Picture for Zheng Lin

Zheng Lin

Unsourced Adversarial CAPTCHA: A Bi-Phase Adversarial CAPTCHA Framework

Add code
Jun 12, 2025
Viaarxiv icon

DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts

Add code
Jun 11, 2025
Viaarxiv icon

HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systems

Add code
Jun 10, 2025
Viaarxiv icon

TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning

Add code
Jun 10, 2025
Viaarxiv icon

Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models

Add code
Jun 07, 2025
Viaarxiv icon

Unveiling and Eliminating the Shortcut Learning for Locate-Then-Edit Knowledge Editing via Both Subject and Relation Awareness

Add code
Jun 04, 2025
Viaarxiv icon

Advantageous Parameter Expansion Training Makes Better Large Language Models

Add code
May 30, 2025
Viaarxiv icon

TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization

Add code
May 26, 2025
Viaarxiv icon

PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization

Add code
May 15, 2025
Viaarxiv icon

DP-TRAE: A Dual-Phase Merging Transferable Reversible Adversarial Example for Image Privacy Protection

Add code
May 11, 2025
Viaarxiv icon