PPaperPicks

Hui Xiong

Hong Kong University of Science and Technology

106 papers at tracked venues · 90 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. ARADD: An Automatic Real-World API Discovery and Deployment Framework for AI Guide Service in Baidu Map
  2. AnimAlte: Designing a Multimodal AI-Infused Cartoon Video System to Support Structured Vocabulary Learning for Preschoolers at Home
  3. Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models
  4. Beyond Boundaries: Leveraging Vision Foundation Models for Source-Free Object Detection
  5. Discrete Preference Learning for Personalized Multimodal Generation
  6. Enhancing Conversational Recommender Systems with Tree-Structured Knowledge and Pretrained Language Models
  7. ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection
  8. Explainable Oracle Bone Script Recognition via Multimodal Pictographic Reasoning
  9. GenDis: Generative-Discriminative Dual-View Co-Training for Generalized Category Discovery
  10. Graph Cross-Domain Continual Fine-Tuning via Orthogonal LoRA Routing with Contrastive Expert Specialization
  11. LLM-Oriented Information Retrieval: A Denoising-First Perspective
  12. OccamVTS: Distilling Vision Models to 1% Parameters for Time Series Forecasting
  13. SceneLM: 3D-Aware Language Models for Editable 3D Scene Synthesis
  14. Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning
  15. SiLP: Enhancing Non-Dominant Language Capabilities with a Selective Bidirectional Language Projection Framework
  16. A Survey on Deep Learning based Time Series Analysis with Frequency Transformation
  17. Automatic Instruction Data Selection for Large Language Models via Uncertainty-Aware Influence Maximization
  18. CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency Patching
  19. CitySculpt: 3D City Generation from Satellite Imagery with UV Diffusion
  20. Depth Any Event Stream: Enhancing Event-based Monocular Depth Estimation via Dense-to-Sparse Distillation
  21. Editable Concept Bottleneck Models
  22. Efficient Skill Discovery via Regret-Aware Optimization
  23. Enhancing Long-Tail Bundle Recommendations Utilizing Composition Pattern Modeling
  24. Explaining Length Bias in LLM-Based Preference Evaluations
  25. GCAL: Adapting Graph Models to Evolving Domain Shifts
  26. GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
  27. Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation
  28. Hierarchical Time-Aware Mixture of Experts for Multi-Modal Sequential Recommendation
  29. Instruction Semantics Enhanced Dual-Flow Graph Model for GPU Error Resilience Prediction
  30. Joint Dependency and Conflicting Task Allocation in Collaboration-Aware Spatial Crowdsourcing
  31. LLM-Eraser: Optimizing Large Language Model Unlearning through Selective Pruning
  32. LLM-powered Multi-agent Framework for Goal-oriented Learning in Intelligent Tutoring System
  33. LLMLight: Large Language Models as Traffic Signal Control Agents
  34. Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs
  35. Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding
  36. LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data
  37. MagicCity: Geometry-Aware 3D City Generation from Satellite Imagery with Multi-View Consistency
  38. Multifractal Comparison of Billboard and AI-Generated Music
  39. Multimodal 3D Genome Pre-training
  40. OneForecast: A Universal Framework for Global and Regional Weather Forecasting
  41. Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning
  42. Revisiting Noise Resilience Strategies in Gesture Recognition: Short-Term Enhancement in sEMG Analysis
  43. Robust Explanations of Graph Neural Networks via Graph Curvatures
  44. SAFER: A Calibrated Risk-Aware Multimodal Recommendation Model for Dynamic Treatment Regimes
  45. SCA3D: Enhancing Cross-Modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation
  46. ST$2$360D: Spatial-to-Temporal Consistency for Training-free 360 Monocular Depth Estimation
  47. ScIRGen: Synthesize Realistic and Large-Scale RAG Dataset for Scientific Research
  48. Scalable Pre-Training of Compact Urban Spatio-Temporal Predictive Models on Large-Scale Multi-Domain Data
  49. SciHorizon: Benchmarking AI-for-Science Readiness from Scientific Data to Large Language Models
  50. SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction
  51. See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model
  52. Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding with LLMs
