Jiayang Zhang — accepted AI-conference papers

2025

From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image Reasoning

Hang Du, Jiayang Zhang, Guoshun Nan, Wendi Deng, Zhenyan Chen, Chenyang Zhang +5

ICCV 2025poster

Multi-image Interleaved Reasoning aims to improve Multimodal Large Language Models' (MLLMs) ability to jointly comprehend and reason across multiple images and their associated textual contexts, introducing unique challenges beyond single-image or non-interleaved multi-image tasks.While current mult…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

LOG: A Local-to-Global Optimization Approach for Retrieval-based Explainable Multi-Hop Question Answering

Hao Xu, Yunxiao Zhao, Jiayang Zhang, Zhiqiang Wang, Ru Li

COLING 2025main

Multi-hop question answering (MHQA) aims to utilize multi-source intensive documents retrieved to derive the answer. However, it is very challenging to model the importance of knowledge retrieved. Previous approaches primarily emphasize single-step and multi-step iterative decomposition or retrieval…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