# Short-Form Video Recommendations with Multimodal Embeddings: Addressing Cold-Start and Bias Challenges

arXiv: https://arxiv.org/abs/2507.19346 · HTML: https://mlsanity.com/paper/2507.19346/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 22 references that are in the map.
- First posted on arXiv 25 Jul 2025.

## Builds on (most cited first, 11 of 11)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Unbiased Learning-to-Rank with Biased Feedback](https://mlsanity.com/paper/1608.04468/) (2016)
- [Understanding Echo Chambers in E-commerce Recommender Systems](https://mlsanity.com/paper/2007.02474/) (2020)
- [Deconfounding Duration Bias in Watch-time Prediction for Video Recommendation](https://mlsanity.com/paper/2206.06003/) (2022)
- [Correcting for Selection Bias in Learning-to-rank Systems](https://mlsanity.com/paper/2001.11358/) (2020)
- [Reinforcing User Retention in a Billion Scale Short Video Recommender System](https://mlsanity.com/paper/2302.01724/) (2023)
- [DVR: Micro-Video Recommendation Optimizing Watch-Time-Gain under Duration Bias](https://mlsanity.com/paper/2208.05190/) (2022)
- [Feature-aware Diversified Re-ranking with Disentangled Representations for Relevant Recommendation](https://mlsanity.com/paper/2206.05020/) (2022)
- [Business Entity Matching with Siamese Graph Convolutional Networks](https://mlsanity.com/paper/2105.03701/) (2021)
- [Building a Scalable, Effective, and Steerable Search and Ranking Platform](https://mlsanity.com/paper/2409.02856/) (2024)
- [Efficient and Effective Query Context-Aware Learning-to-Rank Model for Sequential Recommendation](https://mlsanity.com/paper/2507.03789/) (2025)

## Abstract (arXiv)

In recent years, social media users have spent significant amounts of time on short-form video platforms. As a result, established platforms in other domains, such as e-commerce, have begun introducing short-form video content to engage users and increase their time spent on the platform. The success of these experiences is due not only to the content itself but also to a unique UI innovation: instead of offering users a list of choices to click, platforms actively recommend content for users to watch one at a time. This creates new challenges for recommender systems, especially when launching a new video experience. Beyond the limited interaction data, immersive feed experiences introduce stronger position bias due to the UI and duration bias when optimizing for watch-time, as models tend to favor shorter videos. These issues, together with the feedback loop inherent in recommender systems, make it difficult to build effective solutions. In this paper, we highlight the challenges faced when introducing a new short-form video experience and present our experience showing that, even with sufficient video interaction data, it can be more beneficial to leverage a video retrieval system using a fine-tuned multimodal vision-language model to overcome these challenges. This approach demonstrated greater effectiveness compared to conventional supervised learning methods in online experiments conducted on our e-commerce platform.