Sequential recommendation aims to model users' evolving preferences from their historical interactions. Recent latent reasoning methods improve sequential recommenders by extending inferencetime computation in continuous representation space, refining user representations without generating explicit reasoning text. How...
Minxuan Shan, Shu-Xian Bi, Zi-Ye Zhang et al.· Proceedings of the 35th ACM...· 1 citation
Algorithm-driven services, including search, recommendation, and advertising, rely on multi-stage model pipelines. While research prioritizes model optimization, post-deployment monitoring focuses on operational reliability. Yet operationally healthy systems may still produce poor-quality results, exposing a gap in exi...
Wen-Yi Xu, Ren-Zhe Zhou, Song-Yang Li et al.· 0 citations
Addressing the User-Oriented Fairness (UOF) issue is a critical challenge in recommender systems (e.g., short-video platforms), as models tend to generate lower-fidelity embeddings for users with sparse signals. Many existing approaches simplify this issue using a binary advantaged/disadvantaged dichotomy. In terms of...
Chen Qin, Xin Wang, Han-Tao Shu et al.· Proceedings of the 34th ACM...· 0 citations
GloRank (Global Action Space Ranker), a generative framework that represents items as sequences of discrete tokens and reformulate reranking as a token generation task, and effectively decouples the scoring mechanism from the order of variable inputs, ensuring that items are evaluated against a consistent global standa...
Peng-Yue Jia, Xiao-Bei Wang, Yingyi Zhang et al.· Proceedings of the 35th ACM...· 0 citations
Sequential recommendation aims to model users' evolving preferences from their historical interactions. Recent latent reasoning methods improve sequential recommenders by extending inferencetime computation in continuous representation space, refining user representations without generating explicit reasoning text. How...
Minxuan Shan, Shu-Xian Bi, Zi-Ye Zhang et al.· 1 citation
Reranking is instrumental in multi-stage recommender systems as it produces the target sequence of items exposed to users. Generative models have shown promise in this field recently, surpassing traditional discriminative paradigms. However, current methods generally follow an item-level generation manner. They either...
Hui-Ying Hu, Xin-Lang Yue, Mu-Yang Li et al.· Proceedings of the 35th ACM...· 0 citations
As a critical stage in the modern multi-stage recommendation pipeline, list-wise reranking determines the final exposed item sequence and directly shapes the user experience by modeling complex dependencies among candidate items within a list. Existing methods typically formulate this task as selecting indices from the...
Peng-Yue Jia, Xiao-Bei Wang, Yingyi Zhang et al.· Proceedings of the 35th ACM...· 0 citations
A series of models are explored that connect item Semantic IDs with natural language in a unified representation space and seek to unlock the potential of natural-language chain-of-thought (CoT) reasoning for recommendation, including OneReason.
This work proposes SCRec, a general framework that enhances cross-stage coherence through bidirectional information supplementation and aligns semantic and collaborative signals and enhances cross-stage information coherence, with minimal additional training and inference costs.
Jia-Yi Dan, Wei-Jian Li, Yong-Qi Liu et al.· Proceedings of the 20th ACM...· 0 citations
This work proposes OGR, an end-to-end framework that directly generates ordered slates-"Once Generated, Ranked" and proposes SPA, a reward-guided conservative policy optimization method that aligns generated slates with user preferences beyond likelihood imitation.
CineForge is introduced, a self-evolving video-production agent framework that couples CineForge-Produce for video generation with CineForge-Evolve for cross-story policy evolution, and CineForge-Evolve applies Case-to-Pattern-to-Policy Evolution to review trajectory evidence, consolidate recurrent findings into bounde...
Jun-Xiang Liu, Lin Wang, Haitian Shi et al.· 0 citations
SWIM (Step-Wise Integrated Measure), a list-level evaluator that models user behaviors as a finite-horizon prefix session-level survival process, and efficiently estimates continuation probabilities and utilities in parallel, satisfying strict industrial latency constraints.
Yuan Pu, Cheng-Hao Zhang, Chao Feng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.