CJ
Clark Mingxuan Ju
cs.LGcs.IRcs.AIcs.CL5-alpha-reductase inhibitoralpha-blockerArtificial IntelligenceBPHcs.CRcs.CV
On Valency
published · living versionsW_j2scmu6v·v1 · currentpublished
Forging More Tasks into Better Harnesses: Agentic Harness Evolution via Successive Scale Racing
with Jingzhe Liu, Jiliang Tang, Tong Zhao, Neil Shah
1 version
Preprints & journals
45 papers in the corpus · 2019–2026Forging More Tasks into Better Harnesses: Agentic Harness Evolution via Successive Scale Racing2610.28815v1 · Jingzhe Liu, Jiliang Tang, Tong Zhao et al.2026 · 0 citationsarXivon Valency
LLM-based User-Product Relevance Evaluation for Dynamic Product Advertising2610.14550v1 · Wen Zhang, Xiao Bai, Hsiang-wei Chao et al.2026 · 0 citationsarXiv
LLM-Based Generative Retrieval for Snapchat Content Recommendation2607.28895v4 · Liam Collins, Jiwen Ren, Donald Loveland et al.2026 · 0 citationsarXiv
Beyond Fixed Depths and Widths: Optimizing Textual Decoding Tries in LLM-based Generative Recommendation2607.16633v1 · Jingzhe Liu, Hanbing Wang, Jiliang Tang et al.2026 · 0 citationsarXiv
On the Memorization Behavior of LLMs in Generative Recommendation: Observations, Implications, and Training Strategies2606.17276v3 · Sunwoo Kim, Sunkyung Lee, Clark Mingxuan Ju et al.2026 · 0 citationsarXiv
Self-supervised User Profile Generation for Personalization2606.05336v1 · Clark Mingxuan Ju, Yuwei Qiu, Tong Zhao et al.2026 · 0 citationsarXiv
MLPs are Efficient Distilled Generative Recommenders2605.12617v1 · Zitian Guo, Yupeng Hou, Clark Mingxuan Ju et al.2026 · 0 citationsarXiv
Expressiveness Limits of Autoregressive Semantic ID Generation in Generative Recommendation2605.06331v1 · Yupeng Hou, Haven Kim, Clark Mingxuan Ju et al.2026 · 0 citationsarXiv
Semantic IDs for Recommender Systems at Snapchat: Use Cases, Technical Challenges, and Design Choices2604.03949v1 · Clark Mingxuan Ju, Tong Zhao, Leonardo Neves et al.2026 · 0 citationsarXiv
FlexRec: Adapting LLM-based Recommenders for Flexible Needs via Reinforcement Learning2603.11901v1 · Yijun Pan, Weikang Qiu, Qiyao Ma et al.2026 · 0 citationsarXiv
Plain Transformers are Surprisingly Powerful Link Predictors2602.01553v4 · Quang Truong, Yu Song, Donald Loveland et al.2026 · 0 citationsarXiv
Threshold Differential Attention for Sink-Free, Ultra-Sparse, and Non-Dispersive Language Modeling2601.12145v3 · Xingyue Huang, Xueying Ding, Mingxuan Ju et al.2026 · 0 citationsACL 2026
Exploiting ID-Text Complementarity via Ensembling for Sequential Recommendation2512.17820v2 · Liam Collins, Bhuvesh Kumar, Clark Mingxuan Ju et al.2025 · 0 citationsarXiv
Hierarchical Token Prepending: Enhancing Information Flow in Decoder-based LLM Embeddings2511.14868v1 · Xueying Ding, Xingyue Huang, Mingxuan Ju et al.2025 · 0 citationsarXiv
Understanding Generative Recommendation with Semantic IDs from a Model-scaling View2509.25522v3 · Jingzhe Liu, Liam Collins, Jiliang Tang et al.2025 · 0 citationsarXiv
Generative Recommendation with Semantic IDs: A Practitioner's Handbook2507.22224v1 · Clark Mingxuan Ju, Liam Collins, Leonardo Neves et al.2025 · 15 citationsarXiv
A Pre-training Framework for Relational Data with Information-theoretic Principles2507.09837v2 · Quang Truong, Zhikai Chen, Mingxuan Ju et al.2025 · 0 citationsarXiv
Non-parametric Graph Convolution for Re-ranking in Recommendation Systems2507.09969v1 · Zhongyu Ouyang, Mingxuan Ju, Soroush Vosoughi et al.2025 · 0 citationsarXiv
Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning2506.05826v1 · Ngoc Bui, Menglin Yang, Runjin Chen et al.2025 · 0 citationsarXiv
Revisiting Self-attention for Cross-domain Sequential Recommendation2505.21811v1 · Clark Mingxuan Ju, Leonardo Neves, Bhuvesh Kumar et al.2025 · 7 citationsarXiv
On the Role of Weight Decay in Collaborative Filtering: A Popularity Perspective2505.11318v2 · Donald Loveland, Mingxuan Ju, Tong Zhao et al.2025 · 2 citationsarXiv
Learning Universal User Representations Leveraging Cross-domain User Intent at Snapchat2504.21838v2 · Clark Mingxuan Ju, Leonardo Neves, Bhuvesh Kumar et al.2025 · 5 citationsarXiv
