Thanks!
Yuling
YerbaPage
AI & ML interests
None yet
Recent Activity
submitted
a paper
1 day ago
GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts
upvoted
a
paper
3 days ago
GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts
Organizations
replied to
their
post
3 months ago
reacted to
their
post with 🚀👀❤️🔥
3 months ago
Post
8970
How to compress long code context? 📚
Check out our LongCodeZip! Paper just got accepted to ASE 2025. 🔥
Code: https://github.com/YerbaPage/LongCodeZip
Paper: LongCodeZip: Compress Long Context for Code Language Models (2510.00446)
Check out our LongCodeZip! Paper just got accepted to ASE 2025. 🔥
Code: https://github.com/YerbaPage/LongCodeZip
Paper: LongCodeZip: Compress Long Context for Code Language Models (2510.00446)
-
- 4 replies
posted
an
update
3 months ago
Post
8970
How to compress long code context? 📚
Check out our LongCodeZip! Paper just got accepted to ASE 2025. 🔥
Code: https://github.com/YerbaPage/LongCodeZip
Paper: LongCodeZip: Compress Long Context for Code Language Models (2510.00446)
Check out our LongCodeZip! Paper just got accepted to ASE 2025. 🔥
Code: https://github.com/YerbaPage/LongCodeZip
Paper: LongCodeZip: Compress Long Context for Code Language Models (2510.00446)
-
-
- 4 replies
reacted to
their
post with 🤗👀🔥
4 months ago
Post
2632
Announcing our new work on "Repository Level Question Answering"! 🎉
We introduce SWE-QA, a repository-level code QA benchmark with 576 real-world questions that require a deep understanding of the entire codebase to answer.
Curious about the limits of today's LLMs on complex codebases? Check out our paper and open-source data! 💻🧠
Link 👇
https://arxiv.org/pdf/2509.14635
https://github.com/peng-weihan/SWE-QA-Bench
#LLM #AI #SoftwareEngineering #Benchmark
We introduce SWE-QA, a repository-level code QA benchmark with 576 real-world questions that require a deep understanding of the entire codebase to answer.
Curious about the limits of today's LLMs on complex codebases? Check out our paper and open-source data! 💻🧠
Link 👇
https://arxiv.org/pdf/2509.14635
https://github.com/peng-weihan/SWE-QA-Bench
#LLM #AI #SoftwareEngineering #Benchmark
posted
an
update
4 months ago
Post
2632
Announcing our new work on "Repository Level Question Answering"! 🎉
We introduce SWE-QA, a repository-level code QA benchmark with 576 real-world questions that require a deep understanding of the entire codebase to answer.
Curious about the limits of today's LLMs on complex codebases? Check out our paper and open-source data! 💻🧠
Link 👇
https://arxiv.org/pdf/2509.14635
https://github.com/peng-weihan/SWE-QA-Bench
#LLM #AI #SoftwareEngineering #Benchmark
We introduce SWE-QA, a repository-level code QA benchmark with 576 real-world questions that require a deep understanding of the entire codebase to answer.
Curious about the limits of today's LLMs on complex codebases? Check out our paper and open-source data! 💻🧠
Link 👇
https://arxiv.org/pdf/2509.14635
https://github.com/peng-weihan/SWE-QA-Bench
#LLM #AI #SoftwareEngineering #Benchmark
reacted to
their
post with 👀🚀🔥
4 months ago
Post
1459
Are LLMs just memorizing benchmarks?
We developed LastingBench to stop the "cheating" and ensure fair AI evaluation.
Our LastingBench has been accepted to #EMNLP2025 Findings! 🎉
Paper: https://arxiv.org/abs/2506.21614
Code: https://github.com/Seriousss/LastingBench
#NLP #EMNLP2025
We developed LastingBench to stop the "cheating" and ensure fair AI evaluation.
Our LastingBench has been accepted to #EMNLP2025 Findings! 🎉
Paper: https://arxiv.org/abs/2506.21614
Code: https://github.com/Seriousss/LastingBench
#NLP #EMNLP2025
posted
an
update
4 months ago
Post
1459
Are LLMs just memorizing benchmarks?
We developed LastingBench to stop the "cheating" and ensure fair AI evaluation.
