MineWorld: A Real-time interactive world model on Minecraft

Let LLM join group chat with exclusively lines from certain works

[Fully open] [Encoder-free MLLM] Vision as LoRA

Scaling Vision Pre-Training to 4K Resolution

Sparse autoencoders for vision

s1: Simple test-time scaling

MoBA: Mixture of Block Attention for Long-Context LLMs

Animating R1's thoughts.

verl: Volcano Engine Reinforcement Learning for LLMs

Reproduce R1 Zero on Logic Puzzle

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

This repo contains the code for 1D tokenizer and generator

[CVPR 2025] 🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".

Integrate the DeepSeek API into popular softwares

This is a repo to track the latest autoregressive visual generation papers.

Large Concept Models: Language modeling in a sentence representation space

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

A curated list for awesome discrete diffusion models resources.

Visualizer for neural network, deep learning and machine learning models

PyTorch implementation of Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities.

[CVPR 2025 Highlight] Official implementation of "Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters"

Source code for Auctionformer

StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding

中国科学技术大学第十一届信息安全大赛的官方与非官方题解

A suite of image and video neural tokenizers