Siyuan Chai — accepted AI-conference papers

2025

IntelliCockpitBench: A Comprehensive Benchmark to Evaluate VLMs for Intelligent Cockpit

Liang Lin, Siyuan Chai, Jiahao Wu, Hongbing Hu, Xiaotao Gu, Hao Hu +3

ACL 2025finding

The integration of sophisticated Vision-Language Models (VLMs) in vehicular systems is revolutionizing vehicle interaction and safety, performing tasks such as Visual Question Answering (VQA). However, a critical gap persists due to the lack of a comprehensive benchmark for multimodal VQA models in…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Layer Decomposition and Morphological Reconstruction for Task-Oriented Infrared Image Enhancement

Siyuan Chai, Xiaodong Guo, Tong Liu

IROS 2025

Infrared image helps improve the perception capabilities of autonomous driving in complex weather conditions such as fog, rain, and low light. However, infrared image often suffers from low contrast, especially in non-heat-emitting targets like bicycles, which significantly affects the performance o

Cited by 0 Source ↗Scholar ↗