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment☆64Updated 6 months ago
- [NeurIPS 2025] Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations☆193Updated 4 months ago
- [NeurIPS 2024 D&B Track] Official Repo for "LVD-2M: A Long-take Video Dataset with Temporally Dense Captions"☆75Updated last year
- WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning☆36Updated 7 months ago
- Code and dataset link for "DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World"☆121Updated 3 months ago
- Code release for Ming-UniVision: Joint Image Understanding and Geneation with a Continuous Unified Tokenizer☆135Updated 3 months ago
- Towards Scalable Pre-training of Visual Tokenizers for Generation☆421Updated last month
- ☆80Updated 6 months ago
- [Preprint] GMem: A Modular Approach for Ultra-Efficient Generative Models☆42Updated 10 months ago
- The SAIL-VL2 series model developed by the BytedanceDouyinContent Group☆76Updated 4 months ago
- Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision☆194Updated 3 weeks ago
- Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe☆138Updated last month
- Official respository for ReasonGen-R1☆74Updated 6 months ago
- EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling☆201Updated 2 months ago