Kang Wei

5 papers · 2023–2026 · 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 (11)

Venues

CVPR (2) ECCV (1) ICML (1) IJCAI (1)

Top co-authors

Dacheng Tao (2) Yifan Shi (2) Zhijie Rao (2) Xueqian Wang (2) Li Shen (2) Jingcai Guo (2) Jingming Liang (1) Bo Yuan (1) Haozhao Wang (1) Chuan Ma (1)

Research topics

Artificial Intelligence (4) Learning Paradigms · Artificial Intelligence (4) Machine Learning (3) Application Areas (3) Optimization & Theory (2) Computer Vision (1) Analysis (1) Core AI (1) Learning Paradigms · Machine Learning (1) Learning Types (1)

Keywords

gradient perturbation (2) sharpness-aware minimization (2) zero-shot learning (2) knowledge distillation (2) parameter-efficient fine-tuning (1) low-rank adaptation (1) visual attribute (1) decentralized learning (1) dual expert (1) generalized zero-shot learning (1) model consistency (1) peer-to-peer communication (1) client-level privacy (1) differentially private federated learning (1) federated learning (1) weight perturbation robustness (1) non-convex optimization (1) attention mechanism (1) loss landscape (1)

Papers

SG-LoRA: Semantic-guided LoRA Parameters Generation CVPR 2026 Dual Expert Distillation Network for Generalized Zero-Shot Learning IJCAI 2024 "Refine, Discriminate and Align: Stealing Encoders via Sample-Wise Prototypes and Multi-Relational Extraction" ECCV 2024 Improving the Model Consistency of Decentralized Federated Learning ICML 2023 Make Landscape Flatter in Differentially Private Federated Learning CVPR 2023