Posts by Collection

portfolio

Generative Retrieval

Research on generative information retrieval, direct relevance optimization, decoding, and continual retrieval memory.

Multilingual Retrieval

Work on embeddings, evaluation resources, and retrieval benchmarks for multilingual and low-resource settings.

RAG and Recommendation

Projects connecting neural IR, recommendation, retrieval-augmented generation, and large-scale machine learning.

publications

Balanced Face Dataset: Guiding StyleGAN for Labeled Synthetic Face Image Dataset for Underrepresented Group

Published in arXiv, 2023

An arXiv preprint on guiding StyleGAN to create labeled synthetic face datasets for underrepresented groups.

Recommended citation: Mekonnen, K. A., et al. (2023). "Balanced Face Dataset: Guiding StyleGAN for Labeled Synthetic Face Image Dataset for Underrepresented Group." arXiv preprint.
Download Paper

Adv-KD: Adversarial Knowledge Distillation for Faster Diffusion Sampling

Published in arXiv, 2024

An arXiv preprint on adversarial knowledge distillation for faster diffusion sampling.

Recommended citation: Mekonnen, K. A., et al. (2024). "Adv-KD: Adversarial Knowledge Distillation for Faster Diffusion Sampling." arXiv preprint.
Download Paper

Conditioning GAN Without Training Dataset

Published in arXiv, 2024

An arXiv preprint on conditioning GANs without a training dataset.

Recommended citation: Mekonnen, K. A., et al. (2024). "Conditioning GAN Without Training Dataset." arXiv preprint.
Download Paper

Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval

Published in SIGIR 2025, 2025

A SIGIR 2025 full paper on lightweight document relevance optimization for generative information retrieval.

Recommended citation: Mekonnen, K. A., et al. (2025). "Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval." Proceedings of SIGIR 2025.
Download Paper

Optimized Text Embeddings & Benchmarks for Amharic Passage Retrieval

Published in ACL Findings 2025, 2025

An ACL Findings 2025 paper on embeddings and benchmarks for Amharic passage retrieval.

Recommended citation: Mekonnen, K. A., et al. (2025). "Optimized Text Embeddings & Benchmarks for Amharic Passage Retrieval." Findings of the Association for Computational Linguistics.
Download Paper

The Multilingual Curse at the Retrieval Layer: Evidence from Amharic

Published in ACL MeLLM 2026, 2026

An ACL MeLLM 2026 workshop paper on retrieval-layer failures in multilingual systems, with evidence from Amharic.

Recommended citation: Alemneh, Y. W.^*, Mekonnen, K. A.^*, and de Rijke, M. (2026). "The Multilingual Curse at the Retrieval Layer: Evidence from Amharic." The 1st Workshop on Multilinguality in the Era of Large Language Models, ACL 2026. ^*Equal contribution.
Download Paper

Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval

Published in SIGIR 2026 Reproducibility Track, 2026

A SIGIR 2026 Reproducibility Track paper stress-testing the look-ahead prior in generative retrieval.

Recommended citation: Mekonnen, K. A., et al. (2026). "Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval." Proceedings of SIGIR 2026.
Download Paper

A Parametric Memory Head for Continual Generative Retrieval

Published in SIGIR 2026, 2026

A SIGIR 2026 full paper on continual generative retrieval with parametric memory.

Recommended citation: Mekonnen, K. A., et al. (2026). "A Parametric Memory Head for Continual Generative Retrieval." Proceedings of SIGIR 2026.
Download Paper

talks

teaching

Recommender Systems

Teaching assistant, University of Amsterdam, MSc Artificial Intelligence, 2025

Teaching assistant for the MSc Artificial Intelligence Recommender Systems course. Developed and delivered a lecture on generative approaches to recommender systems, including semantic identifiers and generative recommendation.

Download Download Slides

Information Retrieval 0

Teaching assistant, University of Amsterdam, BSc Artificial Intelligence, 2025

Teaching assistant for the Information Retrieval 0 course. Supported lab sessions, assignment preparation, project feedback, grading, and exam assessment for an undergraduate information retrieval course.

Academic Service

Service, Information retrieval, machine learning, and NLP communities, 2026

Reviewer for major information retrieval and machine learning venues, including NeurIPS 2026, SIGIR 2026 across multiple tracks, and ECIR 2025. Received ECIR best reviewer recognition.

BSc Thesis Supervision

Thesis supervision, University of Amsterdam, 2026

Supervising a BSc thesis project on multilingual search for low-resource languages, with a focus on multilingual retrieval evaluation, query translation, dense retrieval, and error analysis.