Ninghao Liu
30 papers · 2017–2026 · 11 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🏃 Academic Marathon (8) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (10) 🐣 Hot Topic Early Bird
🌍
Conference Polyglot
(10)
🏃
Academic Marathon
(8)
🧭
Keyword Pioneer
🧬
Topic Evolution
🏆
Grand Slam
🗃️
Keyword Collector
(112)
💎
Century Club
(28)
🔥
Unstoppable
(6)
⚡
Prolific Year
(10)
Conferences
AAAI (7)
ICLR (5)
ICML (5)
ACL (2)
EMNLP (2)
IJCAI (2)
NAACL (2)
NIPS (2)
COLING (1)
CVPR (1)
EACL (1)
Top co-authors
Keywords
large language model
(6)
sparse autoencoder
(3)
backdoor attack
(2)
model steering
(2)
attention mechanism
(2)
neural network interpretability
(2)
outlier detection
(2)
foundation model
(2)
deep neural network
(2)
graph neural network
(2)
anomaly detection
(1)
information bottleneck
(1)
graph classification
(1)
medical imaging
(1)
natural language processing
(1)
few-shot learning
(1)
compressed sensing
(1)
neural coding
(1)
prompt engineering
(1)
sparse coding
(1)
Papers
AutoSCORE: Enhancing Automated Scoring with Multi-Agent Large Language Models via Structured Component Recognition
AAAI 2026
Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
EACL 2026
Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
EMNLP 2025
A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
EMNLP 2025
Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data
ICLR 2025
Mutual Effort for Efficiency: A Similarity-based Token Pruning for Vision Transformers in Self-Supervised Learning
ICLR 2025
MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations
ICLR 2025
Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages
AAAI 2025
LMOD: A Large Multimodal Ophthalmology Dataset and Benchmark for Large Vision-Language Models
NAACL 2025
Concept-Centric Token Interpretation for Vector-Quantized Generative Models
ICML 2025
Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models
ICLR 2024
BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks (Student Abstract)
AAAI 2024
Automated Natural Language Explanation of Deep Visual Neurons with Large Models (Student Abstract)
AAAI 2024
PokeMQA: Programmable knowledge editing for Multi-hop Question Answering
ACL 2024
Enhancing Explainable Rating Prediction through Annotated Macro Concepts
ACL 2024
Mitigating Shortcuts in Language Models with Soft Label Encoding
COLING 2024
Molecular Data Programming: Towards Molecule Pseudo-labeling with Systematic Weak Supervision
CVPR 2024
Improving Interpretation Faithfulness for Vision Transformers
ICML 2024
Rethinking Independent Cross-Entropy Loss For Graph-Structured Data
ICML 2024
From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
NAACL 2024
Black-box Backdoor Defense via Zero-shot Image Purification
NIPS 2023
Interpreting Unfairness in Graph Neural Networks via Training Node Attribution
AAAI 2023
DIVISION: Memory Efficient Training via Dual Activation Precision
ICML 2023
SEAT: Stable and Explainable Attention
AAAI 2023
G-Mixup: Graph Data Augmentation for Graph Classification
ICML 2022
DEGREE: Decomposition Based Explanation for Graph Neural Networks
ICLR 2022
Dynamic Memory based Attention Network for Sequential Recommendation
AAAI 2021
Learning sparse codes from compressed representations with biologically plausible local wiring constraints
NIPS 2020
Contextual Outlier Interpretation
IJCAI 2018
Accelerated Local Anomaly Detection via Resolving Attributed Networks
IJCAI 2017