Multimodal Learning | Chenzhu Wanghttps://chenzhuwang.com/tags/multimodal-learning/Multimodal LearningHugo Blox Builder (https://hugoblox.com)en-usSun, 26 Apr 2026 00:00:00 +0000https://chenzhuwang.com/media/icon_hu7729264130191091259.pngMultimodal Learninghttps://chenzhuwang.com/tags/multimodal-learning/Multimodal ADAS Video Safetyhttps://chenzhuwang.com/project/multimodal-adas-video/Sun, 26 Apr 2026 00:00:00 +0000https://chenzhuwang.com/project/multimodal-adas-video/<p>This project line studies how first-person traffic video, social media crash evidence, and ADAS-equipped vehicle events can support richer safety understanding.</p> <p>Current work includes the SAVeD dataset for near-miss and crash event analysis, LLM-assisted event parsing, vision-language modeling, and controllable diffusion-based counterfactual scenarios for &ldquo;what-if&rdquo; safety assessment.</p>