Hao Zhao

Hao Zhao

Creator
0 followers

Robotics researcher; shares work on robot world models and learning for embodied AI.

Train 1B 3D Gaussians on One 24GB GPU
SocialMay 20, 2026

Train 1B 3D Gaussians on One 24GB GPU

🚀 #ICML2026 TideGS trains over 1 BILLION 3D Gaussian primitives on a single 24GB GPU. No multi-GPU cluster. No 80GB H100 requirement. We rethink 3DGS training as a working-set caching problem instead of persistent VRAM residency. 💡 Key idea: Only visible Gaussians are active each iteration,...

By Hao Zhao
LLMs Still Falter at 3D Vision Scientific Coding
SocialMay 19, 2026

LLMs Still Falter at 3D Vision Scientific Coding

#CVPR2026 Can frontier LLMs write PhD-level 3D vision code? We introduce GeoCodeBench, a benchmark that asks models to read real 3D geometric vision papers and implement core functions. Best result so far: GPT-5 reaches only 36.6%. This suggests that scientific coding in 3D...

By Hao Zhao
Simulated HOI Data Replaces Human Data with PAM
SocialMar 24, 2026

Simulated HOI Data Replaces Human Data with PAM

[CVPR 2026] The embodied AI community is going all-in on human data: teleop, mocap, ego videos… We take a different path: 👉 Generate HOI data from simulation 👉 Bridge to realism with diffusion 👉 Use it to replace human data Introducing PAM — a unified...

By Hao Zhao
4D Occupancy Drives Photoreal
SocialMar 16, 2026

4D Occupancy Drives Photoreal

🚀 ORV: 4D Occupancy-centric Robot Video Generation (CVPR 2026) https://t.co/9ILR3w3XND What if we could generate photorealistic robot manipulation videos with precise 4D control? With ORV, we condition video generation on 4D semantic occupancy, enabling: ✨ High-fidelity robot videos with fine-grained motion control 🎥 Multi-view generation...

By Hao Zhao