Zhehao Huang

5 papers · 2022–2026 · 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 (15) 🔥 Unstoppable · Bronze

Venues

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

Top co-authors

Xiaolin Huang (5) Tao Li (3) Yuhang Liu (2) Qinghua Tao (2) Zhengbao He (2) Yingwen Wu (2) Ning Lu (1) Baijiong Lin (1) Jingying Wang (1) Jingyuan Zhang (1)

Research topics

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

Keywords

stochastic gradient descent (1) benchmark evaluation (1) model robustness (1) privacy preservation (1) machine unlearning (1) model forgetting (1) neural network optimization (1) gradient descent (1) gradient-based method (1) hessian approximation (1) distributed training (1) training efficiency (1) parameter recovery (1) adversarial attack (1) diffusion model (1) adversarial defense (1) training dynamics (1) vision-language model (1) weight averaging (1) parameter update (1)

Papers

VL-RouterBench: A Benchmark for Vision-Language Model Routing CVPR 2026 Simulating Training Dynamics to Reconstruct Training Data from Deep Neural Networks ICLR 2025 Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement NeurIPS 2024 Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions ICLR 2023 Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks NeurIPS 2022