Scholar
Johnny Tian-Zheng Wei
Google Scholar ID: TVFpiukAAAAJ
University of Southern California
Natural language processing
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
876
H-index
9
i10-index
9
Publications
18
Co-authors
0
Publications
6 items
Spiking the training data to correct for test set contamination
2026
Cited
0
SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion
2026
Cited
0
Hubble: a Model Suite to Advance the Study of LLM Memorization
2025
Cited
0
TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability
2025
Cited
0
Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge
2025
Cited
0
Interrogating LLM design under a fair learning doctrine
2025
Cited
0
