Kai Yao

Venues

Frequent coauthors

Papers

1. GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection
   EACL 2026 · Kai Yao
2. GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models
   ACL 2025 · Kai Yao
3. KDTalker++: Controllable Talking Portrait Generation with Audio, Text, and Expression Editing
   ACM MM 2025 ·

   Chaolong Yang

   DBLP profile ↗ORCID search ↗
4. ScaleOT: Privacy-utility-scalable Offsite-tuning with Dynamic LayerReplace and Selective Rank Compression
   AAAI 2025 · Kai Yao
5. Towards Instance-wise Personalized Federated Learning via Semi-Implicit Bayesian Prompt Tuning
   CIKM 2025 ·

   Tiandi Ye

   DBLP profile ↗ORCID search ↗
6. Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models
   EMNLP 2024 · Kai Yao
7. Maximum k-Plex Computation: Theory and Practice
   SIGMOD 2024 ·

   Lijun Chang

   DBLP profile ↗ORCID search ↗
8. Unleashing the Power of Prompt-Driven Nucleus Instance Segmentation
   ECCV 2024 ·

   Zhongyi Shui

   DBLP profile ↗ORCID search ↗
9. Unraveling Batch Normalization for Realistic Test-Time Adaptation
   AAAI 2024 ·

   Zixian Su

   DBLP profile ↗ORCID search ↗