338 citations · 454 across the 70 of their papers we have counts for
73 papers
Support Selection Beyond Smooth DAG Exactness: Completion Geometry,Score Margins, and Selective Certificates
Rui Wu, Zongyuan Chen, Hong Xie +2
Smooth acyclicity constraints answer whether a weighted support is a DAG, whereas structure learning asks which support change should be made. Existing analyses establish degenerac…
Rethinking Item Tokenization in Generative Recommenders: From Fixed Atoms to Semantic Subwords
Xinrui Miao, Mingjia Yin, Jiaqing Zhang +5
In generative recommender systems, items are typically tokenized into fixed-length semantic ID sequences for autoregressive next-item prediction. However, for user-context modeling…
SITA: Semantic Interest Tokens for Target-Aware Compression in Long-Sequence Recommendation
Rui Zhou, Bo Chen, Qinglin Jia +5
As user behavior histories continue to grow on modern Internet platforms, effectively modeling long behavior sequences has become crucial for predicting user interests in candidate…
Learning Generated Controls under Fractured Geometry: Projective Residualization and Variation-Allocation Frontiers
Rui Wu, Zongyuan Chen, Hong Xie +2
Many two-stage estimators assess the first-stage learner by prediction error, even when the next stage uses its residual. In control-function instrumental variables, that residual…
Understanding DNNs in Feature Interaction Models: A Dimensional Collapse Perspective
Jiancheng Wang, Mingjia Yin, Hao Wang +1
DNNs have gained widespread adoption in feature interaction recommendation models. However, there has been a longstanding debate on their roles. On one hand, some works claim that…
IE as Cache: Information Extraction Enhanced Agentic Reasoning
Hang Lv, Sheng Liang, Hongchao Gu +5
Information Extraction aims to distill structured, decision-relevant information from unstructured text, serving as a foundation for downstream understanding and reasoning. However…
Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration
Hang Lv, Hongchao Gu, Ruiqing Yang +5
Generative listwise reranking leverages global context for superior retrieval but is plagued by intrinsic position bias, where models exhibit structural sensitivity to input order…
SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility
Xuyang Zhi, Peilun zhou, Chengqiang Lu +10
The evolution of Large Language Models (LLMs) is shifting the focus from single, verifiable tasks toward complex, open-ended real-world scenarios, imposing significant challenges o…
Generative Data Transformation: From Mixed to Unified Data
Jiaqing Zhang, Mingjia Yin, Hao Wang +6
Recommendation model performance is intrinsically tied to the quality, volume, and relevance of their training data. To address common challenges like data sparsity and cold start,…
DIET: Learning to Distill Dataset Continually for Recommender Systems
Jiaqing Zhang, Hao Wang, Mingjia Yin +6
Modern deep recommender models are trained under a continual learning paradigm, relying on massive and continuously growing streaming behavioral logs. In large-scale platforms, ret…
SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized Generation
Hang Lv, Sheng Liang, Hao Wang +6
Realizing personalized intelligence faces a core dilemma: sending user history to centralized large language models raises privacy concerns, while on-device small language models l…
Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillation
Kai Cheng, Hao Wang, Wei Guo +4
Generative models offer a promising paradigm for the final stage reranking in multi-stage recommender systems, with the ability to capture inter-item dependencies within reranked l…
FuXi-Linear: Unleashing the Power of Linear Attention in Long-term Time-aware Sequential Recommendation
Yufei Ye, Wei Guo, Hao Wang +7
Modern recommendation systems primarily rely on attention mechanisms with quadratic complexity, which limits their ability to handle long user sequences and slows down inference. W…
Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance
Wei Yang, Hong Xie, Tao Tan +3
While open sourced Vision-Language Models (VLMs) have proliferated, selecting the optimal pretrained model for a specific downstream task remains challenging. Exhaustive evaluation…
Is Softmax Loss All You Need? A Principled Analysis of Softmax-family Loss
Yuanhao Pu, Defu Lian, Enhong Chen
The Softmax loss is one of the most widely employed surrogate objectives for classification and ranking tasks. To elucidate its theoretical properties, the Fenchel-Young framework…
Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective
Hong Xie, Xiao Hu, Tao Tan +5
The reinforcement fine-tuning area is undergoing an explosion papers largely on optimizing design choices. Though performance gains are often claimed, inconsistent conclusions also…
From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models
Mingjia Yin, Junwei Pan, Hao Wang +5
Click-Through Rate (CTR) prediction, a core task in recommendation systems, aims to estimate the probability of users clicking on items. Existing models predominantly follow a disc…
RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering
Rongyang Zhang, Yuqing Huang, Chengqiang Lu +8
In real-world scenarios, providing user queries with visually enhanced responses can considerably benefit understanding and memory, underscoring the great value of interleaved imag…
A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting
Cheng He, Xijie Liang, Zengrong Zheng +6
Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers. They often e…
Composable Score-based Graph Diffusion Model for Multi-Conditional Molecular Generation
Anjie Qiao, Zhen Wang, Chuan Chen +2
Controllable molecular graph generation is essential for material and drug discovery, where generated molecules must satisfy diverse property constraints. While recent advances in…
LLM Cache Bandit Revisited: Addressing Query Heterogeneity for Cost-Effective LLM Inference
Hantao Yang, Hong Xie, Defu Lian +1
This paper revisits the LLM cache bandit problem, with a special focus on addressing the query heterogeneity for cost-effective LLM inference. Previous works often assume uniform q…
FuXi-β: Towards a Lightweight and Fast Large-Scale Generative Recommendation Model
Yufei Ye, Wei Guo, Hao Wang +7
Scaling laws for autoregressive generative recommenders reveal potential for larger, more versatile systems but mean greater latency and training costs. To accelerate training and…
Efficient Machine Unlearning via Influence Approximation
Jiawei Liu, Chenwang Wu, Defu Lian +1
Due to growing privacy concerns, machine unlearning, which aims at enabling machine learning models to ``forget" specific training data, has received increasing attention. Among ex…
CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering
Hang Lv, Sheng Liang, Hao Wang +6
Personalization has become crucial for adapting models to the diverse and evolving needs of users across cultural, temporal, and contextual dimensions. While existing methods often…