← Search

Fengchang Yu

2 accepted papers

2026

Fake-HR1: Rethinking Reasoning of vision language model for Synthetic Image Detection

ICASSP 2026poster

Recent studies have demonstrated that incorporating Chain-of-Thought (CoT) reasoning into the detection process can enhance a model's ability to detect synthetic images. However, excessively lengthy reasoning incurs substantial resource overhead, including token consumption and latency, which is par…

Cited by 0SourcePDFScholar
2025

TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data

EMNLP 2025

Complex reasoning over tabular data is crucial in real-world data analysis, yet large language models (LLMs) often underperform due to complex queries, noisy data, and limited numerical capabilities. To address these issues, we propose TabDSR, a three-agent framework consisting of: (1) a query decom

Cited by 0SourcePDFScholar