YerbaPage (Yuling)

posted an update 9 days ago

Post

1411

Curated list of **Repository-level Code Generation** papers & benchmarks! 🔥

Stay ahead with the latest in:
✅ Repo-level Issue Resolution
✅ Repo-level Code Completion
✅ Datasets & Benchmarks

👉 Check it out: https://github.com/YerbaPage/Awesome-Repo-Level-Code-Generation 🔥

replied to their post 3 months ago

We have released our demo on Hugging Face here: https://huggingface.co/spaces/learnmlf/MGDebugger 🚀✨.

liked a Space 3 months ago

Sleeping

1

📈

MGDebugger

upvoted 2 papers 3 months ago

Horizon-Length Prediction: Advancing Fill-in-the-Middle Capabilities for Code Generation with Lookahead Planning

Paper • 2410.03103 • Published Oct 4 • 6

Internal Consistency and Self-Feedback in Large Language Models: A Survey

Paper • 2407.14507 • Published Jul 19 • 46

commented a paper 3 months ago

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

Paper • 2410.01215 • Published Oct 2 • 30 •

8

liked a Space 3 months ago

Running

10

🐨

LDB

commented a paper 3 months ago

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

Paper • 2410.01215 • Published Oct 2 • 30 •

8

upvoted a collection 3 months ago

Coding

Collection

193 items • Updated Oct 4 • 17

commented a paper 3 months ago

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

Paper • 2410.01215 • Published Oct 2 • 30 •

8

upvoted a collection 3 months ago

LLM for code

Collection

8 items • Updated Oct 3 • 3

authored a paper 3 months ago

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

Paper • 2410.01215 • Published Oct 2 • 30

reacted to their post with 👀🔥🤗 3 months ago

Post

2047

We propose MGDebugger, a hierarchical bottom-up LLM code debugger 🔥 that can fix bugs from low-level syntax errors to high-level algorithmic flaws.

It achieves an ⭐️ 18.9% improvement in accuracy over seed generations in HumanEval and a ⭐️ 97.6% repair success rate in HumanEvalFix.

Paper available at https://arxiv.org/abs/2410.01215.
Code and demo available at https://github.com/YerbaPage/MGDebugger.

2 replies

·

posted an update 3 months ago

Post

2047

We propose MGDebugger, a hierarchical bottom-up LLM code debugger 🔥 that can fix bugs from low-level syntax errors to high-level algorithmic flaws.

It achieves an ⭐️ 18.9% improvement in accuracy over seed generations in HumanEval and a ⭐️ 97.6% repair success rate in HumanEvalFix.

Paper available at https://arxiv.org/abs/2410.01215.
Code and demo available at https://github.com/YerbaPage/MGDebugger.

2 replies

·

upvoted a paper 3 months ago

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

Paper • 2410.01215 • Published Oct 2 • 30

commented a paper 3 months ago

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

Paper • 2410.01215 • Published Oct 2 • 30 •

8

authored a paper 6 months ago

Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers

Paper • 2401.06461 • Published Jan 12 • 1

Yuling

AI & ML interests

Recent Activity

Organizations

YerbaPage's activity

MGDebugger

Horizon-Length Prediction: Advancing Fill-in-the-Middle Capabilities for Code Generation with Lookahead Planning

Internal Consistency and Self-Feedback in Large Language Models: A Survey

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

LDB

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

Coding

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

LLM for code

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers