Charles Rosenberg
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Charles Rosenberg has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Jiajing Xu
Pinterest, San Francisco, CA, USA
7 shared publications - Jaewon Yang
Pinterest, Palo Alto, CA, USA
5 shared publications - Prabhat Agarwal
Pinterest, Palo Alto, CA, USA
5 shared publications - Anirudhan Badrinath
Pinterest, Palo Alto, CA, USA
3 shared publications - Kousik Rajesh
Pinterest, San Francisco, CA, USA
3 shared publications - Laksh Bhasin
Pinterest, Palo Alto, CA, USA
3 shared publications
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1613-1622
UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1613-1622
Open AccessUniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7037-7048
PinRec: Unified Generative Retrieval Model for Pinterest Recommender Systems
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7037-7048
Open AccessPinRec: Unified Generative Retrieval Model for Pinterest Recommender Systems
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 8190-8201
Pinterest Canvas: Large-Scale Image Generation at Pinterest
While recent image generation models demonstrate a remarkable ability to handle a wide variety of image generation tasks, this flexibility makes them hard to control via prompting or simple inference adaptation alone, rendering them unsuitable for use cases with strict product requirements. In this paper, we introduce Pinterest Canvas, our large-scale image generation system built to support image editing and enhancement use cases at Pinterest. Canvas is first trained on a diverse, multimodal dataset to produce a foundational diffusion model with broad image-editing capabilities. However, rather than relying on one generic model to handle every downstream task, we instead rapidly fine-tune variants of this base model on task-specific datasets, producing specialized models for individual use cases. We describe key components of Canvas and summarize our best practices for dataset curation, training, and inference. We also showcase task-specific variants through case studies on background enhancement and aspect-ratio outpainting, highlighting how we tackle their specific product requirements. Online A/B experiments demonstrate that our enhanced images receive a significant 18.0% and 12.5% engagement lift, respectively, and comparisons with human raters further validate that our models outperform third-party models on these tasks. Finally, we showcase other Canvas variants, including multi-image scene synthesis and image-to-video generation, demonstrating that our approach can generalize to a wide variety of potential downstream tasks.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 8190-8201
Open AccessPinterest Canvas: Large-Scale Image Generation at Pinterest
While recent image generation models demonstrate a remarkable ability to handle a wide variety of image generation tasks, this flexibility makes them hard to control via prompting or simple inference adaptation alone, rendering them unsuitable for use cases with strict product requirements. In this paper, we introduce Pinterest Canvas, our large-scale image generation system built to support image editing and enhancement use cases at Pinterest. Canvas is first trained on a diverse, multimodal dataset to produce a foundational diffusion model with broad image-editing capabilities. However, rather than relying on one generic model to handle every downstream task, we instead rapidly fine-tune variants of this base model on task-specific datasets, producing specialized models for individual use cases. We describe key components of Canvas and summarize our best practices for dataset curation, training, and inference. We also showcase task-specific variants through case studies on background enhancement and aspect-ratio outpainting, highlighting how we tackle their specific product requirements. Online A/B experiments demonstrate that our enhanced images receive a significant 18.0% and 12.5% engagement lift, respectively, and comparisons with human raters further validate that our models outperform third-party models on these tasks. Finally, we showcase other Canvas variants, including multi-image scene synthesis and image-to-video generation, demonstrating that our approach can generalize to a wide variety of potential downstream tasks.
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6861-6862
Autoregressive Generative Retrieval for Industrial-Scale Recommendations at Pinterest
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6861-6862
Open AccessAutoregressive Generative Retrieval for Industrial-Scale Recommendations at Pinterest
- Open Access
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 945-948
Deep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at Pinterest
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 945-948
Open AccessDeep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at Pinterest
- Open Access
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 381-390
PinFM: Foundation Model for User Activity Sequences at a Billion-scale Visual Discovery Platform
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 381-390
Open AccessPinFM: Foundation Model for User Activity Sequences at a Billion-scale Visual Discovery Platform
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 4261-4272
OmniSage: Large Scale, Multi-Entity Heterogeneous Graph Representation Learning
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 4261-4272
Open AccessOmniSage: Large Scale, Multi-Entity Heterogeneous Graph Representation Learning
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 121-130
OmniSearchSage: Multi-Task Multi-Entity Embeddings for Pinterest Search
In this paper, we present OmniSearchSage, a versatile and scalable system for understanding search queries, pins, and products for Pinterest search. We jointly learn a unified query embedding coupled with pin and product embeddings, leading to an improvement of >8% relevance, >7% engagement, and >5% ads CTR in Pinterest's production search system. The main contributors to these gains are improved content understanding, better multi-task learning, and real-time serving. We enrich our entity representations using diverse text derived from image captions from a generative LLM, historical engagement, and user-curated boards. Our multitask learning setup produces a single search query embedding in the same space as pin and product embeddings and compatible with pre-existing pin and product embeddings. We show the value of each feature through ablation studies, and show the effectiveness of a unified model compared to standalone counterparts. Finally, we share how these embeddings have been deployed across the Pinterest search stack, from retrieval to ranking, scaling to serve 300k requests per second at low latency. Our implementation of this work is available at this link https://github.com/pinterest/atg-research/tree/main/omnisearchsage.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 121-130
Open AccessOmniSearchSage: Multi-Task Multi-Entity Embeddings for Pinterest Search
In this paper, we present OmniSearchSage, a versatile and scalable system for understanding search queries, pins, and products for Pinterest search. We jointly learn a unified query embedding coupled with pin and product embeddings, leading to an improvement of >8% relevance, >7% engagement, and >5% ads CTR in Pinterest's production search system. The main contributors to these gains are improved content understanding, better multi-task learning, and real-time serving. We enrich our entity representations using diverse text derived from image captions from a generative LLM, historical engagement, and user-curated boards. Our multitask learning setup produces a single search query embedding in the same space as pin and product embeddings and compatible with pre-existing pin and product embeddings. We show the value of each feature through ablation studies, and show the effectiveness of a unified model compared to standalone counterparts. Finally, we share how these embeddings have been deployed across the Pinterest search stack, from retrieval to ranking, scaling to serve 300k requests per second at low latency. Our implementation of this work is available at this link https://github.com/pinterest/atg-research/tree/main/omnisearchsage.
- Open Access
- 18 January 2021
- Published by Society for Imaging Science & Technology in Electronic Imaging
- Vol. 33 (8) , 283-1
Practical Automatic Thumbnail Generation for Short Videos
Fast track article for IS&T International Symposium on Electronic Imaging 2021: Imaging and Multimedia Analytics in a Web and Mobile World 2021 proceedings.
- 18 January 2021
- Published by Society for Imaging Science & Technology in Electronic Imaging
- Vol. 33 (8) , 283-1
Open AccessPractical Automatic Thumbnail Generation for Short Videos
Fast track article for IS&T International Symposium on Electronic Imaging 2021: Imaging and Multimedia Analytics in a Web and Mobile World 2021 proceedings.
- 1 July 2005
- Published by Dustri-Verlag Dr. Karl Feistle in Prävention und Rehabilitation
- Vol. 17 (07) , 118-122
Zum Einfluß koffeinhaltiger Teesorten auf Belastungsparameter bei einer Alltagsbelastung
- 1 July 2005
- Published by Dustri-Verlag Dr. Karl Feistle in Prävention und Rehabilitation
- Vol. 17 (07) , 118-122
Zum Einfluß koffeinhaltiger Teesorten auf Belastungsparameter bei einer Alltagsbelastung