A Systematic Framework for Interactive World Modeling
AlphaFold 3 inference pipeline
Open-Source Financial Large Language Models
Stable Diffusion with Core ML on Apple Silicon
Mixture-of-Experts Vision-Language Models for Advanced Multimodal
Qwen3-Coder is the code version of Qwen3
Generate Any 3D Scene in Seconds
Qwen2.5-VL is the multimodal large language model series
ChatGLM-6B: An Open Bilingual Dialogue Language Model
OpenTinker is an RL-as-a-Service infrastructure for foundation models
Ultra-Efficient LLMs on End Device
Easy Docker setup for Stable Diffusion with user-friendly UI
A Customizable Image-to-Video Model based on HunyuanVideo
ChatGPT interface with better UI
A Powerful Native Multimodal Model for Image Generation
Generating Immersive, Explorable, and Interactive 3D Worlds
FAIR Sequence Modeling Toolkit 2
RGBD video generation model conditioned on camera input
Advancing Open-source World Models
Qwen-Image-Layered: Layered Decomposition for Inherent Editablity
Industrial-level controllable zero-shot text-to-speech system
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training
Achieving 3+ generation speedup on reasoning tasks
Uncommon Objects in 3D dataset
Video Object and Interaction Deletion