Our LastingBench has been accepted to #EMNLP2025 Findings! 🎉
Paper: https://arxiv.org/abs/2506.21614
Code: https://github.com/Seriousss/LastingBench
#NLP #EMNLP2025
We developed LastingBench to stop the "cheating" and ensure fair AI evaluation.
Our LastingBench has been accepted to #EMNLP2025 Findings! 🎉
Paper: https://arxiv.org/abs/2506.21614
Code: https://github.com/Seriousss/LastingBench
#NLP #EMNLP2025
reacted to
their
post with 👀👍🤗🔥
6 months ago
Post
2947
Latest work on SWE-Bench 🐛
Our two new papers from the SJTU & Huawei: Powered by DeepSeek-V3, we've achieved a new SOTA on the SWE-Bench benchmark!
We introduce two innovative approaches:
⚔️ SWE-Debate: AI agents compete and "debate" to generate the best code fix.
🧠 SWE-Exp: An AI agent learns from past repair "experience" to solve new issues more efficiently.
👇 Explore the future of software development:
SWE-Debate
📄 Paper: https://arxiv.org/abs/2507.23348
💻 Code: https://github.com/YerbaPage/SWE-Debate
SWE-Exp
📄 Paper: https://arxiv.org/abs/2507.23361
💻 Code: https://github.com/YerbaPage/SWE-Exp
Our two new papers from the SJTU & Huawei: Powered by DeepSeek-V3, we've achieved a new SOTA on the SWE-Bench benchmark!
We introduce two innovative approaches:
⚔️ SWE-Debate: AI agents compete and "debate" to generate the best code fix.
🧠 SWE-Exp: An AI agent learns from past repair "experience" to solve new issues more efficiently.
👇 Explore the future of software development:
SWE-Debate
📄 Paper: https://arxiv.org/abs/2507.23348
💻 Code: https://github.com/YerbaPage/SWE-Debate
SWE-Exp
📄 Paper: https://arxiv.org/abs/2507.23361
💻 Code: https://github.com/YerbaPage/SWE-Exp
posted
an
update
6 months ago
Post
2947
Latest work on SWE-Bench 🐛
Our two new papers from the SJTU & Huawei: Powered by DeepSeek-V3, we've achieved a new SOTA on the SWE-Bench benchmark!
We introduce two innovative approaches:
⚔️ SWE-Debate: AI agents compete and "debate" to generate the best code fix.
🧠 SWE-Exp: An AI agent learns from past repair "experience" to solve new issues more efficiently.
👇 Explore the future of software development:
SWE-Debate
📄 Paper: https://arxiv.org/abs/2507.23348
💻 Code: https://github.com/YerbaPage/SWE-Debate
SWE-Exp
📄 Paper: https://arxiv.org/abs/2507.23361
💻 Code: https://github.com/YerbaPage/SWE-Exp
Our two new papers from the SJTU & Huawei: Powered by DeepSeek-V3, we've achieved a new SOTA on the SWE-Bench benchmark!
We introduce two innovative approaches:
⚔️ SWE-Debate: AI agents compete and "debate" to generate the best code fix.
🧠 SWE-Exp: An AI agent learns from past repair "experience" to solve new issues more efficiently.
👇 Explore the future of software development:
SWE-Debate
📄 Paper: https://arxiv.org/abs/2507.23348
💻 Code: https://github.com/YerbaPage/SWE-Debate
SWE-Exp
📄 Paper: https://arxiv.org/abs/2507.23361
💻 Code: https://github.com/YerbaPage/SWE-Exp
reacted to
their
post with 🚀
6 months ago
Post
1611
Is your code written by a human or an AI? 🤖
With the rise of AI coding assistants, this question is more critical than ever. Our new tool, DetectCodeGPT, effectively identifies AI-generated code, outperforming SOTA methods with a 7.6% increase in AUC!
How? By analyzing unique stylistic and syntactic patterns in code, not just the text.
👇 Explore more:
Paper: https://arxiv.org/html/2401.06461v2
Code: https://github.com/YerbaPage/DetectCodeGPT
With the rise of AI coding assistants, this question is more critical than ever. Our new tool, DetectCodeGPT, effectively identifies AI-generated code, outperforming SOTA methods with a 7.6% increase in AUC!
How? By analyzing unique stylistic and syntactic patterns in code, not just the text.
👇 Explore more:
Paper: https://arxiv.org/html/2401.06461v2
Code: https://github.com/YerbaPage/DetectCodeGPT