OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images.
☆354Jun 1, 2025Updated 9 months ago
Alternatives and similar repositories for OpenThinkIMG
Users that are interested in OpenThinkIMG are comparing it to the libraries listed below
Sorting:
- instruction-following benchmark for large reasoning models☆44Aug 9, 2025Updated 6 months ago
- The official code repository for the FullFront benchmark☆26May 16, 2025Updated 9 months ago
- ☆1,129Nov 20, 2025Updated 3 months ago
- Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual in…☆1,338Feb 3, 2026Updated 3 weeks ago
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆71Jul 13, 2025Updated 7 months ago
- OpenThinkIMG is an end-to-end open-source framework that empowers Large Vision-Language Models to think with images.☆116Jul 11, 2025Updated 7 months ago
- ✈️ [ICCV 2025] Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints☆79Jul 10, 2025Updated 7 months ago
- [ACL' 25] The official code repository for PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models.☆88Feb 15, 2025Updated last year
- [NeurIPS 2025] NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation☆105Sep 18, 2025Updated 5 months ago
- [CVPR 2026] TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models☆64Feb 21, 2026Updated last week
- Code and data for "Timo: Towards Better Temporal Reasoning for Language Models" (COLM 2024)☆25Oct 23, 2024Updated last year
- ☆122Feb 4, 2026Updated 3 weeks ago
- [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…☆773Jan 26, 2026Updated last month
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆182Jun 5, 2025Updated 8 months ago
- [ICLR 2026] "VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use"☆156Feb 7, 2026Updated 3 weeks ago
- ☆23Oct 30, 2025Updated 4 months ago
- MMSearch-R1 is an end-to-end RL framework that enables LMMs to perform on-demand, multi-turn search with real-world multimodal search too…☆402Aug 26, 2025Updated 6 months ago
- RM-R1: Unleashing the Reasoning Potential of Reward Models☆159Jun 26, 2025Updated 8 months ago
- [ICLR2026] Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping☆62May 22, 2025Updated 9 months ago
- Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’☆2,305Oct 29, 2025Updated 4 months ago
- Official Code for "Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search"☆405Jan 29, 2026Updated last month
- Test-time preferenece optimization (ICML 2025).☆178May 8, 2025Updated 9 months ago
- Official PyTorch implementation of RACRO (https://www.arxiv.org/abs/2506.04559)☆19Jul 1, 2025Updated 8 months ago
- ☆66Jul 8, 2025Updated 7 months ago
- ☆98Jun 23, 2025Updated 8 months ago
- R1-onevision, a visual language model capable of deep CoT reasoning.☆576Apr 13, 2025Updated 10 months ago
- Video-R1: Reinforcing Video Reasoning in MLLMs [🔥the first paper to explore R1 for video]☆831Dec 14, 2025Updated 2 months ago
- MM-EUREKA: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning☆770Sep 7, 2025Updated 5 months ago
- Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.☆841May 14, 2025Updated 9 months ago
- This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-bas…☆1,360Updated this week
- code for Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning☆20Jul 16, 2024Updated last year
- A fork to add multimodal model training to open-r1☆1,493Feb 8, 2025Updated last year
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆4,649Updated this week
- Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)☆693Sep 24, 2025Updated 5 months ago
- ☆107Jun 10, 2025Updated 8 months ago
- ☆16Oct 12, 2025Updated 4 months ago
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆147Apr 9, 2025Updated 10 months ago
- Echos is a headless, API-driven DAW engine. It’s the backend for building AI tools that automate the entire music production lifecycle.☆55Nov 10, 2025Updated 3 months ago
- Code and data for "Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?" (ACL 2024)☆32Jul 3, 2024Updated last year