HKUST(GZ) Data Intelligence and Analytics Lab
This is the source-code homepage of HKUST(GZ)-DIAL. We are glad to share our code
Pinned Repositories
ChartInsights
Officical repository for the paper“ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering”(EMNLP'24)
DeepEye-APIs
APIs of DeepEye. DeepEye: Towards Automatic Data Visualization [ICDE 2018]
HAIChart
Official repository for the paper “HAIChart: Human and AI Paired Visualization System” (VLDB'24)
LineNet-and-LineBench-SIGMOD2023
Official repository for the paper “Learned Data-aware Image Representations of Line Charts for Similarity Search” (SIGMOD'23)
ncNet
ncNet is a Transformer-based model for supporting NL2VIS.
NL2SQL360
Official repository for the paper “The Dawn of Natural Language to SQL: Are We Fully Ready?” (VLDB'24)
NL2SQL_Handbook
This is a continuously updated handbook for readers to easily track the latest NL2SQL (Text-to-SQL) techniques in the literature and provide practical guidance for researchers and practitioners.
StatQA
Official repository for the paper “Are Large Language Models Good Statisticians?” [NeurIPS'24]
Vega-Zero
Vega-Zero is a sequence-based visualization grammar based on Vega-Lite.
HKUST(GZ) Data Intelligence and Analytics Lab's Repositories
HKUSTDial/NL2SQL_Handbook
This is a continuously updated handbook for readers to easily track the latest NL2SQL (Text-to-SQL) techniques in the literature and provide practical guidance for researchers and practitioners.
HKUSTDial/DeepEye-APIs
APIs of DeepEye. DeepEye: Towards Automatic Data Visualization [ICDE 2018]
HKUSTDial/NL2SQL360
Official repository for the paper “The Dawn of Natural Language to SQL: Are We Fully Ready?” (VLDB'24)
HKUSTDial/ncNet
ncNet is a Transformer-based model for supporting NL2VIS.
HKUSTDial/HAIChart
Official repository for the paper “HAIChart: Human and AI Paired Visualization System” (VLDB'24)
HKUSTDial/StatQA
Official repository for the paper “Are Large Language Models Good Statisticians?” [NeurIPS'24]
HKUSTDial/Vega-Zero
Vega-Zero is a sequence-based visualization grammar based on Vega-Lite.
HKUSTDial/ChartInsights
Officical repository for the paper“ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering”(EMNLP'24)
HKUSTDial/MAR
Official repository for the paper “MAR: Matching-Augmented Reasoning for Enhancing Visual-based Entity Question Answering ” (EMNLP'24)
HKUSTDial/LineNet-and-LineBench-SIGMOD2023
Official repository for the paper “Learned Data-aware Image Representations of Line Charts for Similarity Search” (SIGMOD'23)
HKUSTDial/vistroubleshooting.github.io
Official repository for the paper "VisTroubleshooting: Ask Humans or AI? Exploring Their Roles in Visualization Troubleshooting" 🔍 Through analysis of 889 Vega-Lite cases from Stack Overflow, we provide insights into their respective roles and effectiveness.