-
Tsinghua University
- Tsinghua University
-
12:43
(UTC +08:00) - https://knightnemo.github.io
- https://knightnemo.github.io/blog
Lists (4)
Sort Name ascending (A-Z)
Stars
Official repo for vidar and vidarc: video foundation model for robotics.
[ArXiv 2025] A survey about controllable video generation: This repo is the official awesome of "Controllable video generation: A survey"
WorldPlay: Interactive World Modeling with Real-Time Latency and Geometric Consistency
Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model
This is a repo to track the latest autoregressive visual generation papers.
Author's PyTorch implementation of TD3 for OpenAI gym tasks
Code implementation of the paper "World-in-World: World Models in a Closed-Loop World"
A real-time streaming conversational video system that transforms text interactions into continuous, high-fidelity video responses using autoregressive diffusion.
An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone
Towards Unified Latent VLA for Whole-body Loco-manipulation Control
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models
A framework for Reinforcement Learning research.
Collection of reinforcement learning algorithms
PyTorch Implementation of Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
Pretraining and inference code for a large-scale depth-recurrent language model
PyTorch implementation of soft actor critic
Code for "Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation"
[AAAI 2026] VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
Light-X: Generative 4D Video Rendering with Camera and Illumination Control
Accelerate VGGT with efficient desciptor-based global attention
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels