Lune

Profiles2020-2026

Shi Han

Microsoft Research

32Papers
0Last author
56Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers32

  1. Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language ModelsAuthor 5 of 7VLDB 2026
  2. SECRET: Towards Scalable and Efficient Code Retrieval via Segmented Deep HashingAuthor 5 of 8ICSE 2025 · 3 citations
  3. TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language ModelsAuthor 6 of 8ACL 2025
  4. Text2Analysis: A Benchmark of Table Question Answering with Advanced Data Analysis and Unclear QueriesAuthor 10 of 12AAAI 2024 · 48 citations
  5. Text-to-Image Generation for Abstract ConceptsAuthor 7 of 8AAAI 2024 · 25 citations
  6. TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model ReasoningAuthor 6 of 7EMNLP Findings 2024 · 18 citations
  7. PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuningAuthor 4 of 5EMNLP Findings 2024 · 6 citations
  8. Scalable Differentiable Causal Discovery in the Presence of Latent Confounders with Skeleton PosteriorAuthor 4 of 8KDD 2024 · 5 citations
  9. Robust Mid-Pass Filtering Graph Convolutional NetworksAuthor 5 of 7WWW 2023 · 57 citations
  10. CoCoSoDa: Effective Contrastive Learning for Code SearchAuthor 6 of 8ICSE 2023 · 45 citations
  11. Homophily-oriented Heterogeneous Graph RewiringAuthor 5 of 9WWW 2023 · 43 citations
  12. Towards Efficient Fine-Tuning of Pre-trained Code Models: An Experimental Study and BeyondAuthor 5 of 7ISSTA 2023 · 37 citations
  13. On Manipulating Signals of User-Item Graph: A Jacobi Polynomial-based Graph Collaborative FilteringAuthor 4 of 8KDD 2023 · 21 citations
  14. Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic ParsingAuthor 7 of 9AAAI 2023 · 9 citations
  15. SheetPT: Spreadsheet Pre-training Based on Hierarchical Attention NetworkAuthor 8 of 9AAAI 2023 · 3 citations
  16. CASR: Generating Complex Sequences with Autoregressive Self-Boost RefinementAuthor 3 of 5ICLR 2023
  17. GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and HeterophilyAuthor 6 of 7WWW 2022 · 155 citations
  18. On the Evaluation of Neural Code SummarizationAuthor 5 of 8ICSE 2022 · 76 citations
  19. RACE: Retrieval-augmented Commit Message GenerationAuthor 6 of 8EMNLP 2022 · 36 citations
  20. PLOG: Table-to-Logic Pretraining for Logical Table-to-Text GenerationAuthor 4 of 5EMNLP 2022 · 15 citations
  21. TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular DataAuthor 5 of 6EMNLP 2022 · 15 citations
  22. Neuron with Steady Response Leads to Better GeneralizationAuthor 6 of 7NeurIPS 2022 · 5 citations
  23. pureGAM: Learning an Inherently Pure Additive ModelAuthor 4 of 5KDD 2022 · 4 citations
  24. FORTAP: Using Formulas for Numerical-Reasoning-Aware Table PretrainingAuthor 5 of 7ACL 2022
  25. HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language GenerationAuthor 7 of 10ACL 2022
  26. TUTA: Tree-based Transformers for Generally Structured Table Pre-trainingAuthor 6 of 7KDD 2021 · 88 citations
  27. TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular DataAuthor 7 of 8KDD 2021 · 58 citations
  28. CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax TreesAuthor 5 of 7EMNLP 2021 · 42 citations
  29. MetaInsight: Automatic Discovery of Structured Knowledge for Exploratory Data AnalysisAuthor 3 of 4SIGMOD 2021 · 35 citations
  30. Semantic table structure identification in spreadsheetsAuthor 5 of 8ISSTA 2021 · 11 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines