PPaperPicks

Gang Chen

Zhejiang University, Database Laboratory, China

71 papers at tracked venues · 61 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Corpus-Centric Learning for Zero-Shot Table Retrieval
  2. DeepOR: A Deep Reasoning Foundation Model for Optimization Modeling
  3. Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects
  4. FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis
  5. Group-aware Multiscale Ensemble Learning for Test-Time Multimodal Sentiment Analysis
  6. IncreQueryFusion: On-demand Data Fusion Framework in Dynamic Data Lakes
  7. Modeling Concurrency Control as a Learnable Function
  8. NeurBench: A Benchmark Suite for Learned Database Components with Drift Modeling: [Experiments & Analysis]
  9. NeurIDA: Dynamic Modeling for Effective In-Database Analytics
  10. QBridge: Bridging Natural Language and SQL via Gold Query Rewriting with Agentic Refinement
  11. Reinforcement Learning with Verbalized Probabilities for LLM Classification
  12. SVFusion: A CPU-GPU Co-Processing Architecture for Large-Scale Real-Time Vector Search
  13. See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs
  14. Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic Graph
  15. A Comprehensive Study of Shapley Value in Data Analytics
  16. A Demonstration of QueryArtisan: Real-Time Data Lake Analysis via Dynamically Generated Data Manipulation Code
  17. A Survey of Optimization Modeling Meets LLMs: Progress and Future Directions
  18. A Timestep-Adaptive Frequency-Enhancement Framework for Diffusion-based Image Super-Resolution
  19. Adda: Towards Efficient in-Database Feature Generation via LLM-based Agents
  20. Bridging the Semantic Gap Between Text and Table: A Case Study on NL2SQL
  21. CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency
  22. CoLA: Model Collaboration for Log-based Anomaly Detection
  23. CogSQL: A Cognitive Framework for Enhancing Large Language Models in Text-to-SQL Translation
  24. Ensembling Prompting Strategies for Zero-Shot Hierarchical Text Classification with Large Language Models
  25. Exploit Gradient Skewness to Circumvent Byzantine Defenses for Federated Learning
  26. HAKES: Scalable Vector Database for Embedding Search Service
  27. High-Throughput Ingestion for Video Warehouse: Comprehensive Configuration and Effective Exploration
  28. HyperMR: Efficient Hypergraph-enhanced Matrix Storage on Compute-in-Memory Architecture
  29. In-Context Adaptation to Concept Drift for Learned Database Operations
  30. LongTableBench: Benchmarking Long-Context Table Reasoning across Real-World Formats and Domains
  31. Mining Platoon Patterns from Traffic Videos
  32. MorphingDB: A Task-Centric AI-Native DBMS for Model Management and Inference
  33. Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecasting
  34. POLO: An LLM-Powered Project-Level Code Performance Optimization Framework
  35. SafeLoad: Efficient Admission Control Framework for Identifying Memory-Overloading Queries in Cloud Data Warehouses
  36. SeSeMI: Secure Serverless Model Inference on Sensitive Data
  37. SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning
  38. Table as a Modality for Large Language Models
  39. TableCopilot: A Table Assistant Empowered by Natural Language Conditional Table Discovery
  40. Towards Automatic and Efficient Prediction Query Processing in Analytical Database
  41. Towards Robust Incremental Learning Under Ambiguous Supervision
  42. Twisted Twin: A Collaborative and Competitive Memory Management Approach in HTAP Systems
  43. T²DR: A Two-Tier Deficiency-Resistant Framework for Incomplete Multimodal Learning
  44. nlcTables: A Dataset for Marrying Natural Language Conditions with Table Discovery
  45. A Separation and Alignment Framework for Black-Box Domain Adaptation
  46. CARAT: Contrastive Feature Reconstruction and Aggregation for Multi-Modal Multi-Label Emotion Recognition
  47. Chain-of-Experts: When LLMs Meet Complex Operations Research Problems
  48. CoMAL: Contrastive Active Learning for Multi-Label Text Classification
  49. Data Contamination Calibration for Black-box LLMs
  50. Database Native Model Selection: Harnessing Deep Neural Networks in Database Systems
  51. Draft& Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding
  52. Embedding and Gradient Say Wrong: A White-Box Method for Hallucination Detection
  53. Enhancing LLM Reasoning via Vision-Augmented Prompting
  54. Exploring Robustness of GNN against Universal Injection Attack from a Worst-case Perspective
  55. FC: Adaptive Atomic Commit via Failure Detection
  56. FedCTQ: A Federated-Based Framework for Accurate and Efficient Contact Tracing Query
  57. In Situ Neural Relational Schema Matcher
  58. Learning Geometry-Aware Representations for New Intent Discovery
  59. Locating What You Need: Towards Adapting Diffusion Models to OOD Concepts In-the-Wild
  60. On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey
  61. Positive-Unlabeled Learning by Latent Group-Aware Meta Disambiguation
  62. Powering In-Database Dynamic Model Slicing for Structured Data Analytics
  63. Predictive and Near-Optimal Sampling for View Materialization in Video Databases
  64. QueryArtisan: Generating Data Manipulation Codes for Ad-hoc Analysis in Data Lakes
  65. Revisiting CNNs for Trajectory Similarity Learning
  66. Sampling-Resilient Multi-Object Tracking
  67. Targeted Representation Alignment for Open-World Semi-Supervised Learning
  68. Towards Cross-Table Masked Pretraining for Web Data Mining
  69. Unbiased Multi-Label Learning from Crowdsourced Annotations
  70. Variational Hybrid-Attention Framework for Multi-Label Few-Shot Aspect Category Detection
  71. VecAug: Unveiling Camouflaged Frauds with Cohort Augmentation for Enhanced Detection