Zhengbao He

5 papers · 2024–2025 · 4 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 (14)

Venues

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

Top co-authors

Xiaolin Huang (5) Tao Li (3) Xinwen Cheng (3) Zhehao Huang (2) Ruikai Yang (1) Hanling Tian (1) Yuhang Liu (1) Yasheng Wang (1) Lifeng Shang (1) Pan Zhou (1)

Research topics

Machine Learning (5) Artificial Intelligence (3) Deep Learning (3) Application Areas (3) Core AI (3) Optimization & Theory · Machine Learning (3) Techniques (2) Security & Privacy (1) Architectures (1) Core Methods (1) Learning Types (1) Optimization & Theory · Deep Learning (1) Privacy (1)

Keywords

privacy preservation (1) machine unlearning (1) sharpness-aware minimization (1) model forgetting (1) neural network optimization (1) gradient descent (1) gradient-based method (1) hessian approximation (1) parameter recovery (1) generalization (1) diffusion model (1) deep neural network (1) adversarial perturbation (1) neural collapse (1) low-rank adaptation (1) out-of-distribution detection (1) training dynamics (1) parameter update (1) selective forgetting (1) flat loss landscape (1)

Papers

Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape ICML 2025 Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection ICLR 2025 Simulating Training Dynamics to Reconstruct Training Data from Deep Neural Networks ICLR 2025 Friendly Sharpness-Aware Minimization CVPR 2024 Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement NeurIPS 2024