-
The University of Hong Kong
- Hong Kong
- https://tianshuoy.github.io/
Lists (9)
Sort Name ascending (A-Z)
Starred repositories
CLAW🦀 is a web pipeline for scalable language-annotated whole-body motion generation on Unitree G1.
Unlock your displays on your Mac! Flexible HiDPI scaling, XDR/HDR extra brightness, virtual screens, DDC control, extra dimming, PIP/streaming, EDID override and lots more!
[Arxiv 2026] WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory
Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory
Open data and scalable training for long-horizon video world models.
GPT-6 Astra for embodied AI and robotics.
Programmable World Model: explicit world state, generative rendering.
Generative World Renderer: an AI-native Renderer for Games and Virtual Worlds.
Foundation models for 4D spatial and temporal vision tasks.
Official repository for "OpenWAM: An Open, Modular Exploration Towards Systematic World–Action Model Pretraining".
[ICML'26] PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
SCoPE: Sightline-Coordinate Positional Encoding for 3D-Aware Video Generation
DeepSeek Harness: Everything is a Plugin.
[SIGGRAPH Asia 2026] 4DAnyone: Create Anyone in 4D from a Casual Monocular Video
LiteReality-Agent: Turn the real world into simulation-ready environments.
Infinite Worlds with Versatile Interactions
[ECCV2026] Official open-source repository for REAL——Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation
RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination
Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?
StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
Official implementation of Continuous 3D Perception Model with Persistent State
Academic Research Skills for Claude Code: research → write → review → revise → finalize
(CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++
Official implementation for WorldScore: A Unified Evaluation Benchmark for World Generation