  53. TC-LLaVA: Rethinking the Transfer of LLava from Image to Video Understanding with Temporal Considerations
  54. TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning
  55. Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression Comprehension
  56. The 6th International Workshop on Talent and Management Computing (TMC 2025)
  57. TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
  58. Towards Continuous Reuse of Graph Models via Holistic Memory Diversification
  59. Towards the Causal Complete Cause of Multi-Modal Representation Learning
  60. Unleashing The Power of Pre-Trained Language Models for Irregularly Sampled Time Series
  61. Unleashing the Power of Large Language Model for Denoising Recommendation
  62. Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study
  63. AFDGCF: Adaptive Feature De-correlation Graph Collaborative Filtering for Recommendations
  64. BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction
  65. BigST: Linear Complexity Spatio-Temporal Graph Neural Network for Traffic Forecasting on Large-Scale Road Networks
  66. COMET: NFT Price Prediction with Wallet Profiling
  67. Collaboration-Aware Hybrid Learning for Knowledge Development Prediction
  68. CrossLight: Offline-to-Online Reinforcement Learning for Cross-City Traffic Signal Control
  69. Dynamic Sparse Learning: A Novel Paradigm for Efficient Recommendation
  70. Event Camera Demosaicing via Swin Transformer and Pixel-focus Loss
  71. FlagVNE: A Flexible and Generalizable Reinforcement Learning Framework for Network Resource Allocation
  72. Graph Signal Diffusion Model for Collaborative Filtering
  73. Harnessing Large Language Models for Text-Rich Sequential Recommendation
  74. Hierarchical Structure-Aware Graph Prompting for Drug-Drug Interaction Prediction
  75. Improve Dense Passage Retrieval with Entailment Tuning
  76. Improved Bayes Regret Bounds for Multi-Task Hierarchical Bayesian Bandit Algorithms
  77. Improved Regret Bounds for Non-Convex Online-Within-Online Meta Learning
  78. Improving Gloss-free Sign Language Translation by Reducing Representation Density
  79. Interpretable Cascading Mixture-of-Experts for Urban Traffic Congestion Prediction
  80. Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach
  81. Irregular Traffic Time Series Forecasting Based on Asynchronous Spatio-Temporal Graph Convolutional Networks
  82. Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarking
  83. Killing Two Birds with One Stone: Cross-modal Reinforced Prompting for Graph and Language Tasks
  84. LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay
  85. MIPI 2024 Challenge on Demosaic for Hybridevs Camera: Methods and Results
  86. MIRROR: A Multi-View Reciprocal Recommender System for Online Recruitment
  87. Optimized Cost Per Click in Online Advertising: A Theoretical Analysis
  88. PAIL: Performance based Adversarial Imitation Learning Engine for Carbon Neutral Optimization
  89. Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting
  90. Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs
  91. Pre-DyGAE: Pre-training Enhanced Dynamic Graph Autoencoder for Occupational Skill Demand Forecasting
  92. ReFound: Crafting a Foundation Model for Urban Region Understanding upon Language and Visual Foundations
  93. Refiner: Restructure Retrieved Content Efficiently to Advance Question-Answering Capabilities
  94. Resource-Aware Federated Self-Supervised Learning with Global Class Representations
  95. Scaling Up Multivariate Time Series Pre-Training with Decoupled Spatial-Temporal Representations
  96. Self-Paced Unified Representation Learning for Hierarchical Multi-Label Classification
  97. SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network
  98. Spatio-Temporal Sequence Modeling for Traffic Signal Control
  99. Tabular Data-centric AI: Challenges, Techniques and Future Perspectives
  100. Tackling Uncertain Correspondences for Multi-Modal Entity Alignment
  101. Temporal Graph Contrastive Learning for Sequential Recommendation
  102. The 5th International Workshop on Talent and Management Computing (TMC'2024)
  103. UniINR: Event-Guided Unified Rolling Shutter Correction, Deblurring, and Interpolation
  104. Unifying Graph Retrieval and Prompt Tuning for Graph-Grounded Text Classification
  105. Unleashing the Power of Knowledge Graph for Recommendation via Invariant Learning
  106. Urban Foundation Models: A Survey