Xinwen Cheng

4 papers · 2023–2025 · 3 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 · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11)

Venues

ICLR (2) CVPR (1) NeurIPS (1)

Top co-authors

Xiaolin Huang (4) Zhengbao He (3) Tao Li (2) Yanzhi Wang (1) Haoran Wang (1) Zhehao Huang (1) Yingwen Wu (1) Geng Yuan (1) Sizhe Chen (1) Minghai Qin (1)

Research topics

Machine Learning (4) Deep Learning (3) Techniques (3) Artificial Intelligence (2) Application Areas (2) Core AI (2) Learning Types (2) Optimization & Theory · Machine Learning (2) Security & Privacy (1) Core Methods (1) Optimization & Theory · Deep Learning (1) Privacy (1)

Keywords

deep neural network (2) adversarial perturbation (2) machine unlearning (1) sharpness-aware minimization (1) model forgetting (1) gradient descent (1) gradient-based method (1) data perturbation (1) hessian approximation (1) diffusion model (1) ensemble method (1) neural collapse (1) out-of-distribution detection (1) parameter update (1) selective forgetting (1) exponential moving average (1) feature separation (1) neural network (1) class forgetting (1) stochastic gradient noise (1)

Papers

Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection ICLR 2025 Friendly Sharpness-Aware Minimization CVPR 2024 Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement NeurIPS 2024 Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors ICLR 2023