34 citations · 55 across the 19 of their papers we have counts for
20 papers
Salvation Lies Within: Eliciting Inherent Style Transfer in Step-Distilled Diffusion Models
Shengyin Sun, Yiming Li, Yingzhao Lian +7
Adapting step-distilled text-to-image (T2I) models through post-training incurs additional computational costs and affects native few-step generation behavior. This motivates a com…
Harmful Content Is Not Enough: Continuation Framing Moderates In-Context Emergent Misalignment
Peiyang Liu, Xi Wang, Ziqiang Cui +2
In-context learning (ICL) can induce emergent misalignment (EM), where narrow misaligned examples alter answers to unrelated questions. Existing prompts, however, conflate harmful-…
AdaMTP: An Adaptive Training Paradigm for Multi-Token Prediction
Ziqiang Cui, Han Shi, Bowei He +8
Multi-Token Prediction (MTP) has emerged as an effective paradigm that augments a shared Large Language Model backbone with auxiliary heads, training the model to predict several f…
Looking Farther with Confidence: Uncertainty-Guided Future Learning for Sequential Recommendation
Ziqiang Cui, Xing Tang, Peiyang Liu +4
Sequential recommendation effectively models dynamic user interests but continues to face challenges related to data sparsity. While self-supervised learning has alleviated this is…
Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation
Peiyang Liu, Ziqiang Cui, Xi Wang +2
Iterative Retrieval-Augmented Generation (iRAG) has emerged as a powerful paradigm for answering complex multi-hop questions by progressively retrieving and reasoning over external…
Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation
Peiyang Liu, Qiang Yan, Ziqiang Cui +3
Standard Retrieval-Augmented Generation (RAG) systems predominantly rely on semantic relevance as a proxy for utility. However, this assumption collapses in realistic decision-maki…
Beyong Tokens: Item-aware Attention for LLM-based Recommendation
Xiaokun Zhang, Bowei He, Jiamin Chen +2
Large Language Models (LLMs) have recently gained increasing attention in the field of recommendation. Existing LLM-based methods typically represent items as token sequences, and…
Retrieve-then-Adapt: Retrieval-Augmented Test-Time Adaptation for Sequential Recommendation
Xing Tang, Ziqiang Cui, Jingyang Bin +6
The sequential recommendation (SR) task aims to predict the next item based on users' historical interaction sequences. Typically trained on historical data, SR models often strugg…
Have We Really Understood Collaborative Information? An Empirical Investigation
Xiaokun Zhang, Zhaochun Ren, Bowei He +2
Collaborative information serves as the cornerstone of recommender systems which typically focus on capturing it from user-item interactions to deliver personalized services. Howev…
Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation
Shiwei Li, Xiandi Luo, Haozhao Wang +6
Low-rank adaptation (LoRA) is a parameter-efficient fine-tuning (PEFT) method widely used in large language models (LLMs). LoRA essentially describes the projection of an input spa…
Who Stole Your Data? A Method for Detecting Unauthorized RAG Theft
Peiyang Liu, Ziqiang Cui, Di Liang +1
Retrieval-augmented generation (RAG) enhances Large Language Models (LLMs) by mitigating hallucinations and outdated information issues, yet simultaneously facilitates unauthorized…
Queries Are Not Alone: Clustering Text Embeddings for Video Search
Peyang Liu, Xi Wang, Ziqiang Cui +1
The rapid proliferation of video content across various platforms has highlighted the urgent need for advanced video retrieval systems. Traditional methods, which primarily depend…
BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity
Shiwei Li, Xiandi Luo, Haozhao Wang +6
Low-rank adaptation (LoRA) is a parameter-efficient fine-tuning (PEFT) method widely used in large language models (LLMs). It approximates the update of a pretrained weight matrix…
Less Is More: Elevating RAG via Performance-Driven Context Compression
Ziqiang Cui, Yunpeng Weng, Xing Tang +7
Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for improving the timeliness of knowledge updates and the factual accuracy of large language models. Howeve…
Shapley Value-driven Data Pruning for Recommender Systems
Yansen Zhang, Xiaokun Zhang, Ziqiang Cui +1
Recommender systems often suffer from noisy interactions like accidental clicks or popularity bias. Existing denoising methods typically identify users' intent in their interaction…
Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation
Ziqiang Cui, Yunpeng Weng, Xing Tang +8
Contrastive learning has shown effectiveness in improving sequential recommendation models. However, existing methods still face challenges in generating high-quality contrastive p…
Comprehending Knowledge Graphs with Large Language Models for Recommender Systems
Ziqiang Cui, Yunpeng Weng, Xing Tang +4
In recent years, the introduction of knowledge graphs (KGs) has significantly advanced recommender systems by facilitating the discovery of potential associations between items. Ho…
Rankability-enhanced Revenue Uplift Modeling Framework for Online Marketing
Bowei He, Yunpeng Weng, Xing Tang +5
Uplift modeling has been widely employed in online marketing by predicting the response difference between the treatment and control groups, so as to identify the sensitive individ…
Diffusion-based Contrastive Learning for Sequential Recommendation
Ziqiang Cui, Haolun Wu, Bowei He +2
Contrastive learning has been effectively utilized to enhance the training of sequential recommendation models by leveraging informative self-supervised signals. Most existing appr…
Treatment-Aware Hyperbolic Representation Learning for Causal Effect Estimation with Social Networks
Ziqiang Cui, Xing Tang, Yang Qiao +4
Estimating the individual treatment effect (ITE) from observational data is a crucial research topic that holds significant value across multiple domains. How to identify hidden co…