2 papers
cs.CL2026
RoleBreak: Benchmarking Long-Horizon Role-Playing Robustness in Spoken Dialogue
Yuqi Wang, Fengyuan Liu, Haochen Luo +2
Speech-to-speech dialogue models increasingly support persona control, yet existing spoken role-playing benchmarks remain largely character-centric and short-horizon. This leaves o…
cs.LG2025
Boosting Brain-inspired Path Integration Efficiency via Learning-based Replication of Continuous Attractor Neurodynamics
Zhangyu Ge, Xu He, Lingfei Mo +5
The brain's Path Integration (PI) mechanism offers substantial guidance and inspiration for Brain-Inspired Navigation (BIN). However, the PI capability constructed by the Continuou…