Kai Yao

8 papers · 2022–2026 · 5 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (10) 🧭 Keyword Pioneer 🌍 Conference Polyglot (4) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (19) 🌈 Renaissance Researcher (5) 🔥 Unstoppable (5)

Conferences

AAAI (3) ECCV (2) ACL (1) EACL (1) EMNLP (1)

Top co-authors

Penglei Gao (4) Zhaorui Tan (3) Jianke Zhu (3) Kaizhu Huang (3) Xi Yang (3) Wei Wang (3) Yuan Zhao (3) Lichun Li (3) Kaixin Wu (2) Jie Sun (2)

Keywords

large language model (2) parameter-efficient fine-tuning (2) rank compression (2) model compression (2) style transfer (1) knowledge distillation (1) data augmentation (1) batch normalization (1) test-time adaptation (1) privacy preservation (1) model adaptation (1) medical image segmentation (1) data selection (1) memory optimization (1) privacy protection (1) domain shift (1) sparse tuning (1) exponential moving average (1) medical image (1) gradient preservation (1)

Papers

GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection EACL 2026

ScaleOT: Privacy-utility-scalable Offsite-tuning with Dynamic LayerReplace and Selective Rank Compression AAAI 2025

GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models ACL 2025

Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models EMNLP 2024

Unraveling Batch Normalization for Realistic Test-Time Adaptation AAAI 2024

Unleashing the Power of Prompt-driven Nucleus Instance Segmentation ECCV 2024

Rethinking Data Augmentation for Single-Source Domain Generalization in Medical Image Segmentation AAAI 2023

Outpainting by Queries ECCV 2022