Zixin Ding — accepted AI-conference papers

2026

THEMIS: Towards Holistic Evaluation of MLLMs for Scientific Paper Fraud Forensics

Tzu-Yen Ma, Bo Zhang, Zichen Tang, Junpeng Ding, Haolin Tian, Yuanze Li +17

ICLR 2026poster

We present **THEMIS**, a novel multi-task benchmark designed to comprehensively evaluate Multimodal Large Language Models (MLLMs) on visual fraud reasoning within real-world academic scenarios. Compared to existing benchmarks, THEMIS introduces three major advancements. (1) **Real-world Scenarios &…

Cited by 0 Source ↗code ↗Scholar ↗

2024

Learning to Rank for Active Learning via Multi-Task Bilevel Optimization

Zixin Ding, Si Chen, Ruoxi Jia, Yuxin Chen

UAI 2024poster

Active learning is a promising paradigm for reducing labeling costs by strategically requesting labels to improve model performance. However, existing active learning methods often rely on expensive acquisition functions, extensive model retraining, and multiple rounds of interaction with annotators…

Cited by 1 Source ↗PDF ↗Scholar ↗