papers

Publications (39)

cs.IR2025

Rec: Towards Large Recommender Models with Reasoning

Runyang You, Yongqi Li, Xinyu Lin +4

Large recommender models have extended LLMs as powerful recommenders via encoding or item generation, and recent breakthroughs in LLM reasoning synchronously motivate the explorati…

cs.IR2025

Diffusion Recommender Model

Wenjie Wang, Yiyan Xu, Fuli Feng +3

Generative models such as Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAEs) are widely utilized to model the generative process of user interactions. Howe…

cs.CL2026

Can Large Language Models Derive New Knowledge? A Dynamic Benchmark for Biological Knowledge Discovery

Chaoqun Yang, Xinyu Lin, Shulin Li +4

Recent advancements in Large Language Model (LLM) agents have demonstrated remarkable potential in automatic knowledge discovery. However, rigorously evaluating an AI's capacity fo…

cs.IR2026

Verifiable Reasoning for LLM-based Generative Recommendation

Xinyu Lin, Hanqing Zeng, Hanchao Yu +8

Reasoning in Large Language Models (LLMs) has recently shown strong potential in enhancing generative recommendation through deep understanding of complex user preference. Existing…

cs.IR2025

Collaboration of Large Language Models and Small Recommendation Models for Device-Cloud Recommendation

Zheqi Lv, Tianyu Zhan, Wenjie Wang +6

Large Language Models (LLMs) for Recommendation (LLM4Rec) is a promising research direction that has demonstrated exceptional performance in this field. However, its inability to c…

cs.IR2026

Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems

Xinyu Lin, Yashar Deldjoo, Sunhao Dai +7

The rapid integration of large language model-based agents into recommender systems has driven a shift from static, ranking-based pipelines toward autonomous and interactive system…

cs.IR2024

A Survey of Generative Search and Recommendation in the Era of Large Language Models

Yongqi Li, Xinyu Lin, Wenjie Wang +6

With the information explosion on the Web, search and recommendation are foundational infrastructures to satisfying users' information needs. As the two sides of the same coin, bot…

cs.CV2016

3D Keypoint Detection Based on Deep Neural Network with Sparse Autoencoder

Xinyu Lin, Ce Zhu, Qian Zhang +1

Researchers have proposed various methods to extract 3D keypoints from the surface of 3D mesh models over the last decades, but most of them are based on geometric methods, which l…

cs.IR2024

The 2nd Workshop on Recommendation with Generative Models

Wenjie Wang, Yang Zhang, Xinyu Lin +7

The rise of generative models has driven significant advancements in recommender systems, leaving unique opportunities for enhancing users' personalized recommendations. This works…

cs.AI2026

FinDeepIndicator: Benchmarking Deep Research Agents in End-to-End Financial Indicator Construction

Chaoqun Yang, Fengbin Zhu, Xinyu Lin +5

Financial indicators are essential tools for transforming raw financial data into interpretable measures for various downstream tasks, such as valuation, risk assessment, and econo…

cs.CV2024

Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancement

Kun Zhou, Xinyu Lin, Wenbo Li +5

Previous low-light image enhancement (LLIE) approaches, while employing frequency decomposition techniques to address the intertwined challenges of low frequency (e.g., illuminatio…

cs.CL2025

Parse Trees Guided LLM Prompt Compression

Wenhao Mao, Chengbin Hou, Tianyu Zhang +3

Offering rich contexts to Large Language Models (LLMs) has shown to boost the performance in various tasks, but the resulting longer prompt would increase the computational cost an…

cs.IR2024

Mitigating Spurious Correlations for Self-supervised Recommendation

Xinyu Lin, Yiyan Xu, Wenjie Wang +2

Recent years have witnessed the great success of self-supervised learning (SSL) in recommendation systems. However, SSL recommender models are likely to suffer from spurious correl…

cs.CV2023

Illumination-insensitive Binary Descriptor for Visual Measurement Based on Local Inter-patch Invariance

