PPaperPicks

Xiangyu Zhao

City University of Hong Kong, Hong Kong

127 papers at tracked venues · 96 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. $L{3}$ C: Leaf-Centric Continuous Codes for Natural Language-Driven Table Discovery
  2. ARCHER: Shooting Straight in Multimodal E-Commerce Search at Alibaba with Progressive Alignment
  3. AdapTime: Enabling Adaptive Temporal Reasoning in Large Language Models
  4. Automated Information Flow Selection for Multi-scenario Multi-task Recommendation
  5. BalanceSFT: Improving LLM Function Calling with Balanced Training Signals and Data Hardness
  6. BlossomRec: Block-level Fused Sparse Attention Mechanism for Sequential Recommendations
  7. Boosting Fine-Grained Urban Flow Inference via Lightweight Architecture and Focalized Optimization
  8. Bridging Personalization and AI: From RAG to Agent
  9. Can LLMs Hear the Dogwhistle?
  10. DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent
  11. Detecting Miscitation on the Scholarly Web through LLM-Augmented Text-Rich Graph Learning
  12. Emotion and Intention Guided Multi-Modal Learning for Sticker Response Selection
  13. Exploring Recommender System Evaluation: A Multi-Modal LLM Agent Framework for A/B Testing
  14. GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks
  15. GeoArena: Evaluating Open-World Geographic Reasoning in Large Vision-Language Models
  16. Improving Interpretability of Cognitive Diagnosis Models with LLM-based Semantic Augmentation
  17. LLM-EDT: Large Language Models Enhanced Cross-domain Sequential Recommendation with Dual-phase Training
  18. Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
  19. Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression
  20. MTA: A Merge-then-Adapt Framework for Personalized Large Language Models
  21. MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search
  22. MultiDx: A Multi-Source Knowledge Integration Framework towards Diagnostic Reasoning
  23. NEZHA: A Zero-sacrifice and Hyperspeed Decoding Architecture for Generative Recommendations
  24. Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval
  25. Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery
  26. ProEchoMem: Enhancing Long Video Understanding via Multi-Trace Probe-Echo Memory
  27. PromptX: A Cognitive Agent Platform with Long-term Memory
  28. Renormalization Group Guided Tensor Network Structure Search
  29. RoSA: Enhancing Parameter-Efficient Fine-Tuning via RoPE-aware Selective Adaptation in Large Language Models
  30. SAGE: Global Semantic Alignment with LLMs for Long-Tail Sequential Recommendation
  31. SEARCH-R: Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator for Multi-hop Question Answering
  32. Select Before Use: On the Importance of Reference Model Selection in Preference Alignment
  33. TORepair: Diffusion-Based Task-Oriented Error Repair Via Differentiable Bi-Level Optimization
  34. Tandem: Riding Together with Large and Small Language Models for Efficient Reasoning
  35. To Search or Not to Search: Aligning the Decision Boundary of Deep Search Agents via Causal Intervention
  36. A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge Graphs
  37. AI4Reading: Chinese Audiobook Interpretation System Based on Multi-Agent Collaboration
  38. AgentIR: 2nd Workshop on Agent-based Information Retrieval
  39. Behavior Modeling Space Reconstruction for E-Commerce Search
  40. Bridge the Domains: Large Language Models Enhanced Cross-domain Sequential Recommendation
  41. Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation
  42. Causality-aware Graph Aggregation Weight Estimator for Popularity Debiasing in Top-K Recommendation
  43. Contextual Attention Modulation: Towards Efficient Multi-Task Adaptation in Large Language Models
  44. DANCE: Resource-Efficient Neural Architecture Search with Data-Aware and Continuous Adaptation
  45. Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning
  46. DimCL: Dimension-Aware Augmentation in Contrastive Learning for Recommendation
  47. ECKGBench: Benchmarking Large Language Models in E-commerce Leveraging Knowledge Graph
  48. Empowering Denoising Sequential Recommendation with Large Language Model Embeddings
  49. Empowering Large Language Model for Sequential Recommendation via Multimodal Embeddings and Semantic IDs
  50. FiRE: Enhancing MLLMs with Fine-Grained Context Learning for Complex Image Retrieval
  51. Flow Matching Based Sequential Recommender Model
  52. GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching
  53. GLINT-RU: Gated Lightweight Intelligent Recurrent Units for Sequential Recommender Systems
  54. Generative Auto-Bidding with Value-Guided Explorations
  55. GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization
  56. Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation
  57. LLM-Powered User Simulator for Recommender System
  58. LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations
  59. LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation
  60. LLMs Trust Humans More, That's a Problem! Unveiling and Mitigating the Authority Bias in Retrieval-Augmented Generation
  61. LSRP: A Leader-Subordinate Retrieval Framework for Privacy-Preserving Cloud-Device Collaboration
  62. Large Language Model Enhanced Recommender Systems: Methods, Applications and Trends
