SEA: Search Engines Amsterdam

This meetup session will focus on SIGIR 2026 and feature three speakers from University of Amsterdam: Oscar Ramirez Milian, Jingwei Kang, and Yongkang Li. They will present their papers accepted at SIGIR 2026.

Location: Science Park 904, Room C3.161
Date: Friday, May 29
Time: 16:00-17:00
Zoom link: https://uva-live.zoom.us/j/65011610507

Details below:
Speaker #1: Oscar Ramirez Milian from University of Amsterdam

Title: From Interactions to Distributions

Abstract: In this work, we introduce the first evidential deep-learning approach to form an epistemic alternative to the important position-based click model. Our learned model takes as input item and position features and outputs a beta-distribution for every relevance
and position-bias variable of the position-based model. These distributions capture epistemic uncertainty about click probabilities
and the underlying effects of attraction and position bias. The main challenge of our approach is its optimization for which we propose approximation and conditioning techniques to provide numerical stability and variance reduction

Short Bio: I'm a PhD student in University of Amsterdam.

Speaker #2: Jingwei Kang from University of Amsterdam

Title: Following the Eye-Tracking Evidence: Established Web-Search Assumptions Fail in Carousel Interfaces

Abstract: Carousel interfaces have been the de-facto standard for streaming media services for over a decade. Yet, there has been very little research into user behavior with such interfaces, which thus remains poorly understood. Due to this lack of empirical research, previous work has assumed that behaviors established in single-list web-search interfaces, such as the F-pattern and the examination hypothesis, also apply to carousel interfaces, for instance when designing click models or evaluation metrics. We analyze a recently-released interaction and examination dataset resulting from an eye-tracking study performed on carousel interfaces to verify whether these assumptions actually hold.
We find that (i) the F-pattern holds only for vertical examination and not for horizontal swiping; additionally, we discover that, when conditioned on a click, user examination follows an L-pattern unique to carousel interfaces; (ii) click-through-rates conditioned on examination indicate that the well-known examination hypothesis does not hold in carousel interfaces; and (iii) contrary to the assumptions of previous work, users generally ignore carousel headings and focus directly on the content items. Our findings show that many user behavior assumptions, especially concerning examination patterns, do not transfer from web search interfaces to carousel recommendation settings. Our work shows that the field lacks a reliable foundation on which to build models of user behavior with these interfaces. Consequently, a re-evaluation of existing metrics and click models for carousel interfaces may be warranted.

Bio: Jingwei Kang is a third-year PhD student at the IRLab at University of Amsterdam. His main research interest is preference learning. During PhD, his main research focus is on recommender systems in carousel interfaces.

Speaker #3: Yongkang Li from University of Amsterdam
Title: Spectral Tempering for Embedding Compression in Dense Passage Retrieval

Abstract: Dimensionality reduction is critical for deploying dense retrieval systems at scale, yet mainstream post-hoc methods face a fundamental trade-off: principal component analysis (PCA) preserves dominant variance but underutilizes representational capacity, while whitening enforces isotropy at the cost of amplifying noise in the heavy-tailed eigenspectrum of retrieval embeddings. Intermediate spectral scaling methods unify these extremes by reweighting dimensions with a power coefficient gamma, but treat gamma as a fixed hyperparameter that requires task-specific tuning. We show that the optimal scaling strength gamma is not a global constant: it varies systematically with target dimensionality k and is governed by the signal-to-noise ratio (SNR) of the retained subspace. Based on this insight, we propose Spectral Tempering (SpecTemp), a learning-free method that derives an adaptive gamma(k) directly from the corpus eigenspectrum using local SNR analysis and knee-point normalization, requiring no labeled data or validation-based search. Extensive experiments demonstrate that Spectral Tempering consistently achieves near-oracle performance relative to grid-searched gamma^(k) while remaining fully learning-free and model-agnostic.
Bio: Yongkang is a third-year PhD student at the IR Lab at the University of Amsterdam. He is very interested in embedding-based retrieval systems. His main research focuses on the robustness and generalization of dense retrieval.

Counter: SEA Talks #305, #306 and #307.