Puheng Li

5 papers · 2023–2026 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 📈 Trend Setter

Venues

AISTATS (1) CVPR (1) ICCV (1) ICLR (1) NeurIPS (1)

Top co-authors

Haotian Ye (2) Stefano Ermon (2) Jiaqi Han (2) James Zou (2) Keyao Zhan (1) Lei Wu (1) Minkai Xu (1) Huishuai Zhang (1) Zhong Li (1) Jiang Bian (1)

Research topics

Deep Learning (4) Machine Learning (4) Models (3) Optimization & Theory · Machine Learning (3) Artificial Intelligence (1) Computer Vision (1) Application Areas (1) Core AI (1) Core Methods (1) Generation (1) Learning Types (1) Optimization & Theory · Deep Learning (1)

Keywords

diffusion model (2) stochastic gradient descent (1) image generation (1) ridge regression (1) model merging (1) fair classification (1) early stopping (1) generative model (1) generalization bound (1) score-based diffusion model (1) group fairness (1) generalization gap (1) linear mode connectivity (1) inference acceleration (1) ode solver (1) permutation invariance (1) demographic parity (1) chebyshev polynomial (1) equalized odd (1) finite-sample guarantee (1)

Papers

Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration CVPR 2026 Analyzing the Role of Permutation Invariance in Linear Mode Connectivity AISTATS 2025 CHORDS: Diffusion Sampling Accelerator with Multi-core Hierarchical ODE Solvers ICCV 2025 FaiREE: fair classification with finite-sample and distribution-free guarantee ICLR 2023 On the Generalization Properties of Diffusion Models NeurIPS 2023