Shervin Shahryari
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shervin Shahryari has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Alexandre Salle
Institute of Informatics Universidade Federal do Rio Grande do Sul
1 shared publication - Chenglei Niu
Tubi, San Francisco, CA, USA
1 shared publication - Michael Tamir
Tubi, San Francisco, CA, USA
1 shared publication - Qiang Chen
Tubi, San Francisco, CA, USA
1 shared publication - Saurabh Agrawal
Tubi, San Francisco, CA, USA
1 shared publication - Suchismit Mahapatra
Computer Science and Engineering Computer Science and Engineering State University of New York at Buffalo State University of New York at Buffalo
1 shared publication
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1595-1604
TubiFM: Unified Item, Carousel, and Search Ranking for Streaming Discovery
Personalized discovery systems often train separate models for item ranking, carousel ranking, and search, even though these tasks expose complementary signals from the same viewer journey: watches shape carousel and item ranking, search queries reveal intent even when they do not lead to a catalog match, and watch history helps interpret search as rewatching, continuation, or new discovery. We introduce the user story, a serialized representation that turns a user’s cross-surface history (attributes, sessions, watch events with surface and carousel context, and search events) into a single token sequence. By interleaving pretrained language tokens with domain-specific event tokens, user stories let heterogeneous recommendation and search tasks be expressed as prompted next-token prediction over a shared grammar. TubiFM is one instantiation of this approach: a Llama 3.2 1B-based model trained on user stories and prompted to rank items, carousels, or search results without task-specific architectures. In offline evaluation, this single model outperforms specialist baselines across item, carousel, and search ranking. In online A/B tests, TubiFM significantly improves search total viewing time (TVT) by +3.9% and carousel TVT by +0.30%. Item ranking is statistically neutral on TVT (+0.14%), matching a mature production stack while replacing it with a single model. Across all three tasks, TubiFM serves on L40S GPUs and reduces p99 ranking latency from approximately 500ms to 200ms. These results show that shared user stories can improve discovery while simplifying ranking systems.
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1595-1604
Open AccessTubiFM: Unified Item, Carousel, and Search Ranking for Streaming Discovery
Personalized discovery systems often train separate models for item ranking, carousel ranking, and search, even though these tasks expose complementary signals from the same viewer journey: watches shape carousel and item ranking, search queries reveal intent even when they do not lead to a catalog match, and watch history helps interpret search as rewatching, continuation, or new discovery. We introduce the user story, a serialized representation that turns a user’s cross-surface history (attributes, sessions, watch events with surface and carousel context, and search events) into a single token sequence. By interleaving pretrained language tokens with domain-specific event tokens, user stories let heterogeneous recommendation and search tasks be expressed as prompted next-token prediction over a shared grammar. TubiFM is one instantiation of this approach: a Llama 3.2 1B-based model trained on user stories and prompted to rank items, carousels, or search results without task-specific architectures. In offline evaluation, this single model outperforms specialist baselines across item, carousel, and search ranking. In online A/B tests, TubiFM significantly improves search total viewing time (TVT) by +3.9% and carousel TVT by +0.30%. Item ranking is statistically neutral on TVT (+0.14%), matching a mature production stack while replacing it with a single model. Across all three tasks, TubiFM serves on L40S GPUs and reduces p99 ranking latency from approximately 500ms to 200ms. These results show that shared user stories can improve discovery while simplifying ranking systems.