ArchitectureIQ: On the Measure of Training IntuitionZirui Ren, Shaoyang Guo, Chencheng Tang et al.0 citations2609.39714v12026arXiv
When2Talk: When Should a Proactive In-Car Agent Talk?Kaiser Hamid, Peihang Li, Nade Liang0 citations2609.12503v12026arXiv
Pointing to a Llama and Call it a Camel: On the Sycophancy of Multimodal Large Language ModelsRenjie Pi, Kehao Miao, Li Peihang et al.1 citation2509.16149v12025arXiv