Apple could unveil Gemini-powered Siri in Feb. Pinterest is conducting a massive round of layoffs to prioritize'AI-powered products and capabilities' This could total up to 675 employees. Pinterest is planning on laying off up to 15 percent of its workforce, . The company has been, so why punish employees? You already know the answer. The company said it's reallocating resources to AI projects and prioritizing AI-powered products and capabilities.

Javed is a senior editor at TIME, based in the London bureau. Javed is a senior editor at TIME, based in the London bureau. Leaders from across the tech sector, academia, and beyond gathered to explore how to implement responsible AI and ensure safeguarding while fostering innovation, at a roundtable convened by TIME in Davos, Switzerland, on Jan 21. In a wide-ranging conversation, participants in the roundtable, hosted by TIME CEO Jess Sibley, discussed topics including the impact of AI on children's development and safety, how to regulate the technology, and how to better train models to ensure they don't harm humans. Discussing the safety of children, Jonathan Haidt, professor of ethical leadership at NYU Stern and author of said that parents shouldn't focus on restricting their child's exposure entirely but on the habits they form.

Since implicit feedback data contain positive instances only, the implicit CF problem is also related to learning from positive-unlabeled (PU) data. The first three authors have equal contributions. However, the size of unlabeled data in implicit CF can approach to nearly a product of user count and item count, making above non-sampling approach become unaffordable in terms of learning efficiency. Negative sampling approaches have also been widely adopted in other domains of embedding learning for text, graph, etc. Motivated by these works that tend to leverage a simple model for Our SRNS's hyper-parameters can be divided into three parts: (1) sampling related part, including In synthetic noise experiments, since we do not explicitly split a validation set on synthetic data, we draw two different train/test splits. In real data experiments, we conduct the standard procedure to split train/validation/test set.

A surge of AI-generated content is frustrating Pinterest users and left some questioning whether the platform still works at all. For five years, Caitlyn Jones has used Pinterest on a weekly basis to find recipes for her son. In September, Jones spotted a creamy chicken and broccoli slow-cooker recipe, sprinkled with golden cheddar and a pop of parsley. She quickly looked at the ingredients and added them to her grocery list. But just as she was about to start cooking, having already bought everything, one thing stood out: The recipe told her to start by "logging" the chicken into the slow cooker.

Generative retrieval methods utilize generative sequential modeling techniques, such as transformers, to generate candidate items for recommender systems. These methods have demonstrated promising results in academic benchmarks, surpassing traditional retrieval models like two-tower architectures. However, current generative retrieval methods lack the scalability required for industrial recommender systems, and they are insufficiently flexible to satisfy the multiple metric requirements of modern systems. This paper introduces PinRec, a novel generative retrieval model developed for applications at Pinterest. PinRec utilizes outcome-conditioned generation, enabling modelers to specify how to balance various outcome metrics, such as the number of saves and clicks, to effectively align with business goals and user exploration. Additionally, PinRec incorporates multi-token generation to enhance output diversity while optimizing generation. Our experiments demonstrate that PinRec can successfully balance performance, diversity, and efficiency, delivering a significant positive impact to users using generative models. This paper marks a significant milestone in generative retrieval, as it presents, to our knowledge, the first rigorous study on implementing generative retrieval at the scale of Pinterest.

User retention is a critical objective for online platforms like Pinterest, as it strengthens user loyalty and drives growth through repeated engagement. A key indicator of retention is revisitation, i.e., when users return to view previously saved content, a behavior often sparked by personalized recommendations and user satisfaction. However, modeling and optimizing revisitation poses significant challenges. One core difficulty is accurate attribution: it is often unclear which specific user actions or content exposures trigger a revisit, since many confounding factors (e.g., content quality, user interface, notifications, or even changing user intent) can influence return behavior. Additionally, the scale and timing of revisitations introduce further complexity; users may revisit content days or even weeks after their initial interaction, requiring the system to maintain and associate extensive historical records across millions of users and sessions. These complexities render existing methods insufficient for robustly capturing and optimizing long-term revisitation. To address these gaps, we introduce a novel, lightweight, and interpretable framework for modeling revisitation behavior and optimizing long-term user retention in Pinterest's search-based recommendation context. By defining a surrogate attribution process that links saves to subsequent revisitations, we reduce noise in the causal relationship between user actions and return visits. Our scalable event aggregation pipeline enables large-scale analysis of user revisitation patterns and enhances the ranking system's ability to surface items with high retention value. Deployed on Pinterest's Related Pins surface to serve 500+ million users, the framework led to a significant lift of 0.1% in active users without additional computational costs.

The alt-text generation task produces concise, context-relevant descriptions of images, enabling blind and low-vision users to access online images. Despite the capabilities of large vision-language models, alt-text generation performance remains limited due to noisy user annotations, inconsistent standards, and MLLMs' insensitivity to contextual information. Previous efforts to fine-tune MLLMs using supervised fine-tuning (SFT) have struggled, as SFT relies on accurate target annotations, which are often flawed in user-generated alt-text. To address this, we propose Multi-faceted Cross-modal Direct Preference Optimization (MCM-DPO), which improves alt-text generation by learning to identify better options in preference pairs without requiring precise annotations. MCM-DPO optimizes preferences across single, paired, and multi-preference dimensions, covering textual, visual, and cross-modal factors. In light of the scarcity of high-quality annotated and preference-labeled datasets for alt-text, we constructed two large-scale, high-quality datasets named TAlt and PAlt, sourced from Twitter and Pinterest. These datasets include 202k annotated alt-text samples and 18k preference pairs that cover diverse preference dimensions, aiming to support further research in this domain. Experimental results show that our proposed MCM-DPO method consistently outperforms both DPO and SFT, establishing a new state of the art in alt-text generation. We release the code and data here: https://github.com/LVUGAI/MCM-DPO

In this paper, we introduce a novel framework following an upstream-downstream paradigm to construct user and item (Pin) embeddings from diverse data sources, which are essential for Pinterest to deliver personalized Pins and ads effectively. Our upstream models are trained on extensive data sources featuring varied signals, utilizing complex architectures to capture intricate relationships between users and Pins on Pinterest. To ensure scalability of the upstream models, entity embeddings are learned, and regularly refreshed, rather than real-time computation, allowing for asynchronous interaction between the upstream and downstream models. These embeddings are then integrated as input features in numerous downstream tasks, including ad retrieval and ranking models for CTR and CVR predictions. We demonstrate that our framework achieves notable performance improvements in both offline and online settings across various downstream tasks. This framework has been deployed in Pinterest's production ad ranking systems, resulting in significant gains in online metrics.

Large embedding tables are indispensable in modern recommendation systems, thanks to their ability to effectively capture and memorize intricate details of interactions among diverse entities. As we explore integrating large embedding tables into Pinterest's ads ranking models, we encountered not only common challenges such as sparsity and scalability, but also several obstacles unique to our context. Notably, our initial attempts to train large embedding tables from scratch resulted in neutral metrics. To tackle this, we introduced a novel multi-faceted pretraining scheme that incorporates multiple pretraining algorithms. This approach greatly enriched the embedding tables and resulted in significant performance improvements. As a result, the multi-faceted large embedding tables bring great performance gain on both the Click-Through Rate (CTR) and Conversion Rate (CVR) domains. Moreover, we designed a CPU-GPU hybrid serving infrastructure to overcome GPU memory limits and elevate the scalability. This framework has been deployed in the Pinterest Ads system and achieved 1.34% online CPC reduction and 2.60% CTR increase with neutral end-to-end latency change.