Uncertainty-Aware Continual Learning for Open-World Intent Discovery Under an evolving Label Space
This story is from 2026-09-17. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.17866v1 Announce Type: new Abstract: Real-world intelligent systems increasingly operate under open-world conditions, where user intents are not fixed or exhaustively known a priori and may evolve as new interaction patterns emerge. This paper proposes a unified uncertainty-aware probabi…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-09-17 04:00 · arXiv cs.LG
Uncertainty-Aware Continual Learning for Open-World Intent Discovery Under an evolving Label Space