by Shaosheng Cao Papers
3 papers found
Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models
Xiaoyu Zhan, Wenxuan Huang, Hao Sun et al.
NeurIPS 2025poster
Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification
Wenxuan Huang, Zijie Zhai, Yunhang Shen et al.
ICLR 2025poster
SNS-Bench: Defining, Building, and Assessing Capabilities of Large Language Models in Social Networking Services
Hongcheng Guo, Yue Wang, Shaosheng Cao et al.
ICML 2025poster