3 papers
cs.CV2025
Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models
Tianfan Peng, Yuntao Du, Pengzhou Ji +9
Large multimodal models (LMMs) often suffer from severe inference inefficiency due to the large number of visual tokens introduced by image encoders. While recent token compression…
cs.CV2025
MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook
Peng Xu, Shengwu Xiong, Jiajun Zhang +125
This paper reviews the MARS2 2025 Challenge on Multimodal Reasoning. We aim to bring together different approaches in multimodal machine learning and LLMs via a large benchmark. We…
math.AP2025
Scattering for the Klein-Gordon-Zakharov system in two dimensions
Shijie Dong, Zihua Guo, Kuijie Li
We study the Klein-Gordon-Zakharov system in two spatial dimensions, an important model in plasma physics. For small, smooth, and spatially localized initial data, we establish the…