Picture for Tianbo Ji

Tianbo Ji

Large Language Models as Code Executors: An Exploratory Study

Add code
Oct 10, 2024
Figure 1 for Large Language Models as Code Executors: An Exploratory Study
Figure 2 for Large Language Models as Code Executors: An Exploratory Study
Figure 3 for Large Language Models as Code Executors: An Exploratory Study
Figure 4 for Large Language Models as Code Executors: An Exploratory Study
Viaarxiv icon

Is a Video worth $n\times n$ Images? A Highly Efficient Approach to Transformer-based Video Question Answering

Add code
May 16, 2023
Viaarxiv icon

Semantic-aware Dynamic Retrospective-Prospective Reasoning for Event-level Video Question Answering

Add code
May 14, 2023
Figure 1 for Semantic-aware Dynamic Retrospective-Prospective Reasoning for Event-level Video Question Answering
Figure 2 for Semantic-aware Dynamic Retrospective-Prospective Reasoning for Event-level Video Question Answering
Figure 3 for Semantic-aware Dynamic Retrospective-Prospective Reasoning for Event-level Video Question Answering
Figure 4 for Semantic-aware Dynamic Retrospective-Prospective Reasoning for Event-level Video Question Answering
Viaarxiv icon

Document-Level Machine Translation with Large Language Models

Add code
Apr 05, 2023
Viaarxiv icon

QAScore -- An Unsupervised Unreferenced Metric for the Question Generation Evaluation

Add code
Oct 09, 2022
Figure 1 for QAScore -- An Unsupervised Unreferenced Metric for the Question Generation Evaluation
Figure 2 for QAScore -- An Unsupervised Unreferenced Metric for the Question Generation Evaluation
Figure 3 for QAScore -- An Unsupervised Unreferenced Metric for the Question Generation Evaluation
Figure 4 for QAScore -- An Unsupervised Unreferenced Metric for the Question Generation Evaluation
Viaarxiv icon

Achieving Reliable Human Assessment of Open-Domain Dialogue Systems

Add code
Mar 11, 2022
Figure 1 for Achieving Reliable Human Assessment of Open-Domain Dialogue Systems
Figure 2 for Achieving Reliable Human Assessment of Open-Domain Dialogue Systems
Figure 3 for Achieving Reliable Human Assessment of Open-Domain Dialogue Systems
Figure 4 for Achieving Reliable Human Assessment of Open-Domain Dialogue Systems
Viaarxiv icon