How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning A new RL method for visual reasoning, which significantly outperforms vanilla GRPO, and bypasses the need for explicit chain-of-thought supervision during training.
The main features of maifoundations/visionary-r1 are: Multimodal Understanding.
Projects with overlapping indexed features include: deepseek-ai/janus — Janus is a multimodal large language model and unified framework that integrates visual understanding and image… egolife-ai/ego-r1 — [TPAMI 2026] Ego-R1: Agentic Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning. eric-ai-lab/grit — Grounded Reasoning wiht Texts and Images (GRIT) is a novel method for training Multimodal Large Language Models… hitsz-tmg/veripo — [📄 Paper Link] [🤗 VerIPO-7B-v1.0]. jun297/v1 — Jiwan Chung   Junhyeok Kim   Siyeol Kim   Jaeyoung Lee   Minsoo Kim   Youngjae Yu. diankun-wu/spatial-mllm — Yi-Hsin Hung 1 , Yueqi Duan 1 , * Equal Contribution. 1 Tsinghua University NeurIPS 2025 (Spotlight).
Janus is a multimodal large language model and unified framework that integrates visual understanding and image generation within a single neural network. It functions as both a visual understanding model for analyzing images and a text-to-image generator. The system uses a unified transformer backbone and a multimodal latent space to bridge the gap between text and visual data. This architecture employs decoupled visual encoding and cross-modal tokenization to separate the paths for discriminative understanding and generative tasks, representing images as grids of discrete codes. The projec
TPAMI 2026 Ego-R1: Agentic Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning
Grounded Reasoning wiht Texts and Images (GRIT) is a novel method for training Multimodal Large Language Models (MLLMs) to perform grounded reasoning by generating reasoning chains that interleave natural language and explicit bounding box coordinates. This approach can use as few as 20 training…
Yi-Hsin Hung 1 , Yueqi Duan 1 , Equal Contribution. 1 Tsinghua University NeurIPS 2025 (Spotlight)