Selected Publications

This list highlights recent work on robust learning, imperfect supervision, evaluation, and AI safety. For the full record, see Dr. Feng's personal profile and ORCID.

Personal Website ORCID

2026

Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges

M. Shen, Chen Feng, A. Balashankar, C. Gerner-Beuerle, and M. Rodrigues

International Conference on Learning Representations (ICLR), 2026

Co-first author

OpenReview

Deconstructing the Failure of Ideal Noise Correction: A Three-Pillar Diagnosis

Chen Feng, Z. Zhi, Z. Huang, J. Ge, L. Xiao, N. Sebe, G. Tzimiropoulos, and I. Patras

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

First author

arXiv

Beyond Training for Cultural Awareness: The Role of Dataset Linguistic Structure in Large Language Models

R. I. Masoud, Chen Feng, S. Asano, S. Alshahrani, P. C. Treleaven, and M. R. D. Rodrigues

ICLR 2026 Workshop on Navigating and Addressing Data Problems for Foundation Models

OpenReview

2025

TFAR: A Training-Free Framework for Autonomous Reliable Reasoning in Visual Question Answering

Z. Zhi, Chen Feng, A. Daneshmend, M. Orlu, A. Demosthenous, L. Yin, D. Li, Z. Liu, and M. R. D. Rodrigues

Transactions on Machine Learning Research (TMLR), 2025

OpenReview

PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks

Chen Feng, Z. Liu, Z. Zhi, I. Bogunovic, C. Gerner-Beuerle, and M. Rodrigues

AAAI Conference on Artificial Intelligence (AAAI), 2025, Oral

First author

DOI

Unveiling Open-Set Noise: Theoretical Insights into Label Noise

Chen Feng, N. Sebe, G. Tzimiropoulos, M. R. D. Rodrigues, and I. Patras

ACM International Conference on Multimedia (ACM MM), 2025

First author

DOI

2024 and Earlier

NoiseBox: Towards More Efficient and Effective Learning with Noisy Labels

Chen Feng, G. Tzimiropoulos, and I. Patras

IEEE Transactions on Circuits and Systems for Video Technology, 2024

First author

DOI

CLIPCleaner: Cleaning Noisy Labels with CLIP

Chen Feng, G. Tzimiropoulos, and I. Patras

ACM International Conference on Multimedia (ACM MM), 2024

First author

DOI

MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset

Chen Feng and I. Patras

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

First author

DOI