Haodong Zhao's picture

Haodong Zhao

billhdzhao

·

https://dongdongzhaoup.github.io/

AI & ML interests

Federated Learning, LLM, Agent, Security

Recent Activity

upvoted a paper 9 days ago

EmbTracker: Traceable Black-box Watermarking for Federated Language Models

submitted a paper 9 days ago

EmbTracker: Traceable Black-box Watermarking for Federated Language Models

upvoted a paper 19 days ago

ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data

View all activity

Organizations

upvoted a paper 9 days ago

EmbTracker: Traceable Black-box Watermarking for Federated Language Models

Paper • 2603.12089 • Published 9 days ago • 2

upvoted a paper 19 days ago

ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data

Paper • 2603.00516 • Published 22 days ago • 1

upvoted a paper about 1 month ago

Revisiting Backdoor Threat in Federated Instruction Tuning from a Signal Aggregation Perspective

Paper • 2602.15671 • Published Feb 17 • 1

upvoted a paper 3 months ago

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models

Paper • 2512.06899 • Published Dec 7, 2025 • 3

upvoted 2 papers 4 months ago

PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

Paper • 2512.02589 • Published Dec 2, 2025 • 73

Latent Collaboration in Multi-Agent Systems

Paper • 2511.20639 • Published Nov 25, 2025 • 126

upvoted a paper 6 months ago

Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning

Paper • 2509.18163 • Published Sep 17, 2025 • 1

upvoted a paper 11 months ago

OTC: Optimal Tool Calls via Reinforcement Learning

Paper • 2504.14870 • Published Apr 21, 2025 • 35