Papers2

#error propagation

Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration

This paper teaches AI to look things up on the web and fix its own mistakes mid-thought instead of starting over from scratch.

#search-integrated reasoning#reinforcement learning#credit assignment

End-to-End Joint ASR and Speaker Role Diarization with Child-Adult Interactions

Intermediate

Anfeng Xu, Tiantian Feng et al.Jan 25arXiv

This paper builds one smart system that listens to child–adult conversations and writes what was said, who said it, and exactly when each person spoke.

#end-to-end ASR#speaker diarization#child speech