today local_bar

Lijia Yu

Postdoc, Institute of Software, Chinese Academy of Sciences

3 papers at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Provable Watermarking for Data Poisoning Attacks

#3101 · Yifan Zhu, Lijia Yu, Xiao-Shan Gao

We introduce provable and practical watermarking approaches for data poisoning attacks.

Poster Session 3

Thursday, December 4, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Analyzing the Power of Chain of Thought through Memorization Capabilities

#4019 · Lijia Yu, Xiao-Shan Gao, Lijun Zhang

Use the memorization theorem to analyze the power of chain of thought.

Poster Session 4

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG

#3915 · Xiaonan si, Meilin Zhu, Simeng Qin, Lijia Yu, Lijun Zhang, Shuaitong Liu, Xinfeng Li, Ranjie Duan, Yang Liu, Xiaojun Jia

A defense method against RAG corpus attacks that combines semantic of document.