Heuristic Methods are Good Teachers to Distill MLPs for Graph Link Prediction2504.06193v3 · Zongyue Qin, Shichang Zhang, Mingxuan Ju et al.2025 · 0 citationsarXiv
Beyond Unimodal Boundaries: Generative Recommendation with Multimodal Semantics2503.23333v1 · Jing Zhu, Mingxuan Ju, Yozen Liu et al.2025 · 0 citationsarXiv
Enhancing Item Tokenization for Generative Recommendation through Self-Improvement2412.17171v1 · Runjin Chen, Mingxuan Ju, Ngoc Bui et al.2024 · 0 citationsarXiv
MOPI-HFRS: A Multi-objective Personalized Health-aware Food Recommendation System with LLM-enhanced Interpretation2412.08847v1 · Zheyuan Zhang, Zehong Wang, Tianyi Ma et al.2024 · 16 citationsarXiv
One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs2412.00315v2 · Jingzhe Liu, Haitao Mao, Zhikai Chen et al.2024 · 0 citationsarXiv
Breaking Information Cocoons: A Hyperbolic Framework for Balancing Exploration and Exploitation in Recommender Systems2411.13865v4 · Qiyao Ma, Menglin Yang, Mingxuan Ju et al.2024 · 0 citationsarXiv
Understanding and Scaling Collaborative Filtering Optimization from the Perspective of Matrix Rank2410.23300v3 · Donald Loveland, Xinyi Wu, Tong Zhao et al.2024 · 4 citationsarXiv
Robust Training Objectives Improve Embedding-based Retrieval in Industrial Recommendation Systems2409.14682v1 · Matthew Kolodner, Mingxuan Ju, Zihao Fan et al.2024 · 0 citationsarXiv
Improving Out-of-Vocabulary Handling in Recommendation Systems2403.18280v1 · William Shiao, Mingxuan Ju, Zhichun Guo et al.2024 · 1 citationarXiv
How Does Message Passing Improve Collaborative Filtering?2404.08660v2 · Mingxuan Ju, William Shiao, Zhichun Guo et al.2024 · 2 citationsarXiv
GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation2310.00800v1 · Mingxuan Ju, Tong Zhao, Wenhao Yu et al.2023 · 10 citationsarXiv
Exploring Contrast Consistency of Open-Domain Question Answering Systems on Minimally Edited Questions2305.14441v1 · Zhihan Zhang, Wenhao Yu, Zheng Ning et al.2023 · 2 citationsarXiv
Development of a machine learning-based predictive model for prediction of success or failure of medical management for benign prostatic hyperplasia.36826466 · Pham, Kyle, Ray, Al W, Fernstrum, Austin J et al.2023 · 3 citationsNeurourology and urodynamics. 2023;42(4):707-717
Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement Learning2211.10782v2 · Mingxuan Ju, Yujie Fan, Chuxu Zhang et al.2022 · 45 citationsarXiv
Self-Supervised Graph Structure Refinement for Graph Neural Networks2211.06545v4 · Jianan Zhao, Qianlong Wen, Mingxuan Ju et al.2022 · 28 citationsarXiv
Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering2210.02933v2 · Mingxuan Ju, Wenhao Yu, Tong Zhao et al.2022 · 21 citationsarXiv
Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization2210.02016v3 · Mingxuan Ju, Tong Zhao, Qianlong Wen et al.2022 · 7 citationsarXiv
Generate rather than Retrieve: Large Language Models are Strong Context Generators2209.10063v3 · Wenhao Yu, Dan Iter, Shuohang Wang et al.2022 · 95 citationsarXiv
Black-box Node Injection Attack for Graph Neural Networks2202.09389v1 · Mingxuan Ju, Yujie Fan, Yanfang Ye et al.2022 · 6 citationsarXiv
Adaptive Kernel Graph Neural Network2112.04575v1 · Mingxuan Ju, Shifu Hou, Yujie Fan et al.2021 · 22 citationsarXiv
Heterogeneous Temporal Graph Neural Network2110.13889v1 · Yujie Fan, Mingxuan Ju, Chuxu Zhang et al.2021 · 64 citationsarXiv
α-Satellite: An AI-Driven System and Benchmark Datasets for Dynamic COVID-19 Risk Assessment in the United States.32750960 · Ye, Yanfang, Hou, Shifu, Fan, Yujie et al.2020 · 55 citationsIEEE journal of biomedical and health informatics. 2020;24(10):2755-2764
Development and Validation of a Machine Learning Algorithm for Predicting Response to Anticholinergic Medications for Overactive Bladder Syndrome.31599833 · Sheyn, David, Ju, Mingxuan, Zhang, Sixiao et al.2020 · 25 citationsObstetrics and gynecology. 2019;134(5):946-957
Career total: 63 works. 45 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.