Lattice AI Research

Research focus

Code Generation & Program Synthesis (1)Data Curation & Synthetic Data (1)Natural Language Processing (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Yongyi Cui (1)Tian-Jian Jiang (1)Tianbao Jiang (1)Xin Yi (1)

Papers (2)

Jul 28, 2026

Yongyi Cui +53w ago·also ECNU, Normal University

Construction-Driven Injection: Linguistically-Grounded Edit-Based Code-Mixing Fingerprints for Large Language Models

Code-mixing fingerprints can achieve robust ownership verification in LLMs without sacrificing performance, avoiding accidental activations that plague traditional methods.

Yongyi Cui, Yongyi Cui, Tian-Jian Jiang +3

Code Generation & Program Synthesis Data Curation & Synthetic Data Natural Language Processing+2

Jul 22, 2026

Yanyu Chen +4Jul 22, 2026

Reinforcement Learning for Large Language Model Selective Evidence Adoption from Contaminated Retrieval Results

SelectBench reveals that while selective evidence adoption in LLMs can be improved, the gains are modest and highlight significant challenges that remain in ensuring robust performance.

Yanyu Chen, Yue Li, Yongyi Cui +2

Eval Frameworks & Benchmarks Recommendation & Information Retrieval RLHF & Preference Learning

Search

Yongyi Cui

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)