3 papers
cs.CV2026
PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks
Junxian Li, Kai Liu, Leyang Chen +7
Unified multimodal models (UMMs) have shown impressive capabilities in generating natural images and supporting multimodal reasoning. However, their potential in supporting compute…
cs.CV2025
SpatialGeo:Boosting Spatial Reasoning in Multimodal LLMs via Geometry-Semantics Fusion
Jiajie Guo, Qingpeng Zhu, Jin Zeng +3
Multimodal large language models (MLLMs) have achieved significant progress in image and language tasks due to the strong reasoning capability of large language models (LLMs). Neve…
cs.LG2024
Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction
Ziyang Wu, Tianjiao Ding, Yifu Lu +6
The attention operator is arguably the key distinguishing factor of transformer architectures, which have demonstrated state-of-the-art performance on a variety of tasks. However,…