41 citations · 108 across the 26 of their papers we have counts for
20 papers · 1 filter
Optimizing VLP-aligned Multimodal Intent Representation with Correct Visual Instantiation for Zero-Shot Composed Image Retrieval
Xuri Ge, Chunhao Wang, Junchen Fu +7
ZS-CIR aims to retrieve a target image from a reference image and a modification text without paired supervision, typically by encoding composed queries as text-dominant representa…
What Makes a Good Semantic ID for Generative Recommendation? A Reproducibility Study
Yufei Chen, Junchen Fu, Jujia Zhao +2
Generative recommendation has emerged as an active research direction, where items are commonly represented by semantic IDs (SIDs): discrete codes generated token by token. Despite…
Recommender System as Slow and Fast Thinkers
Zichen Yuan, Xiaoxuan Dong, Linkun Dai +8
Sequential recommendation models are foundational to modern personalized services, yet their effectiveness varies substantially across heterogeneous user environments. In particula…
Risk-Aware Reranking for Agentic Tool Retrieval
Qinfei Li, Xiaoxuan Dong, Jin Zhang +6
Tool retrieval determines which external tools are exposed to an LLM agent for a user query or task, making retrieval a critical pre-execution safety boundary. Unlike document retr…
Role of Personality in Conversational Information Seeking
Abdisalam Abukar, Junchen Fu, Chengli Zhai +1
Large language models (LLMs) are increasingly used for information seeking, where users find, compare, and evaluate information through dialogue. In this role, the assistant does m…
RecRec: Latent Interests Recursive Reasoning for Sequential Recommendation
Wenhao Deng, Junchen Fu, Hanwen Du +6
Sequential recommender systems rely on a single forward pass to encode user interaction histories and predict the next item. Increasing inference-time computation through latent re…
Stream-aware Side Adaptation for Large Pre-trained Multimodal Embedding Models in Sequential Recommendation
Junchen Fu, Kaiwen Zheng, Ioannis Arapakis +4
Recently, large pretrained multimodal embedding models such as Qwen3-VL Embedding have shown strong promise for sequential recommendation, as they provide reusable semantic item re…
The 2nd EReL@MIR Workshop on Efficient Representation Learning for Multimodal Information Retrieval
Junchen Fu, Xuri Ge, Xin Xin +6
Multimodal representation learning has attracted increasing attention in AI, driven by the strong performance of large, pretrained multimodal foundation models such as Qwen, LLaVA,…
Differentiable Semantic ID for Generative Recommendation
Junchen Fu, Xuri Ge, Alexandros Karatzoglou +4
Generative recommendation provides a novel paradigm in which each item is represented by a discrete semantic ID (SID) learned from rich content. Most existing methods treat SIDs as…
Are Multimodal Embeddings Truly Beneficial for Recommendation? A Deep Dive into Whole vs. Individual Modalities
Yu Ye, Junchen Fu, Yu Song +2
Multimodal recommendation has emerged as a mainstream paradigm, typically leveraging text and visual embeddings extracted from pre-trained models such as Sentence-BERT, Vision Tran…
The 1st EReL@MIR Workshop on Efficient Representation Learning for Multimodal Information Retrieval
Junchen Fu, Xuri Ge, Xin Xin +5
Multimodal representation learning has garnered significant attention in the AI community, largely due to the success of large pre-trained multimodal foundation models like LLaMA,…
Teach Me How to Denoise: A Universal Framework for Denoising Multi-modal Recommender Systems via Guided Calibration
Hongji Li, Hanwen Du, Youhua Li +5
The surge in multimedia content has led to the development of Multi-Modal Recommender Systems (MMRecs), which use diverse modalities such as text, images, videos, and audio for mor…
CROSSAN: Towards Efficient and Effective Adaptation of Multiple Multimodal Foundation Models for Sequential Recommendation
Junchen Fu, Yongxin Ni, Joemon M. Jose +4
In this paper, we explore a less-studied yet practically important problem: how to efficiently and effectively adapt multiple (2) multimodal foundation models (MFMs) for the seq…
Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendation
Junchen Fu, Xuri Ge, Xin Xin +5
Multimodal foundation models (MFMs) have revolutionized sequential recommender systems through advanced representation learning. While Parameter-efficient Fine-tuning (PEFT) is com…
IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFT
Junchen Fu, Xuri Ge, Xin Xin +4
Multimodal foundation models are transformative in sequential recommender systems, leveraging powerful representation learning capabilities. While Parameter-efficient Fine-tuning (…
An Empirical Study of Training ID-Agnostic Multi-modal Sequential Recommenders
Youhua Li, Hanwen Du, Yongxin Ni +4
Sequential Recommendation (SR) aims to predict future user-item interactions based on historical interactions. While many SR approaches concentrate on user IDs and item IDs, the hu…
A Content-Driven Micro-Video Recommendation Dataset at Scale
Yongxin Ni, Yu Cheng, Xiangyan Liu +5
Micro-videos have recently gained immense popularity, sparking critical research in micro-video recommendation with significant implications for the entertainment, advertising, and…
NineRec: A Benchmark Dataset Suite for Evaluating Transferable Recommendation
Jiaqi Zhang, Yu Cheng, Yongxin Ni +6
Large foundational models, through upstream pre-training and downstream fine-tuning, have achieved immense success in the broad AI community due to improved model performance and s…
Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisited
Zheng Yuan, Fajie Yuan, Yu Song +5
Recommendation models that utilize unique identities (IDs) to represent distinct users and items have been state-of-the-art (SOTA) and dominated the recommender systems (RS) litera…
Exploring Adapter-based Transfer Learning for Recommender Systems: Empirical Studies and Practical Insights
Junchen Fu, Fajie Yuan, Yu Song +6
Adapters, a plug-in neural network module with some tunable parameters, have emerged as a parameter-efficient transfer learning technique for adapting pre-trained models to downstr…