Lijie Hu
28 papers · 2022–2026 · 13 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 ↓+10 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Gold π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (60) π€ Dynamic Duo (25)
π€
Dynamic Duo
(25)
π
Keyword Champion
(2)
π
Triple Crown
π
Grand Slam
β‘
Prolific Year Β· Prolific
π₯
Unstoppable Β· Bronze
β
The Questioner
π
Century Club Β· Bronze
π
Renaissance Researcher
(6)
ποΈ
Keyword Collector
(126)
Venues
Top co-authors
Research topics
Artificial Intelligence
(23)
Core AI
(23)
Machine Learning
(21)
Application Areas
(12)
Deep Learning
(10)
Natural Language Processing
(8)
Optimization & Theory
(8)
Learning Types Β· Deep Learning
(6)
Learning Types Β· Machine Learning
(6)
Applications
(5)
Core Methods
(5)
Security & Privacy
(4)
Differential Privacy
(4)
Resources & Methods
(3)
Mathematics & Optimization
(2)
Keywords
large language model
(8)
differential privacy
(5)
mechanistic interpretability
(4)
knowledge editing
(3)
concept bottleneck model
(3)
vision-language model
(3)
natural language processing
(2)
tysbakov noise condition
(2)
concept alignment
(2)
benchmark evaluation
(2)
model stability
(2)
multimodal large language model
(2)
multimodal learning
(2)
stochastic convex optimization
(2)
excess population risk
(2)
machine unlearning
(2)
statistical learning theory
(1)
vision transformer
(1)
sentiment analysis
(1)
principal component analysis
(1)
Papers
Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs
ACL 2026
Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models
CVPR 2026
Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images
ACL 2026
Backdooring Vision-Language Models with Out-Of-Distribution Data
ICLR 2025
Can Large Language Models Identify Implicit Suicidal Ideation? An Empirical Evaluation
EMNLP 2025
CODEMENV: Benchmarking Large Language Models on Code Migration
ACL 2025
COMPKE: Complex Question Answering under Knowledge Editing
ACL 2025
Editable Concept Bottleneck Models
ICML 2025
Fair Text-to-Image Diffusion via Fair Mapping
AAAI 2025
Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements
ACL 2025
Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
ICML 2025
Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning
NAACL 2025
Semi-supervised Concept Bottleneck Models
ICCV 2025
Tuning-Free Accountable Intervention for LLM Deployment β a Metacognitive Approach
AAAI 2025
Understanding How Value Neurons Shape the Generation of Specified Values in LLMs
EMNLP 2025
Understanding the Repeat Curse in Large Language Models from a Feature Perspective
ACL 2025
Differentially Private Natural Language Models: Recent Advances and Future Directions
EACL 2024
Dissecting Fine-Tuning Unlearning in Large Language Models
EMNLP 2024
Faithful Vision-Language Interpretation via Concept Bottleneck Models
ICLR 2024
Faster Rates of Differentially Private Stochastic Convex Optimization
JMLR 2024
Improving Interpretation Faithfulness for Vision Transformers
ICML 2024
Private Language Models via Truncated Laplacian Mechanism
EMNLP 2024
Towards Multi-dimensional Explanation Alignment for Medical Classification
NeurIPS 2024
UniMEEC: Towards Unified Multimodal Emotion Recognition and Emotion Cause
EMNLP 2024
Generalized Linear Models in Non-interactive Local Differential Privacy with Public Data
JMLR 2023
Privacy-preserving Sparse Generalized Eigenvalue Problem
AISTATS 2023
SEAT: Stable and Explainable Attention
AAAI 2023
Faster Rates of Private Stochastic Convex Optimization
ALT 2022