AI.info

Zihao Wang

Explore Zihao Wang on AI.info.

• $\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ Retrieval
• Adaptive Domain Shift in Diffusion Models for Cross-Modality Image Translation
• Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning
• Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit