PPaperPicks

Mengxuan Hu

14 papers at tracked venues · 11 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

AAAI ×3ICML ×2ACL ×1CIKM ×1CVPR ×1EMNLP ×1ICLR ×1IJCAI ×1NeurIPS ×1SIGIR ×1SIGKDD ×1

Frequent coauthors

Zihan Guan
DBLP profile ↗ORCID search ↗
×3
Dongliang Guo
DBLP profile ↗ORCID search ↗
×2
Hanzhang Yuan
DBLP profile ↗ORCID search ↗
×1
Daiqing Qi
DBLP profile ↗ORCID search ↗
×1
Guangya Wan
DBLP profile ↗ORCID search ↗
×1
Ronghang Zhu
DBLP profile ↗ORCID search ↗
×1
Yaochen Zhu
DBLP profile ↗ORCID search ↗
×1
Zhongliang Zhou
DBLP profile ↗ORCID search ↗
×1
Zhixuan Chu
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Reducing Token Redundancy in LVLMs: A Systematic Review of Token Pruning Methods
    ACL 2026 ·
    Hanzhang Yuan
    DBLP profile ↗ORCID search ↗
  2. Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing
    CIKM 2025 ·
    Dongliang Guo
    DBLP profile ↗ORCID search ↗
  3. BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing
    ICML 2025 ·
    Dongliang Guo
    DBLP profile ↗ORCID search ↗
  4. Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety
    ICML 2025 ·
    Zihan Guan
    DBLP profile ↗ORCID search ↗
  5. Improve Temporal Reasoning in Multimodal Large Language Models via Video Contrastive Decoding
    NeurIPS 2025 ·
    Daiqing Qi
    DBLP profile ↗ORCID search ↗
  6. Large Language Models for Causal Discovery: Current Landscape and Future Directions
    IJCAI 2025 ·
    Guangya Wan
    DBLP profile ↗ORCID search ↗
  7. Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data
    ICLR 2025 · Mengxuan Hu
  8. No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users
    EMNLP 2025 · Mengxuan Hu
  9. Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety
    CVPR 2025 ·
    Ronghang Zhu
    DBLP profile ↗ORCID search ↗
  10. UFID: A Unified Framework for Black-box Input-level Backdoor Detection on Diffusion Models
    AAAI 2025 ·
    Zihan Guan
    DBLP profile ↗ORCID search ↗
  11. BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks (Student Abstract)
    AAAI 2024 ·
    Zihan Guan
    DBLP profile ↗ORCID search ↗
  12. Causal Inference with Latent Variables: Recent Advances and Future Prospectives
    SIGKDD 2024 ·
    Yaochen Zhu
    DBLP profile ↗ORCID search ↗
  13. Img2Loc: Revisiting Image Geolocalization using Multi-modality Foundation Models and Image-based Retrieval-Augmented Generation
    SIGIR 2024 ·
    Zhongliang Zhou
    DBLP profile ↗ORCID search ↗
  14. Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction
    AAAI 2024 ·
    Zhixuan Chu
    DBLP profile ↗ORCID search ↗