Jirui Huang — accepted AI-conference papers

2026

Detecting AI-Generated Forgeries via Iterative Manifold Deviation Amplification

Jiangling Zhang, Shuxuan Gao, Bofan Liu, Siqiang Feng, Jirui Huang, Yaxiong Chen +1

CVPR 2026

The proliferation of highly realistic AI-generated images poses critical challenges for digital forensics, demanding precise pixel-level localization of manipulated regions. Existing methods predominantly learn discriminative patterns of specific forgeries, struggling with novel manipulations as edi

Cited by 0 Source ↗Scholar ↗

2026

LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models

Ruilin Yao, Bo Zhang, Jirui Huang, Xinwei Long, Yifang Zhang, Tianyu Zou +17

ICLR 2026poster

Multimodal Large Language Models (MLLMs) have achieved significant advances in integrating visual and linguistic information, yet their ability to reason about complex and real-world scenarios remains limited. Existing benchmarks are usually constructed in a task-oriented manner, without a guarantee…

Cited by 0 Source ↗Scholar ↗