Yuanzhi Li

Computer Vision and Pattern Recognition · with Chen · 2022

A researcher in the Science corpus: 1 paper; trusts 4 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 13 citations into it
• Generative Models — 12 citations into it
• Probabilistic & Bayesian Methods — 7 citations into it

Whom Yuanzhi Li trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Aapo Hyvärinen
2. Cédric Villani

Papers from Yuanzhi Li's perspective

Ordered by how strongly the researchers Yuanzhi Li trusts endorse each paper. Same corpus, a different order for every researcher.

1. Estimation of Non-Normalized Statistical Models by Score Matching
2. Generative Modeling by Estimating Gradients of the Data Distribution
3. Diffusion Models Beat GANs on Image Synthesis
4. Score-based Generative Modeling in Latent Space
5. Score-Based Generative Modeling with Critically-Damped Langevin Diffusion
6. Hypocoercivity
7. Statistical Query Lower Bounds for Robust Estimation of High-Dimensional Gaussians and Gaussian Mixtures
8. Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Suffices (Neural Information Processing Systems)
9. Brownian Motion, Martingales, and Stochastic Calculus
10. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)

Their papers

• Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions (2022) — 467 citations