NYU Tandon School of Engineering
Author of "DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search" on arXiv
How media typically covers Yang Xu
Yang Xu as author
DeepMMSearch-R1 is the first multimodal LLM capable of performing on-demand, multi-turn web searches with dynamic query crafting for both image and text, using a two-stage training pipeline of supervised finetuning followed by reinforcement learning optimization.
“Author of "DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search" on arXiv”