How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.
NeurIPS 2024 Official PyTorch implementation code for realizing the technical part of Mamba-based traversal of rationale (Meteor) to improve performance of numerous vision language performances for diverse capabilities.
ACL-2026 MMSearch-R1 is an end-to-end RL framework that enables LMMs to perform on-demand, multi-turn search with real-world multimodal search tools.
ACL 2025 🔥 Rethinking Step-by-step Visual Reasoning in LLMs
GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
CogCoM: Train Large Vision-Language Models Diving into Details through Chain of Manipulations If you like our project, please give us a star ⭐ on GitHub for latest update.
The main features of thudm/cogcom are: Multimodal Reasoning Tools.
Open-source alternatives to thudm/cogcom include: byungkwanlee/meteor — [NeurIPS 2024] Official PyTorch implementation code for realizing the technical part of Mamba-based traversal of… evolvinglmms-lab/multimodal-search-r1 — [ACL-2026] MMSearch-R1 is an end-to-end RL framework that enables LMMs to perform on-demand, multi-turn search with… mbzuai-oryx/llamav-o1 — [ACL 2025 🔥] Rethinking Step-by-step Visual Reasoning in LLMs. thudm/glm-4.1v-thinking — GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.