19 papers  /  2023 — 2026

Publications

* co-first author  ·  † corresponding author  ·  Most up-to-date list on Google Scholar

2026

  1. [19] arXiv 2026

    Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics

    Leheng Sheng*, Wenchang Ma*, Ruixin Hong, Xiang Wang, An Zhang, Tat-Seng Chua

    arXiv

  2. [18] arXiv 2026

    Fine-grained Semantics Integration for Large Language Model-based Recommendation

    Jiawei Feng, Xiaoyu Kong, Leheng Sheng, Bin Wu, Chao Yi, Feifang Yang, Xiang-Rong Sheng, Han Zhu, Xiang Wang, Jiancan Wu, Xiangnan He

    arXiv

  3. [17] ICML 2026

    When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning

    Leheng Sheng, Yongtao Zhang, Wenchang Ma, Yaorui Shi, Ting Huang, Xiang Wang, An Zhang, Ke Shen, Tat-Seng Chua

    arXiv

  4. [16] ICLR 2026

    AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint

    Leheng Sheng*, Changshuo Shen*, Weixiang Zhao, Junfeng Fang, Xiaohao Liu, Zhenkai Liang, Xiang Wang, An Zhang, Tat-Seng Chua

    arXiv

  5. [15] ICLR 2026

    AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning

    Yi Zhang, An Zhang, XiuYu Zhang, Leheng Sheng, Yuxin Chen, Zhenkai Liang, Xiang Wang

    arXiv

2025

  1. [14] NeurIPS 2025

    On Reasoning Strength Planning in Large Reasoning Models

    Leheng Sheng, An Zhang, Zijian Wu, Weixiang Zhao, Changshuo Shen, Yi Zhang, Xiang Wang, Tat-Seng Chua

    arXiv

  2. [13] NeurIPS 2025 Spotlight

    AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems

    Yu Shang, Peijie Liu, Yuwei Yan, Zijing Wu, Leheng Sheng, Yuanqing Yu, Chumeng Jiang, An Zhang, Fengli Xu, Yu Wang, Min Zhang, Yong Li

    arXiv

  3. [12] CIKM 2025

    Towards Large Generative Recommendation: A Tokenization Perspective

    Yupeng Hou, An Zhang, Leheng Sheng, Jiancan Wu, Xiang Wang, Tat-Seng Chua, Julian McAuley

    Paper

  4. [11] arXiv 2025

    MiniOneRec: An Open-Source Framework for Scaling Generative Recommendation

    Xiaoyu Kong, Leheng Sheng, Junfei Tan, Yuxin Chen, Jiancan Wu, An Zhang, Xiang Wang, Xiangnan He

    arXiv

  5. [10] arXiv 2025

    MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering

    Chenlu Ding, Jiancan Wu, Leheng Sheng, Fan Zhang, Yancheng Yuan, Xiang Wang, Xiangnan He

    arXiv

  6. [9] WWW 2025 Companion

    Generative Recommendation Models: Progress and Directions

    Yupeng Hou, An Zhang, Leheng Sheng, Zhengyi Yang, Xiang Wang, Tat-Seng Chua, Julian McAuley

    Paper

  7. [8] WWW 2025 Companion

    Personalized Recommendation Agents with Self-Consistency

    Zijing Wu, Leheng Sheng, Yuanlin Xia, Yi Zhang, Yuxin Chen, An Zhang

    Paper

2024

  1. [7] ICLR 2025 Oral

    Language Representations Can Be What Recommenders Need: Findings and Potentials

    Leheng Sheng, An Zhang†, Yi Zhang, Yuxin Chen, Xiang Wang, Tat-Seng Chua

    arXiv Code

  2. [6] NeurIPS 2024

    On Softmax Direct Preference Optimization for Recommendation

    Yuxin Chen, Junfei Tan, An Zhang, Zhengyi Yang, Leheng Sheng, Enzhi Zhang, Xiang Wang, Tat-Seng Chua

    arXiv

  3. [5] NeurIPS 2024

    Customizing Language Models with Instance-wise LoRA for Sequential Recommendation

    Xiaoyu Kong, Jiancan Wu, An Zhang, Leheng Sheng, Hui Lin, Xiang Wang, Xiangnan He

    arXiv

  4. [4] SIGIR 2024

    On Generative Agents in Recommendation

    An Zhang*, Yuxin Chen*, Leheng Sheng*, Xiang Wang†, Tat-Seng Chua

    arXiv Code

  5. [3] WWW 2024

    General Debiasing for Graph-based Collaborative Filtering via Adversarial Graph Dropout

    An Zhang, Wenchang Ma, Pengbo Wei, Leheng Sheng, Xiang Wang

    arXiv

2023

  1. [2] NeurIPS 2023

    Empowering Collaborative Filtering with Principled Adversarial Contrastive Loss

    An Zhang*, Leheng Sheng*, Zhibo Cai†, Xiang Wang, Tat-Seng Chua

    arXiv Code

  2. [1] ICASSP 2023

    BrainNetFormer: Decoding Brain Cognitive States with Spatial-Temporal Cross Attention

    Leheng Sheng, Wehan Wang, Zhiyi Shi, Jichao Zhan, Youyong Kong†

    Paper