Shi Han

Jupiter: Enhancing LLM Data Analysis Capabilities via Notebook and Inference-Time Value-Guided Search AAAI 2026 Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning ACL 2026 SheetBrain: A Neuro-Symbolic Agent for Accurate Reasoning over Complex and Large Spreadsheets AAAI 2026 Learning Identifiable Structures Helps Avoid Bias in DNN-based Supervised Causal Learning AISTATS 2025 SheetDesigner: MLLM-Powered Spreadsheet Layout Generation with Rule-Based and Vision-Based Reflection EMNLP 2025 Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Fine-tuning EMNLP 2025 TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Models ACL 2025 TablePilot: Recommending Human-Preferred Tabular Data Analysis with Large Language Models ACL 2025 TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers’ Guidance EMNLP 2025 CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing EMNLP 2024 Encoding Spreadsheets for Large Language Models EMNLP 2024 KET-QA: A Dataset for Knowledge Enhanced Table Question Answering COLING 2024 PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning EMNLP 2024 TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning EMNLP 2024 Text2Analysis: A Benchmark of Table Question Answering with Advanced Data Analysis and Unclear Queries AAAI 2024 Text-to-Image Generation for Abstract Concepts AAAI 2024 Vision Language Models for Spreadsheet Understanding: Challenges and Opportunities ACL 2024 AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Tasks ACL 2023 CASR: Generating Complex Sequences with Autoregressive Self-Boost Refinement ICLR 2023 Causal-Based Supervision of Attention in Graph Neural Network: A Better and Simpler Choice towards Powerful Attention IJCAI 2023 HermEs: Interactive Spreadsheet Formula Prediction via Hierarchical Formulet Expansion ACL 2023 InsightPilot: An LLM-Empowered Automated Data Exploration System EMNLP 2023 Out-of-Distribution Detection based on In-Distribution Data Patterns Memorization with Modern Hopfield Energy ICLR 2023 SheetPT: Spreadsheet Pre-training Based on Hierarchical Attention Network AAAI 2023 Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing AAAI 2023 Accelerating Code Search with Deep Hashing and Code Classification ACL 2022 FormLM: Recommending Creation Ideas for Online Forms by Modelling Semantic and Structural Information EMNLP 2022 FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining ACL 2022 HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation ACL 2022 Neuron with Steady Response Leads to Better Generalization NeurIPS 2022 PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation EMNLP 2022 RACE: Retrieval-augmented Commit Message Generation EMNLP 2022 Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks IJCAI 2022 TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data EMNLP 2022 Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems EMNLP 2022 CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax Trees EMNLP 2021 Reliable and Efficient Anytime Skeleton Learning AAAI 2020 TableSense: Spreadsheet Table Detection with Convolutional Neural Networks AAAI 2019