22 citations · 35 across the 32 of their papers we have counts for
28 papers · 1 filter
Astar: Learning to Propose Evolution Directions for Self-Evolving Industrial AI Systems
Jinxin Hu, Hao Deng, Haibo Xing +12
Modern AI systems advance through continuous iteration: a loop of proposing evolution directions, implementing code, training, and evaluation. While the latter three stages are inc…
SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation
Yu Cui, Yi Xu, Jiahao Wang +6
Transformer architectures have achieved remarkable success across diverse domains; however, directly applying their standard self-attention mechanism to recommendation often yields…
EvoRec: Self Evolving Agentic Recommender Systems
Lingyu Mu, Hao Deng, Haibo Xing +3
Optimizing modern recommender systems still relies heavily on engineers iterating by hand, which is slow and bounded by individual expertise. LLM-based agents open a path toward au…
Self-Balancing Gradient Allocation for Heterogeneity-Aware Feature Generation in Click-Through Rate Prediction
Moyu Zhang, Yun Chen, Yujun Jin +3
Generative pre-training via discrete diffusion provides dense reconstruction supervision across all feature fields simultaneously, mitigating representation collapse from data spar…
Counterfactual Multi-task Learning for Delayed Conversion Modeling in E-commerce Sales Pre-Promotion
Xin Song, Kaiyuan Li, Jinxin Hu
Sales promotions, as short-term incentives to stimulate product purchases, play a pivotal role in modern e-commerce marketing strategies. During promotional events, user behavior p…
LWGR: Lagrangian-Constrained Personalized World Knowledge for Generative Recommendation
Lingyu Mu, Hao Deng, Haibo Xing +7
Recent progress in large language model (LLM) based generative recommendation (GR) shows that leveraging LLM world knowledge can substantially improve performance. However, existin…
Rethinking Recommendation Paradigms: From Pipelines to Agentic Recommender Systems
Jinxin Hu, Hao Deng, Lingyu Mu +4
Large-scale industrial recommenders typically use a fixed multi-stage pipeline (recall, ranking, re-ranking) and have progressed from collaborative filtering to deep and large pre-…
AgenticRS-Architecture: System Design for Agentic Recommender Systems
Hao Zhang, Jinxin Hu, Hao Deng +4
AutoModel is an agent based architecture for the full lifecycle of industrial recommender systems. Instead of a fixed recall and ranking pipeline, AutoModel organizes recommendatio…
Deferred is Better: A Framework for Multi-Granularity Deferred Interaction of Heterogeneous Features
Yi Xu, Moyu Zhang, Chaofan Fan +3
Click-through rate (CTR) prediction models estimates the probability of a user-item click by modeling interactions across a vast feature space. A fundamental yet often overlooked c…
Bridging Sequential and Contextual Features with a Dual-View of Fine-grained Core-Behaviors and Global Interest-Distribution
Yi Xu, Chaofan Fan, Moyu Zhang +6
Click-through rate (CTR) prediction tasks typically estimate the probability of a user clicking on a candidate item by modeling both user behavior sequence features and the item's…
Learning to Reflect and Correct: Towards Better Decoding Trajectories for Large-Scale Generative Recommendation
Haibo Xing, Hao Deng, Lingyu Mu +4
Generative Recommendation (GR) has become a promising paradigm for large-scale recommendation systems. However, existing GR models typically perform single-pass decoding without ex…
Masked Diffusion Generative Recommendation
Lingyu Mu, Hao Deng, Haibo Xing +4
Generative recommendation (GR) typically first quantizes continuous item embeddings into multi-level semantic IDs (SIDs), and then generates the next item via autoregressive decodi…
STORE: Semantic Tokenization, Orthogonal Rotation and Efficient Attention for Scaling Up Ranking Models
Yi Xu, Chaofan Fan, Jinxin Hu +3
Ranking models have become an important part of modern personalized recommendation systems. However, significant challenges persist in handling high-cardinality, heterogeneous, and…
Infer As You Train: A Symmetric Paradigm of Masked Generative for Click-Through Rate Prediction
Moyu Zhang, Yujun Jin, Yun Chen +3
Generative models are increasingly being explored in click-through rate (CTR) prediction field to overcome the limitations of the conventional discriminative paradigm, which rely o…
Synergistic Integration and Discrepancy Resolution of Contextualized Knowledge for Personalized Recommendation
Lingyu Mu, Hao Deng, Haibo Xing +7
The integration of large language models (LLMs) into recommendation systems has revealed promising potential through their capacity to extract world knowledge for enhanced reasonin…
Taming the Long Tail: Denoising Collaborative Information for Robust Semantic ID Generation
Yi Xu, Moyu Zhang, Chaofan Fan +5
Item IDs form the backbone of industrial recommender systems, but suffer from representation instability and poor long-tail generalization in large, dynamic item corpora. Semantic…
DGenCTR: Towards a Universal Generative Paradigm for Click-Through Rate Prediction via Discrete Diffusion
Moyu Zhang, Yun Chen, Yujun Jin +2
Recent advances in generative models have inspired the field of recommender systems to explore generative approaches, but most existing research focuses on sequence generation, a p…
MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation
Yi Xu, Moyu Zhang, Chenxuan Li +7
Recommender systems traditionally represent items using unique identifiers (ItemIDs), but this approach struggles with large, dynamic item corpora and sparse long-tail data, limiti…
Global-Distribution Aware Scenario-Specific Variational Representation Learning Framework
Moyu Zhang, Yujun Jin, Jinxin Hu +1
With the emergence of e-commerce, the recommendations provided by commercial platforms must adapt to diverse scenarios to accommodate users' varying shopping preferences. Current m…
Distribution-Guided Auto-Encoder for User Multimodal Interest Cross Fusion
Moyu Zhang, Yongxiang Tang, Yujun Jin +2
Traditional recommendation methods rely on correlating the embedding vectors of item IDs to capture implicit collaborative filtering signals to model the user's interest in the tar…
REG4Rec: Reasoning-Enhanced Generative Model for Large-Scale Recommendation Systems
Haibo Xing, Hao Deng, Yucheng Mao +9
Sequential recommendation aims to predict a user's next action in large-scale recommender systems. While traditional methods often suffer from insufficient information interaction,…
HeterRec: Heterogeneous Information Transformer for Scalable Sequential Recommendation
Hao Deng, Haibo Xing, Kanefumi Matsuyama +8
Transformer-based sequential recommendation (TSR) models have shown superior performance in recommendation systems, where the quality of item representations plays a crucial role.…
CSMF: Cascaded Selective Mask Fine-Tuning for Multi-Objective Embedding-Based Retrieval
Hao Deng, Haibo Xing, Kanefumi Matsuyama +6
Multi-objective embedding-based retrieval (EBR) has become increasingly critical due to the growing complexity of user behaviors and commercial objectives. While traditional approa…
Addressing Information Loss and Interaction Collapse: A Dual Enhanced Attention Framework for Feature Interaction
Yi Xu, Zhiyuan Lu, Xiaochen Li +5
The Transformer has proven to be a significant approach in feature interaction for CTR prediction, achieving considerable success in previous works. However, it also presents poten…