483 citations · 4.2k across the 70 of their papers we have counts for
72 papers
ViMax: Agentic Video Generation
Lingxuan Huang, Sizhe He, Hengji Zhou +3
Long-form video generation requires systematic narrative planning and visual consistency that current short-clip methods cannot provide. Existing methods generate isolated sequence…
DramaDirector: Geometry-Guided Short Drama Generation
Hengji Zhou, Sijie Liu, Jianrun Chen +3
Short dramas, with their rapid shot rhythms, dialogue-driven focus shifts, and demanding cinematographic grounding, pose challenges that prompt-level or text-only video generation…
VideoAgent: All-in-One Framework for Video Understanding and Editing
Hengji Zhou, Lingxuan Huang, Jian Wang +4
Video editing has become essential in digital media creation, yet existing automated systems are restricted to short segment processing and domain-specific tasks. They face two cri…
Navigating User Behavior toward Personalized Multimodal Generation
Hengji Zhou, Yufeng Liu, Ye Liu +3
Modern AIGC pipelines deliver high-fidelity images and videos but presuppose a well-formed creation instruction, while end users rarely articulate visual details, leaving generator…
TailorMind: Towards Preference-Aligned Multimodal Content Generation
Hengji Zhou, Ye Liu, Yufeng Liu +3
Personalized content systems depend on available UGC and struggle when suitable content is absent, delayed, or costly to create. Although multimodal generators can synthesize conte…
MR.Rec: Synergizing Memory and Reasoning for Personalized Recommendation Assistant with LLMs
Jiani Huang, Xingchen Zou, Lianghao Xia +1
The application of Large Language Models (LLMs) in recommender systems faces key challenges in delivering deep personalization and intelligent reasoning, especially for interactive…
Adversarial Demonstration Learning for Low-resource NER Using Dual Similarity
Guowen Yuan, Tien-Hsuan Wu, Lianghao Xia +1
We study the problem of named entity recognition (NER) based on demonstration learning in low-resource scenarios. We identify two issues in demonstration construction and model tra…
RecGPT: A Foundation Model for Sequential Recommendation
Yangqin Jiang, Xubin Ren, Lianghao Xia +3
This work addresses a fundamental barrier in recommender systems: the inability to generalize across domains without extensive retraining. Traditional ID-based approaches fail enti…
Pre-training for Recommendation Unlearning
Guoxuan Chen, Lianghao Xia, Chao Huang
Modern recommender systems powered by Graph Neural Networks (GNNs) excel at modeling complex user-item interactions, yet increasingly face scenarios requiring selective forgetting…
AI-Researcher: Autonomous Scientific Innovation
Jiabin Tang, Lianghao Xia, Zhonghang Li +1
The powerful reasoning capabilities of Large Language Models (LLMs) in mathematics and coding, combined with their ability to automate complex tasks through agentic frameworks, pre…
Urban Computing in the Era of Large Language Models
Zhonghang Li, Lianghao Xia, Xubin Ren +4
Urban computing has emerged as a multidisciplinary field that harnesses data-driven technologies to address challenges and improve urban living. Traditional approaches, while benef…
LightGNN: Simple Graph Neural Network for Recommendation
Guoxuan Chen, Lianghao Xia, Chao Huang
Graph neural networks (GNNs) have demonstrated superior performance in collaborative recommendation through their ability to conduct high-order representation smoothing, effectivel…
DiffGraph: Heterogeneous Graph Diffusion Model
Zongwei Li, Lianghao Xia, Hua Hua +3
Recent advances in Graph Neural Networks (GNNs) have revolutionized graph-structured data modeling, yet traditional GNNs struggle with complex heterogeneous structures prevalent in…
MixRec: Heterogeneous Graph Collaborative Filtering
Lianghao Xia, Meiyan Xie, Yong Xu +1
For modern recommender systems, the use of low-dimensional latent representations to embed users and items based on their observed interactions has become commonplace. However, man…
GraphAgent: Agentic Graph Language Assistant
Yuhao Yang, Jiabin Tang, Lianghao Xia +3
Real-world data is represented in both structured (e.g., graph connections) and unstructured (e.g., textual, visual information) formats, encompassing complex relationships that in…
RecLM: Recommendation Instruction Tuning
Yangqin Jiang, Yuhao Yang, Lianghao Xia +3
Modern recommender systems aim to deeply understand users' complex preferences through their past interactions. While deep collaborative filtering approaches using Graph Neural Net…
LightRAG: Simple and Fast Retrieval-Augmented Generation
Zirui Guo, Lianghao Xia, Yanhua Yu +2
Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant respon…
EasyST: A Simple Framework for Spatio-Temporal Prediction
Jiabin Tang, Wei Wei, Lianghao Xia +1
Spatio-temporal prediction is a crucial research area in data-driven urban computing, with implications for transportation, public safety, and environmental monitoring. However, sc…
AnyGraph: Graph Foundation Model in the Wild
Lianghao Xia, Chao Huang
The growing ubiquity of relational data structured as graphs has underscored the need for graph learning models with exceptional generalization capabilities. However, current appro…
DiffMM: Multi-Modal Diffusion Model for Recommendation
Yangqin Jiang, Lianghao Xia, Wei Wei +3
The rise of online multi-modal sharing platforms like TikTok and YouTube has enabled personalized recommender systems to incorporate multiple modalities (such as visual, textual, a…
RecDiff: Diffusion Model for Social Recommendation
Zongwei Li, Lianghao Xia, Chao Huang
Social recommendation has emerged as a powerful approach to enhance personalized recommendations by leveraging the social connections among users, such as following and friend rela…
SelfGNN: Self-Supervised Graph Neural Networks for Sequential Recommendation
Yuxi Liu, Lianghao Xia, Chao Huang
Sequential recommendation effectively addresses information overload by modeling users' temporal and sequential interaction patterns. To overcome the limitations of supervision sig…
FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction
Zhonghang Li, Lianghao Xia, Yong Xu +1
The objective of traffic prediction is to accurately forecast and analyze the dynamics of transportation patterns, considering both space and time. However, the presence of distrib…
A Comprehensive Survey on Self-Supervised Learning for Recommendation
Xubin Ren, Wei Wei, Lianghao Xia +1
Recommender systems play a crucial role in tackling the challenge of information overload by delivering personalized recommendations based on individual user preferences. Deep lear…