1 citations · 1 across the 10 of their papers we have counts for
11 papers
Personalized Task Dependency Graphs for Mitigating Signal Erosion in Multi-Task Recommendation
Fuyuan Liu, Tiandeng Wu, Yaqun Fang +8
Optimizing multiple conversion objectives is a core challenge in industrial recommendation, often limited by signal erosion in rigid architectures. Existing Multi-Task Learning (MT…
Inventory-Grounded Policy-Level Optimization for Training-Free AI Search
Wei Zhou, Tiandeng Wu, Jiandong Ding +2
Early in deployment, an AI search system typically operates over a frequently updated product catalog, so the available items and their properties cannot be treated as stable knowl…
SIDScope: A Diagnostic Resource for Semantic-ID Interfaces in Generative Recommendation
Jiandong Ding, Huijie Qin, Tiandeng Wu +1
Semantic ID tokenizers assign code sequences to catalog items, which generative recommenders predict and resolve back to items. Reusing a released mapping requires checking its cod…
Zero-Observation User Reactivation with Gap-Driven Dimensional Gating
Jiandong Ding, Tianying Liu, Fuyuan Liu +2
Sequential recommendation (SR) models capture continuously observed behavior, but a returning user may have no interactions for months or years. We define this setting as Zero-Obse…
Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
Jiandong Ding, Honglei Ji, Ming Liu +1
A skill can match a task's topic while conflicting with its resource, procedure, or output requirements. We study this as same-capability risk-exposure retrieval and introduce Same…
SIDInspector: A Mapping-First Diagnostic Resource for Semantic-ID Tokenizers
Jiandong Ding, Heng Chang, Huijie Qin +1
Semantic-ID (SID) tokenizers are increasingly reused as standalone artifacts in generative recommendation: an exported item-to-code mapping becomes the address space that a later s…
Beyond the Flat Sequence: Hierarchical and Preference-Aware Generative Recommendations
Zerui Chen, Heng Chang, Tianying Liu +5
Generative Recommenders (GRs), exemplified by the Hierarchical Sequential Transduction Unit (HSTU), have emerged as a powerful paradigm for modeling long user interaction sequences…
Towards Practical Large-scale Dynamical Heterogeneous Graph Embedding: Cold-start Resilient Recommendation
Mabiao Long, Jiaxi Liu, Yufeng Li +5
Deploying dynamic heterogeneous graph embeddings in production faces key challenges of scalability, data freshness, and cold-start. This paper introduces a practical, two-stage sol…
BIS: NL2SQL Service Evaluation Benchmark for Business Intelligence Scenarios
Bora Caglayan, Mingxue Wang, John D. Kelleher +4
NL2SQL (Natural Language to Structured Query Language) transformation has seen wide adoption in Business Intelligence (BI) applications in recent years. However, existing NL2SQL be…
P/D-Serve: Serving Disaggregated Large Language Model at Scale
Yibo Jin, Tao Wang, Huimin Lin +27
Serving disaggregated large language models (LLMs) over tens of thousands of xPU devices (GPUs or NPUs) with reliable performance faces multiple challenges. 1) Ignoring the diversi…
Unified Low-rank Compression Framework for Click-through Rate Prediction
Hao Yu, Minghao Fu, Jiandong Ding +2
Deep Click-Through Rate (CTR) prediction models play an important role in modern industrial recommendation scenarios. However, high memory overhead and computational costs limit th…