Publications
A Parametric Memory Head for Continual Generative Retrieval 🔗 DOI ·
Slides (Full Paper) The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval Kidist Amde Mekonnen, Yubao Tang, and Maarten de Rijke
Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval 🔗 DOI · 📚 arXiv ·
Slides (Reproducibility Track) The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval Kidist Amde Mekonnen, Yongkang Li, Yubao Tang, Simon Lupart, and Maarten de Rijke
The Multilingual Curse at the Retrieval Layer: Evidence from Amharic 📄 Anthology · 🔗 DOI · ⬇️ PDF · 🖼️ Poster
The 1st Workshop on Multilinguality in the Era of Large Language Models, ACL 2026
Yosef Worku Alemneh†, Kidist Amde Mekonnen†, and Maarten de Rijke
†Equal contribution
uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking 📄 Anthology · 🔗 DOI · ⬇️ PDF
The 20th International Workshop on Semantic Evaluation, ACL 2026
Simon Lupart, Kidist Amde Mekonnen, Zahra Abbasiantaeb, and Mohammad Aliannejadi
Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval 📄 Paper ·
Slides (Full Paper) The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval Kidist Amde Mekonnen, Yubao Tang, and Maarten de Rijke
Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval 📄 Anthology · 🔗 DOI · ⬇️ PDF · 🖼️ Poster
Findings of the Association for Computational Linguistics
Kidist Amde Mekonnen†, Yosef Worku Alemneh†, and Maarten de Rijke
†Equal contribution
Earlier Work in Generative Modeling
Adv-KD: Adversarial Knowledge Distillation for Faster Diffusion Sampling
📚 arXiv
Kidist Amde Mekonnen, Nicola Dall’Asen, and Paolo Rota
Conditioning GAN Without Training Dataset
📚 arXiv
Kidist Amde Mekonnen
Balanced Face Dataset: Guiding StyleGAN to Generate Labeled Synthetic Face Image Dataset for Underrepresented Group
📚 arXiv
Kidist Amde Mekonnen
