📖 This is a repository for organizing papers, codes and other resources related to unified multimodal models.

Ongoing research training transformer models at scale

Awesome curated collection of images and prompts generated by gemini-2.5-flash-image (aka Nano Banana) state-of-the-art image generation and editing model. Explore AI generated visuals created with…

SGLang is a fast serving framework for large language models and vision language models.

We introduce Reasoning via Video, a new paradigm that uses maze-solving video generation to probe multimodal reasoning; our VR-Bench shows that fine-tuned video models consistently outperform stron…

This is a collection of recent papers on reasoning in video generation models.

slime is an LLM post-training framework for RL Scaling.

📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

Enjoy the magic of Diffusion models!

Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give it a star 🌟 if you find it useful.

We introduce 'Thinking with Video', a new paradigm leveraging video generation for multimodal reasoning. Our VideoThinkBench shows that Sora-2 surpasses GPT5 by 10% on eyeballing puzzles and reache…

Contexts Optical Compression

LLM/VLM gaming agents and model evaluation through games.

GitHub Copilot CLI brings the power of Copilot coding agent directly to your terminal.

[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat

A sleek dataset viewer built entirely by AI Agent. Supports streaming large files from WebDAV, S3, SSH, Local or Hugging Face.

A Survey of Reinforcement Learning for Large Reasoning Models

The absolute trainer to light up AI agents.

EvaLearn is a pioneering benchmark designed to evaluate large language models (LLMs) on their learning capability and efficiency in challenging tasks.

A curated list of awesome resources about reward construction for AI agents. This repository covers cutting-edge research, and practical guides on defining and collecting rewards to build more inte…

Generate large-scale explorable 3D scenes with high-quality panorama videos from a single image or text prompt.

We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a re…

Tongyi Deep Research, the Leading Open-source Deep Research Agent

verl: Volcano Engine Reinforcement Learning for LLMs

Train transformer language models with reinforcement learning.