Xinyu Lin, Yingjie Zhou, Xun Zhang +2

Binary feature descriptors have been widely used in various visual measurement tasks, particularly those with limited computing resources and storage capacities. Existing binary de…

cs.IR2025

Order-agnostic Identifier for Large Language Model-based Generative Recommendation

Xinyu Lin, Haihan Shi, Wenjie Wang +4

Leveraging Large Language Models (LLMs) for generative recommendation has attracted significant research interest, where item tokenization is a critical step. It involves assigning…

cs.AI2026

Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

Meng Chu, Xuan Billy Zhang, Kevin Qinghong Lin +47

As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment dynamics becomes a central bottleneck. Agents that ma…

cs.IR2026

RecoWorld: Building Simulated Environments for Agentic Recommender Systems

Fei Liu, Xinyu Lin, Hanchao Yu +12

We present RecoWorld, a blueprint for building simulated environments tailored to agentic recommender systems. Such environments give agents a proper training space where they can…

cs.CV2024

A Comprehensive Review of Image Line Segment Detection and Description: Taxonomies, Comparisons, and Challenges

Xinyu Lin, Yingjie Zhou, Yipeng Liu +1

An image line segment is a fundamental low-level visual feature that delineates straight, slender, and uninterrupted portions of objects and scenarios within images. Detection and…

cs.IR2024

Temporally and Distributionally Robust Optimization for Cold-Start Recommendation

Xinyu Lin, Wenjie Wang, Jujia Zhao +3

Collaborative Filtering (CF) recommender models highly depend on user-item interactions to learn CF representations, thus falling short of recommending cold-start items. To address…

cs.IR2025

Learnable Item Tokenization for Generative Recommendation

Wenjie Wang, Honghui Bao, Xinyu Lin +5

Utilizing powerful Large Language Models (LLMs) for generative recommendation has attracted much attention. Nevertheless, a crucial challenge is transforming recommendation data in…

cs.CL2026

TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems

Chen Xu, Yicheng Hu, Ruizi Wang +4

Multi-agent systems (MAS) have emerged as a promising paradigm for solving complex tasks. Recent work has explored self-evolving MAS that automatically optimize agent capabilities…

cs.AI2026

CAPSUL: A Comprehensive Human Protein Benchmark for Subcellular Localization

Yicheng Hu, Xinyu Lin, Shulin Li +3

Subcellular localization is a crucial biological task for drug target identification and function annotation. Although it has been biologically realized that subcellular localizati…

cs.IR2025

EARN: Efficient Inference Acceleration for LLM-based Generative Recommendation by Register Tokens

Chaoqun Yang, Xinyu Lin, Wenjie Wang +4

Large Language Model-based generative recommendation (LLMRec) has achieved notable success, but it suffers from high inference latency due to massive computational overhead and mem…

cs.IR2024

Data-efficient Fine-tuning for LLM-based Recommendation

Xinyu Lin, Wenjie Wang, Yongqi Li +4

Leveraging Large Language Models (LLMs) for recommendation has recently garnered considerable attention, where fine-tuning plays a key role in LLMs' adaptation. However, the cost o…

cs.IR2026

Beyond Action Imitation: Learning a Decision-Aware User Simulator for Online Advertising

Zipeng Chen, Jiaer Zheng, Xiangyang Xu +15

The paper introduces DASH, a decision-aware user simulator that generates reasoning traces and predicts actions for online advertising by integrating heterogeneous cross-domain his…

#user simulation#online advertising#decision-aware modeling#cross-domain context
cs.IR2026

Bringing Reasoning to Generative Recommendation Through the Lens of Cascaded Ranking

Xinyu Lin, Pengyuan Liu, Wenjie Wang +5

Generative Recommendation (GR) has become a promising end-to-end approach with high FLOPS utilization for resource-efficient recommendation. Despite the effectiveness, we show that…

cs.IR2025

Navigating Through Paper Flood: Advancing LLM-based Paper Evaluation through Domain-Aware Retrieval and Latent Reasoning

