Jinghan Jia
18 papers · 2022–2026 · 9 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π£ Hot Topic Early Bird πΊοΈ Taxonomy Completionist (42) π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π€ Dynamic Duo (16)
π
Trend Setter
ποΈ
Keyword Collector
(92)
π
Renaissance Researcher
(5)
π₯
Unstoppable Β· Bronze
β
The Questioner
(3)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
Top co-authors
Research topics
Machine Learning
(16)
Artificial Intelligence
(14)
Core AI
(13)
Deep Learning
(7)
Learning Types Β· Machine Learning
(7)
Optimization & Theory Β· Machine Learning
(7)
Application Areas
(6)
Natural Language Processing
(3)
Learning Types Β· Deep Learning
(3)
Models
(3)
Resources & Methods
(3)
Computer Vision
(2)
Core Methods
(2)
Learning Paradigms
(2)
Optimization & Theory Β· Deep Learning
(2)
Keywords
machine unlearning
(8)
large language model
(5)
model utility
(3)
adversarial robustness
(3)
adversarial training
(2)
diffusion model
(2)
zeroth-order optimization
(2)
text-to-image generation
(2)
model editing
(2)
knowledge editing
(2)
gradient-based optimization
(1)
cross-modal learning
(1)
video understanding
(1)
model unlearning
(1)
natural language processing
(1)
few-shot learning
(1)
preference optimization
(1)
chain-of-thought reasoning
(1)
robustness
(1)
sharpness-aware minimization
(1)
Papers
BLUR: A Bi-Level Optimization Approach for LLM Unlearning
EACL 2026
Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
ICML 2025
Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
EMNLP 2025
Robust Multi-bit Text Watermark with LLM-based Paraphrasers
ICML 2025
SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?
ACL 2025
Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
ICML 2025
DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training
ICLR 2024
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
NeurIPS 2024
Leveraging LLMs for Dialogue Quality Measurement
NAACL 2024
SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning
EMNLP 2024
To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now
ECCV 2024
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
NeurIPS 2024
WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
NeurIPS 2024
Model Sparsity Can Simplify Machine Unlearning
NeurIPS 2023
Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning
NeurIPS 2023
TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization
ICLR 2023
Text-Visual Prompting for Efficient 2D Temporal Video Grounding
CVPR 2023
How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective
ICLR 2022