gulucaptain Claim this profile

[ACM MM'26] 🎬 Tell the camera where to go: CT-1 understands your intent and generates videos with precise, spatially-aware camera control.

[ICML'26] CameraNoise helps control the faithful camera movement 🎞️ in the video diffusion.

[TMM'26] Dynamic human image animation with strong identity preservation, heterogeneous character driving, and controllable backgrounds.

Latex template for ACM conference/Journal rebuttal.

[ECCV'24] Official project of paper "MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing"

Easily do VQ-GAN inference and training on your custom data.

A curated list of awesome works on World Action Models for researchers, practitioners, and enthusiasts interested in action-centric world modeling.

Save code scripts.

🔧 Tools for analyzing, processing, and visualizing the 10K-hour RealOmni-Open dataset [https://www.genrobot.ai/data/open-dataset].

About This repository is a curated collection of the most exciting and influential ICML 2026 papers. 🔥 [Paper + Code + Demo]

Camera trajectories visualization with dynamic results in 3D mesh.

Easily do video segmentation on your custom data

Homepage of Haoyu Zhao.

Personal reporter for my projects and reports.

[IJCV'26] UniCam is the first unified diffusion model that supports camera-controllable T2V, I2V, and V2V generation tasks.

3D Web game within three.js. In this game, you can move around the map, invite your friends join in, and communicate with them.