Peng Yan

Peng Yan

Auto-generated profile, based on publicly available information

Peng Yan

Meituan, Beijing, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 April 2025
Verified
Conference Paper
Open access
YXYiyan Xu
Yiyan Xu
WWWenjie Wang
Wenjie Wang
YZYang Zhang
Yang Zhang
BTBiao Tang
Biao Tang
PYPeng Yan
Peng Yan
XHXiangnan He
Xiangnan He

27 October 2025
Verified
Conference Paper
Open access
DHDisen Hu
Disen Hu
XJXun Jiang
Xun Jiang
Zhe SunZhe Sun
Zhe Sun
HYHao Yang
Hao Yang
CPChong Peng
Chong Peng
XXXing Xu
Xing Xu

14 October 2024
Verified
Conference Paper
Open access
TXTaofeng Xue
Taofeng Xue
ZLZhimin Lin
Zhimin Lin
ZZZijian Zhang
Zijian Zhang
LGLinsen Guo
Linsen Guo
HCHaoru Chen
Haoru Chen
PYPeng Yan
Peng Yan
With the explosive growth of online information, recommender systems have emerged as indispensable tools for navigating the complexities of content generation, discovery and consumption. The RecSys 2024 Challenge, organized by Ekstra Bladet, provides a comprehensive dataset and a robust news recommendation evaluation framework for tackling multifaceted challenges including modeling user preferences based on implicit behavior, accounting for the influence of the news agenda on user interests, and managing the rapid decay of news items. In this paper, we propose a novel Hierarchical User Interest Modeling (HUIM) approach to this challenge, leveraging both long-term invariant interests and short-term rapidly changing interests. Specifically, we utilize the multimodal representations along with the side information of items to distill the long-standing interests from user historical behaviors. By analyzing real-time context and user behavioral path patterns, we identify their fine-grained instant interests. Finally, an interest fusion network is proposed to adaptively fuse the long-term and short-term interests by contrasting the query-aware fine-grained behaviors with query-level cross entropy loss. Our team, BlackPearl, achieved a score of 0.8815 and ranked 2nd place on the final leaderboard.

6 November 2026
Verified
Conference Paper
Open access
KZKangning Zhang
Kangning Zhang
HFHaotian Fang
Haotian Fang
XLXukun Luo
Xukun Luo
HYHao Yin
Hao Yin
YGYang Gao
Yang Gao
YYYong Yu
Yong Yu
Semantic-ID generative recommenders represent each item as a short sequence of discrete semantic tokens and predict the next item by autoregressively generating this token sequence. This paradigm enables a unified generation interface for item IDs, histories, and item text, but it also creates a structured optimization bottleneck during reward-based post-training: when an early semantic token enters the wrong branch of the item-token space, finite rollout groups rarely reach the ground-truth item, so group-relative optimization receives identical zero rewards and produces no useful advantage. We propose Hint-Conditioned Generative Recommendation (\method), a semantic-ID generative recommendation framework that recovers learning signal for such hard training instances. HCGRec diagnoses each instance with checkpoint rollouts and supplies a minimal target-prefix hint only when the current generator cannot reach the correct item. The model then generates the unhinted suffix under the hinted semantic branch, turning zero-reward groups into informative comparisons over item-token completions. Hinting also changes token identity: hinted prefix tokens are oracle-provided item context, while unhinted suffix tokens are sampled generation actions. We therefore introduce hint-aware credit decomposition, using supervised learning to preserve item-semantic and prefix-structure alignment for hinted tokens and GRPO to optimize the sampled suffix. Experiments on sequential recommendation benchmarks show that HCGRec substantially improves over supervised fine-tuning and vanilla reward-based post-training, while reducing zero-advantage training samples from over 70% to below 20%. The code is accessible at https://github.com/WncFht/GRec.