34 60 94

Ningyu Zhang

Ningyu

https://person.zju.edu.cn/en/ningyu

zxlzr

AI & ML interests

NLP, Knowledge Editing

Recent Activity

upvoted a paper 2 days ago

ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging

commented on a paper 2 days ago

ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging

authored a paper 3 days ago

ADS-Edit: A Multimodal Knowledge Editing Dataset for Autonomous Driving Systems

View all activity

Organizations

Ningyu's activity

upvoted a paper 2 days ago

ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging

Paper • 2503.21088 • Published 3 days ago • 6

commented a paper 2 days ago

ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging

Paper • 2503.21088 • Published 3 days ago • 6 •

authored a paper 3 days ago

ADS-Edit: A Multimodal Knowledge Editing Dataset for Autonomous Driving Systems

Paper • 2503.20756 • Published 4 days ago • 6

upvoted a paper 3 days ago

ADS-Edit: A Multimodal Knowledge Editing Dataset for Autonomous Driving Systems

Paper • 2503.20756 • Published 4 days ago • 6

commented a paper 3 days ago

ADS-Edit: A Multimodal Knowledge Editing Dataset for Autonomous Driving Systems

Paper • 2503.20756 • Published 4 days ago • 6 •

upvoted a paper 4 days ago

LookAhead Tuning: Safer Language Models via Partial Answer Previews

Paper • 2503.19041 • Published 6 days ago • 5

commented a paper 4 days ago

LookAhead Tuning: Safer Language Models via Partial Answer Previews

Paper • 2503.19041 • Published 6 days ago • 5 •

authored a paper 9 days ago

CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners

Paper • 2503.16356 • Published 10 days ago • 15

upvoted a paper 9 days ago

CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners

Paper • 2503.16356 • Published 10 days ago • 15

commented a paper 9 days ago

CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners

Paper • 2503.16356 • Published 10 days ago • 15 •

upvoted a paper 18 days ago

BiasEdit: Debiasing Stereotyped Language Models via Model Editing

Paper • 2503.08588 • Published 19 days ago • 6

New activity in zjunlp/OceanGPT-7b-v0.1 23 days ago

Adding `safetensors` variant of this model

#1 opened 23 days ago by

SFconvertbot

commented a paper about 1 month ago

LightThinker: Thinking Step-by-Step Compression

Paper • 2502.15589 • Published Feb 21 • 27 •

upvoted a paper about 1 month ago

LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers

Paper • 2502.15007 • Published Feb 20 • 169

authored a paper about 1 month ago

LightThinker: Thinking Step-by-Step Compression

Paper • 2502.15589 • Published Feb 21 • 27

upvoted a paper about 1 month ago

LightThinker: Thinking Step-by-Step Compression

Paper • 2502.15589 • Published Feb 21 • 27

commented 3 papers about 1 month ago

LightThinker: Thinking Step-by-Step Compression

Paper • 2502.15589 • Published Feb 21 • 27 •

How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training

Paper • 2502.11196 • Published Feb 16 • 22 •

How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training

Paper • 2502.11196 • Published Feb 16 • 22 •