A visual tokenizer supporting both understanding and reconstruction is the fundamental cornerstone for Unified Multimodal Models (UMMs). Recent works typically decouple the visual tokenizer from Vision-Language Models (VLMs) to optimize it for both tasks. However, the resulting tokenizer fails to support plug-and-play...
Jian Jia, An-Ran Ding, Bao-Wei Jiang et al.· Proceedings of the 34th ACM...· 0 citations
Recommender systems, which retrieve items of interest to users based on their interaction histories, have recently witnessed several key technological advancements, benefiting from the semantic representation space and model-data scaling. Nevertheless, practitioners and researchers have frequently encountered critical...
Chen-Xu Li, Shu-Chang Liu, Han-Tao Shu et al.· 0 citations
Recent advances in text-to-video generation have enabled high-fidelity single-shot synthesis, yet practical storytelling creation requires multi-shot videos with both strong inter-shot consistency and fine-grained controllability. Existing multi-shot video generation approaches achieve strong consistency but still fall...
Ying-Shuang Zou, Xiao-Yu Shi, Ya-Wen Luo et al.· 1 citation
Traditional cascaded recommender systems balance accuracy and efficiency over large item spaces, but misaligned stage-wise objectives hinder end-to-end optimization. Generative recommendation unifies these stages in an autoregressive framework, providing a natural interface for reinforcement learning (RL) to optimize t...
Peng-Fei Zheng, Wu-Chao Li, Shi-Yao Wang et al.· 0 citations
MoETok is introduced, a 1D visual tokenizer that routes tokens through sparsely activated experts that combines competitive visual understanding with state-of-the-art generation among unified discrete models, matching or surpassing diffusion-based models such as BAGEL and Qwen-Image on benchmarks.
Jia-Hao Guo, Bao Tang, Hao-Xiang Cao et al.· 0 citations
TrajCFG is introduced, a training-free method for flow-matching models that adapts token-wise guidance using historical changes in guided velocity direction, and results support historical directional feedback as a broadly applicable signal for fine-grained guidance allocation.
Jing-Yu Liu, Hao Jiang, Yi-Kang Ding et al.· 0 citations
List Composer is introduced, a decoupled module that transforms pointwise candidate pools into deliverable exposure lists within generative recommender systems within generative recommender systems, and achieves consistent improvements in recommendation quality and serving efficiency.
Zhe-Li Zhou, Si-Thanh Dong, Wei-Wen Liu et al.· Proceedings of the 35th 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
This work proposes Promise, a novel framework that integrates dense, step-by-step verification into generative models, and unlocks Test-Time Scaling Laws in recommender systems, demonstrating that by increasing inference compute, smaller models can match or surpass larger models.
Cheng-Cheng Guo, Kuo Cai, Yu Zhou et al.· Proceedings of the 20th ACM...· 2 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 Promise, a novel framework that integrates dense, step-by-step verification into generative models, and unlocks Test-Time Scaling Laws in recommender systems, demonstrating that by increasing inference compute, smaller models can match or surpass larger models.
Cheng-Cheng Guo, Kuo Cai, Yu Zhou et al.· Proceedings of the 20th ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.