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.
A domain-agnostic framework enabling VLM self-improvement through competitive visual games
The main features of wangqinsi1/vision-zero are: Multimodal Understanding, Single Agent Optimization, Unsupervised Reward Methods.
Projects with overlapping indexed features include: chengsong-huang/r-zero — Check out our paper or webpage for the details. wantbook-book/serl — SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data. 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. diankun-wu/spatial-mllm — Yi-Hsin Hung 1 , Yueqi Duan 1 , * Equal Contribution. 1 Tsinghua University NeurIPS 2025 (Spotlight). chengpengli1003/cort.
SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data
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
