4 10 9

Nghi Bui

bdqnghi

https://bdqnghi.github.io/

AI & ML interests

AI4Software, AI4Code, CodeLLMs, Code Generation, Autonomous Agents

Recent Activity

liked a dataset about 1 month ago

Fsoft-AIC/CodeMMLU

upvoted a paper about 2 months ago

CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding Capabilities of CodeLLMs

commented a paper about 2 months ago

CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding Capabilities of CodeLLMs

View all activity

Organizations

bdqnghi's activity

liked a dataset about 1 month ago

Fsoft-AIC/CodeMMLU

Viewer • Updated Oct 15 • 19.9k • 316 • 6

upvoted a paper about 2 months ago

CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding Capabilities of CodeLLMs

Paper • 2410.01999 • Published Oct 2 • 10

commented a paper about 2 months ago

CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding Capabilities of CodeLLMs

Paper • 2410.01999 • Published Oct 2 • 10 •

liked a dataset about 2 months ago

Salesforce/xlam-function-calling-60k

Viewer • Updated Jul 19 • 60k • 2.71k • 388

upvoted a paper about 2 months ago

HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale

Paper • 2409.16299 • Published Sep 9 • 9

liked a model 3 months ago

Fsoft-AIC/XMAiNframe-instruct-7b

Updated Aug 23 • 174 • 5

authored a paper 4 months ago

Learning to Predict Program Execution by Modeling Dynamic Dependency on Code Graphs

Paper • 2408.02816 • Published Aug 5 • 4

upvoted 2 collections 4 months ago

Coding

Collection

193 items • Updated Oct 4 • 17

Agent

Collection

112 items • Updated Sep 9 • 18

upvoted a paper 4 months ago

Learning to Predict Program Execution by Modeling Dynamic Dependency on Code Graphs

Paper • 2408.02816 • Published Aug 5 • 4

commented a paper 4 months ago

Learning to Predict Program Execution by Modeling Dynamic Dependency on Code Graphs

Paper • 2408.02816 • Published Aug 5 • 4 •

upvoted a paper 5 months ago

Instruction Pre-Training: Language Models are Supervised Multitask Learners

Paper • 2406.14491 • Published Jun 20 • 85

authored a paper 5 months ago

REPOEXEC: Evaluate Code Generation with a Repository-Level Executable Benchmark

Paper • 2406.11927 • Published Jun 17 • 11

upvoted 2 papers 5 months ago

Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities

Paper • 2406.14562 • Published Jun 20 • 27

REPOEXEC: Evaluate Code Generation with a Repository-Level Executable Benchmark

Paper • 2406.11927 • Published Jun 17 • 11

commented 2 papers 5 months ago

REPOEXEC: Evaluate Code Generation with a Repository-Level Executable Benchmark

Paper • 2406.11927 • Published Jun 17 • 11 •

AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology

Paper • 2406.11912 • Published Jun 16 • 26 •

liked a dataset 5 months ago

Fsoft-AIC/RepoExec

Viewer • Updated Jun 23 • 1.07k • 166 • 4

upvoted a paper 5 months ago

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

Paper • 2406.11931 • Published Jun 17 • 57

authored a paper 5 months ago

The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation

Paper • 2305.06156 • Published May 9, 2023 • 2