← Search

Haocheng Gao

2 accepted papers

2026

FinMMDocR: Benchmarking Financial Multimodal Reasoning with Scenario Awareness, Document Understanding, and Multi-Step Computation

AAAI 2026technical

We introduce FinMMDocR, a novel bilingual multimodal benchmark for evaluating multimodal large language models (MLLMs) on real-world financial numerical reasoning. Compared to existing benchmarks, our work delivers three major advancements. (1) Scenario Awareness: 57.9% of 1,200 expert-annotated pro

Cited by 0SourcePDFScholar
2026

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

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 0SourcecodeScholar