PPaperPicks

Ninghao Liu

Hong Kong Polytechnic University, Hong Kong

24 papers at tracked venues · 17 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-9170-2424 ↗Homepage ↗

Venues

AAAI ×4ICLR ×4ICML ×3ACL ×2EMNLP ×2NAACL ×2CIKM ×1CVPR ×1EACL ×1NeurIPS ×1SIGKDD ×1WSDM ×1WWW ×1

Frequent coauthors

Xuansheng Wu
DBLP profile ↗ORCID search ↗
×3
Dong Shu
DBLP profile ↗ORCID search ↗
×2
Yucheng Shi
DBLP profile ↗ORCID search ↗
×2
Yun Wang
DBLP profile ↗ORCID search ↗
×1
Haiyan Zhao
DBLP profile ↗ORCID search ↗
×1
Tianze Yang
DBLP profile ↗ORCID search ↗
×1
Lin Zhang
DBLP profile ↗ORCID search ↗
×1
Zhenyue Qin
DBLP profile ↗ORCID search ↗
×1
Zihao Li
DBLP profile ↗ORCID search ↗
×1
Shaochen (Henry) Zhong
DBLP profile ↗ORCID search ↗
×1
Sheng Li
DBLP profile ↗ORCID search ↗
×1
Yi Fang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. AutoSCORE: Enhancing Automated Scoring with Multi-Agent Large Language Models via Structured Component Recognition
    AAAI 2026 ·
    Yun Wang
    DBLP profile ↗ORCID search ↗
  2. Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
    EACL 2026 ·
    Haiyan Zhao
    DBLP profile ↗ORCID search ↗
  3. A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
    EMNLP 2025 ·
    Dong Shu
    DBLP profile ↗ORCID search ↗
  4. Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
    EMNLP 2025 ·
    Dong Shu
    DBLP profile ↗ORCID search ↗
  5. Concept-Centric Token Interpretation for Vector-Quantized Generative Models
    ICML 2025 ·
    Tianze Yang
    DBLP profile ↗ORCID search ↗
  6. EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification
    NeurIPS 2025 ·
    Lin Zhang
    DBLP profile ↗ORCID search ↗
  7. Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data
    ICLR 2025 ·
    Yucheng Shi
    DBLP profile ↗ORCID search ↗
  8. LMOD: A Large Multimodal Ophthalmology Dataset and Benchmark for Large Vision-Language Models
    NAACL 2025 ·
    Zhenyue Qin
    DBLP profile ↗ORCID search ↗
  9. Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages
    AAAI 2025 ·
    Zihao Li
    DBLP profile ↗ORCID search ↗
  10. MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations
    ICLR 2025 ·
    Shaochen (Henry) Zhong
    DBLP profile ↗ORCID search ↗
  11. Mutual Effort for Efficiency: A Similarity-based Token Pruning for Vision Transformers in Self-Supervised Learning
    ICLR 2025 ·
    Sheng Li
    DBLP profile ↗ORCID search ↗
  12. Self-Regularization with Sparse Autoencoders for Controllable LLM-based Classification
    SIGKDD 2025 ·
    Xuansheng Wu
    DBLP profile ↗ORCID search ↗
  13. UniGLM: Training One Unified Language Model for Text-Attributed Graphs Embedding
    WSDM 2025 ·
    Yi Fang
    DBLP profile ↗ORCID search ↗
  14. Automated Natural Language Explanation of Deep Visual Neurons with Large Models (Student Abstract)
    AAAI 2024 ·
    Chenxu Zhao
    DBLP profile ↗ORCID search ↗
  15. BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks (Student Abstract)
    AAAI 2024 ·
    Zihan Guan
    DBLP profile ↗ORCID search ↗
  16. Could Small Language Models Serve as Recommenders? Towards Data-centric Cold-start Recommendation
    WWW 2024 ·
    Xuansheng Wu
    DBLP profile ↗ORCID search ↗
  17. Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models
    ICLR 2024 ·
    Yili Wang
    DBLP profile ↗ORCID search ↗
  18. Enhancing Explainable Rating Prediction through Annotated Macro Concepts
    ACL 2024 ·
    Huachi Zhou
    DBLP profile ↗ORCID search ↗
  19. From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
    NAACL 2024 ·
    Xuansheng Wu
    DBLP profile ↗ORCID search ↗
  20. Improving Interpretation Faithfulness for Vision Transformers
    ICML 2024 ·
    Lijie Hu
    DBLP profile ↗ORCID search ↗
  21. Molecular Data Programming: Towards Molecule Pseudo-labeling with Systematic Weak Supervision
    CVPR 2024 ·
    Xin Juan
    DBLP profile ↗ORCID search ↗
  22. PokeMQA: Programmable knowledge editing for Multi-hop Question Answering
    ACL 2024 ·
    Hengrui Gu
    DBLP profile ↗ORCID search ↗
  23. Rethinking Independent Cross-Entropy Loss For Graph-Structured Data
    ICML 2024 ·
    Rui Miao
    DBLP profile ↗ORCID search ↗
  24. Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering
    CIKM 2024 ·
    Yucheng Shi
    DBLP profile ↗ORCID search ↗