Gustavo Penha
@_Guz_
Followers
829
Following
10K
Media
42
Statuses
650
Research Scientist @Spotify · Working with IR, RecSys, NLP · PhD from @tudelft · ex @AmazonScience · https://t.co/SMu8BlyfIb
Holanda (Países Baixos)
Joined January 2009
We wrote a post summarizing our #RecSys2024 paper on bridging search and recommendation with generative retrieval 🧵 (1/N) https://t.co/vmG7iLr1Em w. @AliVardasbi, @denadai2, @enricopalumbo91, Hugues Bouchard
research.atspotify.com
Bridging Search and Recommendation with Generative Retrieval | Spotify Research
1
8
34
For anyone worried their LLM might be making stuff up, we made a budget‐friendly truth serum (semantic entropy + Bayesian). See for yourself: https://t.co/gq8oFP5Eqr Paper:
0
7
3
I doubt to what extent improvements on these datasets would translate to improvements in today's real-world recommendation settings. Reference: https://t.co/aJ4tZAYSqK
1
4
10
Happy to share our #recsys25 paper: “Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge”. 🧠 90 days of listening → natural-language user profiles → LLM judges alignment 📊 Aligns with human eval. With amazing Spotify co-authors. 📄
arxiv.org
Evaluating personalized recommendations remains a central challenge, especially in long-form audio domains like podcasts, where traditional offline metrics suffer from exposure bias and online...
2
5
13
Excited to share our paper “Semantic IDs for Joint Generative Search & Recommendation” @ RecSys'25 🧠 Jointly fine-tuning embeddings for both tasks → shared Semantic IDs that work for search and recs ⚖️ 📦 No more task-specific trade-offs!
2
3
8
Semantic IDs for Joint Generative Search and Recommendation @_Guz_ et al. at Spotify introduce a bi-encoder model fine-tuned on both search and recommendation tasks to obtain item embeddings, followed by construction of unified Semantic ID space. 📝 https://t.co/mTERH16wib
arxiv.org
Generative models powered by Large Language Models (LLMs) are emerging as a unified solution for powering both recommendation and search tasks. A key design choice in these models is how to...
0
2
11
Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge Spotify introduces a profile-aware LLM framework for evaluating personalized podcast recommendations using natural-language user profiles distilled from listening history. 📝 https://t.co/Rk8qUS0V2P
arxiv.org
Evaluating personalized recommendations remains a central challenge, especially in long-form audio domains like podcasts, where traditional offline metrics suffer from exposure bias and online...
0
6
22
Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations @denadai2 et al. at Spotify use multimodal LLMs to generate natural-language descriptions of video content for better recommendations 📝 https://t.co/zloHLosVzd 👨🏽💻 https://t.co/PlWzE5TRWp
0
4
8
What if we could use off-the-shelf Multimodal Large Language Model to enrich current video recommendation models? This is what we asked ourselves in our recent #recsys2025 paper https://t.co/1dqzYgM8LR 🧵
1
2
6
🔗 Blog Post: https://t.co/yfuAGZSySj 📚 Paper:
lnkd.in
This link will take you to a page that’s not on LinkedIn
0
0
1
🔎 LLM alignment techniques can enhance query expansion by eliminating the need for multiple generations followed by re-ranking/filtering steps. Check out this work led by @adam_x_yang during his internship with us at @SpotifyResearch w. @enricopalumbo91 and Hugues Bouchard⬇️
1
1
11
Adaptive Repetition for Mitigating Position Bias in LLM-Based Ranking Spotify introduces a dynamic early-stopping method that adaptively determines repetitions needed for each ranking instance, reducing LLM calls by 81% while preserving accuracy. 📝 https://t.co/TjcyF0RvlG
0
2
10
Aligned Query Expansion: Efficient Query Expansion for Information Retrieval through LLM Alignment @adam_x_yang et al. leverage LLM alignment techniques to fine-tune models for generating query expansions that directly optimize retrieval effectiveness. 📝 https://t.co/sAnWpP67wq
0
1
6
Contextualizing Spotify's Audiobook List Recommendations with Descriptive Shelves Spotify introduces a pipeline that generates personalized audiobook recommendations with descriptive shelves to help users explore content based on their interests. 📝 https://t.co/dzJvBkOzZI
0
4
15
The best-performing ID strategy was to use collaborative-filtering embeddings as input to the discretization approach for semantic IDs
1
0
1
Our approach leverages generative retrieval to return relevant tracks for broad queries.
1
0
0
We just published this blog post about our research on music track search with generative retrieval. 🧵 With @enricopalumbo91 @adamianou @peputo Timothy Christopher, Alice Wang, Hugues Bouchard, @mounialalmas
1
0
1
I am attending #ECIR25 at Lucca 🇮🇹 if you are interested and want to discuss this position!
We have an open research scientist position in our lab at Spotify, Personalization ! The areas of expertise are: Information Retrieval, Recommendation System, Language Technologies, Foundational Models, Generative AI Technologies, and Machine Learning. https://t.co/8DlA5iYmUt
0
0
12
We have an open research scientist position in our lab at Spotify, Personalization ! The areas of expertise are: Information Retrieval, Recommendation System, Language Technologies, Foundational Models, Generative AI Technologies, and Machine Learning. https://t.co/8DlA5iYmUt
0
2
10