2 papers
cs.AI2026
DyadMem: A Long-Term Memory Benchmark of How Agents Work with Users
Yifei Tao, Xinyu Zhong, Henry Hengyuan Zhao +5
Long-term agents must remember not only what is true about a user, but also how a particular agent should work with that user as their shared history evolves. Existing benchmarks p…
cs.CV2026
StepX-Edge: An On-Device UI Vision-Language Model via Architecture-Training-Deployment Co-Design
Yin Wang, Haotian Hu, Jineng Han +4
Deploying a vision-language model with full UI understanding on end devices has long been trapped between accuracy and efficiency: on one side is the accuracy bar for OCR, screen u…