作者位次 #4/4ICML 2026Poster· Reinforcement Learning / Policy Search
TUR-DPO: Topology- and Uncertainty-Aware Direct Preference Optimization
Abdulhady abas · Fatemeh Daneshfar · Seyedali Mirjalili · Mourad Oussalah
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Abdulhady abas · Fatemeh Daneshfar · Seyedali Mirjalili · Mourad Oussalah
Yuanjun Zhang · Mourad Oussalah
Humanitarian reports are long, noisy, and multi-topic, making it difficult to consolidate decision-relevant causal evidence. We present a ReliefWeb study (2000–2024) and a two-stage Large Language Model (LLM) pipeline that extracts structured intervention-outcome records with direction and streng...
Amir Mollazadeh · Mourad Oussalah · Mehrdad Rostami
Food recommender systems often struggle with popularity bias that favors unhealthy recipes, making the promotion of healthier items a significant communication challenge. While explainable recommendations can help justify healthy trade-offs, evaluating their real-world impact is often hindered by...