State of the Field
Recent advancements in recommender systems are focusing on enhancing efficiency and user engagement through innovative frameworks and methodologies. The integration of model merging techniques is gaining traction, allowing for the combination of specialized generative models without the need for retraining, which addresses the high computational costs associated with large-scale models. Additionally, new approaches like semantic ID-based recommendation and information-aware auto-bidding are being developed to improve the accuracy and effectiveness of recommendations while minimizing biases and optimizing content promotion strategies. The emergence of frameworks that facilitate real-time preference propagation and steerability through natural language profiles is also noteworthy, as they aim to create more personalized user experiences. Furthermore, the shift towards agentic recommender systems, which leverage large language models for dynamic user interaction, indicates a trend towards more interactive and responsive recommendation engines. Collectively, these developments signal a move towards more robust, user-centric systems capable of addressing both commercial challenges and evolving user needs.
Papers
1–10 of 14Not All Candidates are Created Equal: A Heterogeneity-Aware Approach to Pre-ranking in Recommender Systems
Most large-scale recommender systems follow a multi-stage cascade of retrieval, pre-ranking, ranking, and re-ranking. A key challenge at the pre-ranking stage arises from the heterogeneity of training...
Bridging Semantic Understanding and Popularity Bias with LLMs
Semantic understanding of popularity bias is a crucial yet underexplored challenge in recommender systems, where popular items are often favored at the expense of niche content. Most existing debiasin...
Rethinking Generative Recommender Tokenizer: Recsys-Native Encoding and Semantic Quantization Beyond LLMs
Semantic ID (SID)-based recommendation is a promising paradigm for scaling sequential recommender systems, but existing methods largely follow a semantic-centric pipeline: item embeddings are learned ...
MMGRid: Navigating Temporal-aware and Cross-domain Generative Recommendation via Model Merging
Model merging (MM) offers an efficient mechanism for integrating multiple specialized models without access to original training data or costly retraining. While MM has demonstrated success in domains...
Talos: Optimizing Top-$K$ Accuracy in Recommender Systems
Recommender systems (RS) aim to retrieve a small set of items that best match individual user preferences. Naturally, RS place primary emphasis on the quality of the Top-$K$ results rather than perfor...
SteerEval: A Framework for Evaluating Steerability with Natural Language Profiles for Recommendation
Natural-language user profiles have recently attracted attention not only for improved interpretability, but also for their potential to make recommender systems more steerable. By enabling direct edi...
Breaking the Curse of Repulsion: Optimistic Distributionally Robust Policy Optimization for Off-Policy Generative Recommendation
Policy-based Reinforcement Learning (RL) has established itself as the dominant paradigm in generative recommendation for optimizing sequential user interactions. However, when applied to offline hist...
WarpRec: Unifying Academic Rigor and Industrial Scale for Responsible, Reproducible, and Efficient Recommendation
Innovation in Recommender Systems is currently impeded by a fractured ecosystem, where researchers must choose between the ease of in-memory experimentation and the costly, complex rewriting required ...
RecNet: Self-Evolving Preference Propagation for Agentic Recommender Systems
Agentic recommender systems leverage Large Language Models (LLMs) to model complex user behaviors and support personalized decision-making. However, existing methods primarily model preference changes...
Guiding the Recommender: Information-Aware Auto-Bidding for Content Promotion
Modern content platforms offer paid promotion to mitigate cold start by allocating exposure via auctions. Our empirical analysis reveals a counterintuitive flaw in this paradigm: while promotion rescu...