← Search

Ang He

2 accepted papers

2026

On the Computational Limits of AI4S-RL : A Unified $\varepsilon$-$N$ Analysis

ICLR 2026poster

Recent work increasingly adopts AI for Science (AI4S) models to replace expensive PDE solvers as simulation environments for reinforcement learning (RL), enabling faster training in complex physical control tasks. However, using approximate simulators introduces modeling errors that affect the learn…

Cited by 0SourceScholar
2025

SinGS: Animatable Single-Image Human Gaussian Splats with Kinematic Priors

CVPR 2025poster

Despite significant advances in accurately estimating geometry in contemporary single-image 3D human reconstruction, creating a high-quality, efficient, and animatable 3D avatar remains an open challenge. Two key obstacles persist: incomplete observation and inconsistent 3D priors. To address these…