Scholar
Tao Zhong
Google Scholar ID: 0zKusWIAAAAJ
Princeton University
Citations & Impact
Citations
126
H-index
4
i10-index
3
Publications
8
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- “Local-Canonicalization Equivariant Graph Neural Networks for Sample-Efficient and Generalizable Swarm Robot Control” (*equal contribution), Preprint 2025: Introduced LEGO, a symmetry-aware GNN framework for scalable swarm control.
- “Grasp2Grasp: Vision-Based Dexterous Grasp Translation via Schrödinger Bridges”, NeurIPS 2025: Enables simulation-free, vision-based grasp transfer across robot hands using physics-informed Schrödinger Bridges.
- “GAGrasp: Geometric Algebra Diffusion for Dexterous Grasping”, ICRA 2025: Uses geometric algebra diffusion to generate pose-equivariant, physically plausible dexterous grasps.
- “Adapting to Distribution Shift by Visual Domain Prompt Generation”, ICLR 2024: Proposed VDPG for test-time domain adaptation using few unlabeled images to generate domain-specific prompts.
- “Fast-Grasp'D: Dexterous Multi-finger Grasp Generation Through Differentiable Simulation”, ICRA 2023: Developed a differentiable simulator to rapidly generate Grasp'D-1M, a large dataset of stable multi-finger grasps.
- “Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts” (*equal contribution), NeurIPS 2022: Proposed a meta-distillation framework from MoE for fast test-time adaptation.
Co-authors