Recommendation as Generation: Unifying Personalized Video Generation and Recommendation at Industrial Scale
- URL: http://arxiv.org/abs/2606.25496v1
- Date: Wed, 24 Jun 2026 07:23:20 GMT
- Title: Recommendation as Generation: Unifying Personalized Video Generation and Recommendation at Industrial Scale
- Abstract summary: We propose Recommendation-as-Generation (RaG), a new paradigm that generates personalized videos on demand from inferred user interest.<n>Our framework unifies generative recommendation and video generation through shared semantic IDs (SIDs)<n>We deploy RaG on an industrial-scale platform with over 400 million daily active users and evaluate it in a revenue-critical advertising scenario.
- Score: 39.03125255049368
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Traditional short-video recommendation systems match user interest to a fixed pool of pre-produced videos, which limits their ability to capture fine-grained and dynamic preferences. We propose Recommendation-as-Generation (RaG), a new paradigm that generates personalized videos on demand from inferred user interest. Our framework unifies generative recommendation and video generation through shared semantic IDs (SIDs), which disentangle video representation into content semantics and creative style semantics, enabling both fine-grained modeling of user interest and controllable generation of interest-aligned videos. We further develop Video Generation Agents (VGAs) that are conditioned on inferred SIDs to drive hierarchical planning and refinement for video creation, including visual composition, audio alignment, and artistic effect enhancement. To optimize the framework, we effectively introduce a synergistic cross-domain reward learning mechanism that jointly enforces interest alignment, user feedback, and video quality assessment. We deploy RaG on an industrial-scale platform with over 400 million daily active users and evaluate it in a revenue-critical advertising scenario. Online A/B tests show up to 1.87% ad revenue improvement compared to a strong production GRM baseline, demonstrating its effectiveness in driving further revenue gains beyond generative recommendation. Our results highlight a closed-loop generative system as a promising paradigm for integrating personalized video generation into recommendation.
Related papers
- HGenPush: A Heterogeneous Generative Recommendation Architecture for Industrial Push Notification Systems [19.17988315151231]
We propose an end-to-end heterogeneous generative recommendation architecture called HGenPush.<n>HGenPush simultaneously fulfills users' demands for high-quality content and trusted authors.<n>We have deployed HGenPush on the push notification system of Kuaishou, a large-scale short-video platform, achieving a significant 0.181% increase in daily active users.
arXiv Detail & Related papers (2026-07-03T14:18:19Z) - Inference-based GAN Video Generation [47.53991869205973]
We propose a new type of video generator by enabling adversarial-based unconditional video generators with a variational encoder.<n>Existing models struggle with the temporal scaling of the generated videos.<n>We employ a novel, memory-efficient approach to generate long videos composed of hundreds or thousands of frames.
arXiv Detail & Related papers (2025-12-25T20:14:38Z) - Diverse Video Generation with Determinantal Point Process-Guided Policy Optimization [11.413630896037576]
We introduce DPP-GRPO, a novel framework for diverse video generation.<n>Our framework is plug-and-play and model-agnostic, and encourages diverse generations across visual appearance, camera motions, and scene structure.<n>We show that our method consistently improves video diversity on state-of-the-art benchmarks such as VBench, VideoScore, and human preference studies.
arXiv Detail & Related papers (2025-11-25T18:59:45Z) - Communicative Agents for Slideshow Storytelling Video Generation based on LLMs [4.389263274945811]
Video-Generation-Team (VGTeam) is a novel slide show video generation system designed to redefine the video creation pipeline.<n>By emulating the sequential stages of traditional video production, VGTeam achieves remarkable improvements in both efficiency and scalability.<n>On average, the system generates videos at a cost of only $0.103, with a successful generation rate of 98.4%.
arXiv Detail & Related papers (2025-09-01T09:04:07Z) - Controllable Video Generation: A Survey [72.38313362192784]
We provide a systematic review of controllable video generation, covering both theoretical foundations and recent advances in the field.<n>We begin by introducing the key concepts and commonly used open-source video generation models.<n>We then focus on control mechanisms in video diffusion models, analyzing how different types of conditions can be incorporated into the denoising process to guide generation.
arXiv Detail & Related papers (2025-07-22T06:05:34Z) - Short Video Segment-level User Dynamic Interests Modeling in Personalized Recommendation [23.082810471266235]
Short video growth has necessitated effective recommender systems to match users with content tailored to their evolving preferences.<n>Current video recommendation models primarily treat each video as a whole, overlooking the dynamic nature of user preferences with specific video segments.<n>We propose an innovative model that integrates a hybrid representation module, a multi-modal user-video encoder, and a segment interest decoder.
arXiv Detail & Related papers (2025-04-05T17:45:32Z) - Enhance-A-Video: Better Generated Video for Free [57.620595159855064]
We introduce a training-free approach to enhance the coherence and quality of DiT-based generated videos.<n>Our approach can be easily applied to most DiT-based video generation frameworks without any retraining or fine-tuning.
arXiv Detail & Related papers (2025-02-11T12:22:35Z) - VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos [25.770675590118547]
VideoRAG is the first retrieval-augmented generation framework specifically designed for processing and understanding extremely long-context videos.<n>Our core innovation lies in its dual-channel architecture that seamlessly integrates (i) graph-based textual knowledge grounding for capturing cross-video semantic relationships, and (ii) multi-modal context encoding for efficiently preserving visual features.
arXiv Detail & Related papers (2025-02-03T17:30:19Z) - Improving Video Generation with Human Feedback [105.81833319891537]
We develop a systematic pipeline that harnesses human feedback to mitigate video generation problems.<n>We introduce VideoReward, a multi-dimensional video reward model, and examine how annotations and various design choices impact its rewarding efficacy.
arXiv Detail & Related papers (2025-01-23T18:55:41Z) - Enhancing Sequential Recommender with Large Language Models for Joint Video and Comment Recommendation [77.42486522565295]
We propose a novel recommendation approach called LSVCR to jointly perform personalized video and comment recommendation.<n>Our approach comprises two key components: sequential recommendation (SR) model and supplemental large language model (LLM) recommender.<n>In particular, we attain a cumulative gain of 4.13% in comment watch time.
arXiv Detail & Related papers (2024-03-20T13:14:29Z) - Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion
Latent Aligners [69.70590867769408]
Video and audio content creation serves as the core technique for the movie industry and professional users.
Existing diffusion-based methods tackle video and audio generation separately, which hinders the technique transfer from academia to industry.
In this work, we aim at filling the gap, with a carefully designed optimization-based framework for cross-visual-audio and joint-visual-audio generation.
arXiv Detail & Related papers (2024-02-27T17:57:04Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.