-
Australian Institute for Machine Learning (AIML)
- zheyuanliu.me
- @DavidZheyuan
Stars
Mac OS Safari theme for Firefox on Linux
Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation [Siggraph Asian 2025]
The official implementation of CVPR'25 Oral paper "Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise"
Supercharge Your LLM Application Evaluations 🚀
[NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
DeepVerse: 4D Autoregressive Video Generation as a World Model
🔥🔥🔥 [IEEE TCSVT] Latest Papers, Codes and Datasets on Vid-LLMs.
[ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAI
[ICLR 2025] Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion
A collection of papers on diffusion models for 3D generation.
This repo is meant to serve as a guide for Machine Learning/AI technical interviews.
Implements the scaled dot product attention mechamism from the transformer. Vaswani, A. et al. https://arxiv.org/pdf/1706.03762.pdf
[CVPR24] DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data
[SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing
Extract Cryptomatte data from EXR image files
Simple viewer for OpenEXR files with detailed metadata display
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
[CVPR 2025] Official code of "DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation"
Video-P2P: Video Editing with Cross-attention Control
SkyReels-V2: Infinite-length Film Generative model
[ICCV 2023] - Composed Image Retrieval on Common Objects in context (CIRCO) dataset
New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos
A pure Unix shell script ACME client for SSL / TLS certificate automation
H.264 sequence param parser (sps) written in pure C with no dependencies