2 papers
cs.CL2025
Progress Ratio Embeddings: An Impatience Signal for Robust Length Control in Neural Text Generation
Ivanhoé Botcazou, Tassadit Amghar, Sylvain Lamprier +1
Modern neural language models achieve high accuracy in text generation, yet precise control over generation length remains underdeveloped. In this paper, we first investigate a rec…
cs.LG2020
Partial Bandit and Semi-Bandit: Making the Most Out of Scarce Users' Feedback
Alexandre Letard, Tassadit Amghar, Olivier Camp +1
Recent works on Multi-Armed Bandits (MAB) and Combinatorial Multi-Armed Bandits (COM-MAB) show good results on a global accuracy metric. This can be achieved, in the case of recomm…