Wuqiang Zheng, Yiyan Xu, Xinyu Lin +3

With the rapid and continuous increase in academic publications, identifying high-quality research has become an increasingly pressing challenge. While recent methods leveraging La…

cs.AI2024

Node Importance Estimation Leveraging LLMs for Semantic Augmentation in Knowledge Graphs

Xinyu Lin, Tianyu Zhang, Chengbin Hou +3

Node Importance Estimation (NIE) is a task that quantifies the importance of node in a graph. Recent research has investigated to exploit various information from Knowledge Graphs…

cs.CV2024

Fossil Image Identification using Deep Learning Ensembles of Data Augmented Multiviews

Chengbin Hou, Xinyu Lin, Hanhui Huang +4

Identification of fossil species is crucial to evolutionary studies. Recent advances from deep learning have shown promising prospects in fossil image identification. However, the…

cs.CV2023

Level-line Guided Edge Drawing for Robust Line Segment Detection

Xinyu Lin, Yingjie Zhou, Yipeng Liu +1

Line segment detection plays a cornerstone role in computer vision tasks. Among numerous detection methods that have been recently proposed, the ones based on edge drawing attract…

cs.IR2025

Heterogeneous User Modeling for LLM-based Recommendation

Honghui Bao, Wenjie Wang, Xinyu Lin +4

Leveraging Large Language Models (LLMs) for recommendation has demonstrated notable success in various domains, showcasing their potential for open-domain recommendation. A key cha…

cs.IR2025

Efficient Inference for Large Language Model-based Generative Recommendation

Xinyu Lin, Chaoqun Yang, Wenjie Wang +5

Large Language Model (LLM)-based generative recommendation has achieved notable success, yet its practical deployment is costly particularly due to excessive inference latency caus…

cs.IR2024

Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendation

Xinyu Lin, Wenjie Wang, Yongqi Li +3

Harnessing Large Language Models (LLMs) for recommendation is rapidly emerging, which relies on two fundamental steps to bridge the recommendation item space and the language space…

cs.CL2026

AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment

Jianfei Xiao, Xiang Yu, Chengbing Wang +8

As Large Language Models (LLMs) evolve into lifelong AI assistants, LLM personalization has become a critical frontier. However, progress is currently bottlenecked by the absence o…

cs.IR2024

Generative Recommendation: Towards Next-generation Recommender Paradigm

Wenjie Wang, Xinyu Lin, Fuli Feng +2

Recommender systems typically retrieve items from an item corpus for personalized recommendations. However, such a retrieval-based recommender paradigm faces two limitations: 1) th…

cs.CV2022

Learning Modal-Invariant and Temporal-Memory for Video-based Visible-Infrared Person Re-Identification

Xinyu Lin, Jinxing Li, Zeyu Ma +5

Thanks for the cross-modal retrieval techniques, visible-infrared (RGB-IR) person re-identification (Re-ID) is achieved by projecting them into a common space, allowing person Re-I…

cs.LG2025

GBO:AMulti-Granularity Optimization Algorithm via Granular-ball for Continuous Problems

Shuyin Xia, Xinyu Lin, Guan Wang +4

Optimization problems aim to find the optimal solution, which is becoming increasingly complex and difficult to solve. Traditional evolutionary optimization methods always overlook…

cs.CV2018

Mesh Interest Point Detection Based on Geometric Measures and Sparse Refinement

Xinyu Lin, Ce Zhu, Yipeng Liu

Three dimensional (3D) interest point detection plays a fundamental role in 3D computer vision and graphics. In this paper, we introduce a new method for detecting mesh interest po…

cs.IR2023

Causal Disentangled Recommendation Against User Preference Shifts

Wenjie Wang, Xinyu Lin, Liuhui Wang +3

Recommender systems easily face the issue of user preference shifts. User representations will become out-of-date and lead to inappropriate recommendations if user preference has s…