Picture for Hongshen Xu

Hongshen Xu

Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?

Add code
Jul 15, 2024
Figure 1 for Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
Figure 2 for Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
Figure 3 for Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
Figure 4 for Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
Viaarxiv icon

Sparsity-Accelerated Training for Large Language Models

Add code
Jun 03, 2024
Viaarxiv icon

CoE-SQL: In-Context Learning for Multi-Turn Text-to-SQL with Chain-of-Editions

Add code
May 04, 2024
Viaarxiv icon

Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback

Add code
Apr 07, 2024
Viaarxiv icon

Multilingual Brain Surgeon: Large Language Models Can be Compressed Leaving No Language Behind

Add code
Apr 06, 2024
Viaarxiv icon

Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding

Add code
Feb 28, 2024
Viaarxiv icon

A BiRGAT Model for Multi-intent Spoken Language Understanding with Hierarchical Semantic Frames

Add code
Feb 28, 2024
Viaarxiv icon

ChemDFM: Dialogue Foundation Model for Chemistry

Add code
Jan 26, 2024
Figure 1 for ChemDFM: Dialogue Foundation Model for Chemistry
Figure 2 for ChemDFM: Dialogue Foundation Model for Chemistry
Figure 3 for ChemDFM: Dialogue Foundation Model for Chemistry
Figure 4 for ChemDFM: Dialogue Foundation Model for Chemistry
Viaarxiv icon

ASTormer: An AST Structure-aware Transformer Decoder for Text-to-SQL

Add code
Oct 28, 2023
Viaarxiv icon

ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought

Add code
Oct 26, 2023
Viaarxiv icon