  63. Learning Generalized and Flexible Trajectory Models from Omni-Semantic Supervision
  64. Measure Domain's Gap: A Similar Domain Selection Principle for Multi-Domain Recommendation
  65. MetaLoRA: Tensor-Enhanced Adaptive Low-Rank Fine-Tuning
  66. Mitigating Stereotypes in Text-to-Image Generation: A Novel Perspective of Selective Neural Suppression
  67. Model Merging for Knowledge Editing
  68. Multi-scenario Instance Embedding Learning for Deep Recommender Systems
  69. Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems
  70. NoteLLM-2: Multimodal Large Representation Models for Recommendation
  71. PAnDA: Combating Negative Augmentation via Large Language Models for User Cold-Start Recommendations
  72. POI-Enhancer: An LLM-based Semantic Enhancement Framework for POI Representation Learning
  73. Pre-train, Align, and Disentangle: Empowering Sequential Recommendation with Large Language Models
  74. Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
  75. Prompt Tuning as User Inherent Profile Inference Machine
  76. Put Teacher in Student's Shoes: Cross-Distillation for Ultra-compact Model Compression Framework
  77. SELF: Surrogate-light Feature Selection with Large Language Models in Deep Recommender Systems
  78. SIGMA: Selective Gated Mamba for Sequential Recommendation
  79. SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
  80. STAR-Rec: Making Peace with Length Variance and Pattern Diversity in Sequential Recommendation
  81. SampleLLM: Optimizing Tabular Data Synthesis in Recommendations
  82. Scenario-Wise Rec: A Multi-Scenario Recommendation Benchmark
  83. Stepwise Reasoning Disruption Attack of LLMs
  84. Swarm Intelligence in Geo-Localization: A Multi-Agent Large Vision-Language Model Collaborative Framework
  85. The Elephant in the Room: Exploring the Role of Neutral Words in Language Model Group-Agnostic Debiasing
  86. Towards Propagation-Aware Representation Learning for Supervised Social Media Graph Analytics
  87. Training-free LLM Merging for Multi-task Learning
  88. Trustworthy Knowledge Discovery and Data Mining (TrustKDD)
  89. Twice the Gradient, Twice the Privacy Risk in Federated Learning? A Case Study of Federated Recommendation Systems
  90. UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces
  91. ZeroED: Hybrid Zero-Shot Error Detection Through Large Language Model Reasoning
  92. Adapting Job Recommendations to User Preference Drift with Behavioral-Semantic Fusion Learning
  93. AgentIR: 1st Workshop on Agent-based Information Retrieval
  94. Association of Objects May Engender Stereotypes: Mitigating Association-Engendered Stereotypes in Text-to-Image Generation
  95. Automatic Data Repair: Are We Ready to Deploy?
  96. Bi-Level User Modeling for Deep Recommenders
  97. ControlTraj: Controllable Trajectory Generation with Topology-Constrained Diffusion Model
  98. D3: A Methodological Exploration of Domain Division, Modeling, and Balance in Multi-Domain Recommendations
  99. DNS-Rec: Data-aware Neural Architecture Search for Recommender Systems
  100. Diff-MSR: A Diffusion Model Enhanced Paradigm for Cold-Start Multi-Scenario Recommendation
  101. Does Egalitarian Fairness Lead to Instability? The Fairness Bounds in Stable Federated Learning Under Altruistic Behaviors
  102. ERASE: Benchmarking Feature Selection Methods for Deep Recommender Systems
  103. Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models
  104. Efficient and Robust Regularized Federated Recommendation
  105. Enhancing Length Generalization for Attention Based Knowledge Tracing Models with Linear Biases
  106. G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models
  107. Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification
  108. HierRec: Scenario-Aware Hierarchical Modeling for Multi-scenario Recommendations
  109. KDDC: Knowledge-Driven Disentangled Causal Metric Learning for Pre-Travel Out-of-Town Recommendation
  110. LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation
  111. LLM4MSR: An LLM-Enhanced Paradigm for Multi-Scenario Recommendation
  112. Large Multimodal Model Compression via Iterative Efficient Pruning and Distillation
  113. M3oE: Multi-Domain Multi-Task Mixture-of Experts Recommendation Framework
  114. MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion
  115. Mitigating Hallucinations of Large Language Models in Medical Information Extraction via Contrastive Decoding
  116. Modeling User Retention through Generative Flow Networks
  117. Multi-turn Classroom Dialogue Dataset: Assessing Student Performance from One-on-one Conversations
  118. MultiFS: Automated Multi-Scenario Feature Selection in Deep Recommender Systems
  119. OpenSiteRec: An Open Dataset for Site Recommendation
  120. Optimal Transport Enhanced Cross-City Site Recommendation
  121. SSDRec: Self-Augmented Sequence Denoising for Sequential Recommendation
  122. Scalable Dynamic Embedding Size Search for Streaming Recommendation
  123. Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term Retention
  124. Tensorized Hypergraph Neural Networks
  125. The 2nd Workshop on Recommendation with Generative Models
  126. Unveiling the Bias Impact on Symmetric Moral Consistency of Large Language Models
  127. When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications