#ml4code search results
Yesterday I defended my PhD thesis on neural networks for source code processing at @CS_HSE! Huge thanks to my advisor, Dmitry Vetrov, for his valuable guidance, to the committee for insightful questions and to @bayesgroup for friendly support during these 4 years! #PhD #ML4Code
What if your IDE crashed with specific variable names? 😱 #ML4Code is powerful, but models like BERT are sensitive to adversarial code edits, performing worse than random guessing! We find that contrastive learning is more robust. Check out ContraCode: arxiv.org/abs/2007.04973 👇
.. and the companion website for easy exploration and navigation of added papers - tusharma.in/ML4SCA/ #ml4se #ml4code #ml4sca
@DanielNichols10's work in collaboration with Aniruddha Marathe and @tgamblin explores the use of deep learning to model the performance impact of code changes across git commits as a function of AST diffs. #HPC #DeepLearning #ML4code
Interested in doing a PhD at the intersection of Machine Learning, Programming Languages and Software Engineering? Michael Pradel's excellent group at Stuttgart is looking for candidates: software-lab.org/jobs/PhD_openi… #MLonCode #ML4Code
Excited to be in Vienna for @icmlconf to present “Class-Level Code Generation from Natural Language Using Iterative, Tool-Enhanced Reasoning over Repository” (github.com/microsoft/repo…) at @DMLRWorkshop 4PM today. Excited to connect with #ML4Code & LLM Agent enthusiasts! #icml
![anmolagarwal999's tweet card. [ICML DMLR 2024] Repo that contains code for the paper titled: "Class-Level Code Generation from Natural Language Using Iterative, Tool-Enhanced Reasoning over Repository". - micr...](https://pbs.twimg.com/card_img/1986611829561307136/9SPDEpUY?format=jpg&name=orig)
What happens when Moderne’s fast, 100% accurate code refactoring automation meets #generativeAI? 🚀 Check out this blog from our CTO to learn what it takes to auto-remediate code at scale—and how #ML4Code 🤖can make this even better. hubs.ly/Q01Z35G90
moderne.ai
Generative AI for Automating Code Remediation at Scale | Moderne
Learn how to use generative AI for automated code refactoring at scale and why code remediation needs more than an in-line AI assistant.
Recently, we noticed that near-duplicates in code corpora have a negative effect on real-life applications of #ML4Code. I spent some time documenting and understanding this: arxiv.org/abs/1812.06469. Many applications are affected (includes ideas published in ML, NLP, PL, SE).
Happy to share that our research paper, "An Empirical Study of Large Language Models for Type and Call Graph Analysis in Python and JavaScript" has been accepted for publication in Empirical Software Engineering (EMSE) journal. #LLM #ML4Code #EMSE #AI
If you are interested in #ml4code here is a video I recorded on this topic channel9.msdn.com/Events/Microso… #Azure
Thrilled to share our ICLR’22 paper titled “CodeTrek: Flexible Modeling of Code using an Extensible Relational Representation” #ICLR22 #DL4Code #ML4Code cis.upenn.edu/~pardisp/ICLR2…
Machine Programming & Tech, Ep. 6: "Computation-Cautious Machine Learning Systems" by Dr. Abdul Wasay (the latest addition to Intel Labs' Machine Programming Research). youtube.com/watch?v=lA39WX… #machineprogramming #ml4code #ml #iamintel #intel #Harvard
For further research investigating how program structure can push #ML4Code forward, hopeful that python_graphs continues to prove useful!
The model is pre-trained using 1.8m JavaScript programs mined from Github @miltos1 @mmjb86. Our work extends the Momentum Contrast approach to code @inkynumbers. Unsupervised learning is a powerful method to scale #ml4code methods. 5/7
Deep code search is a novel code search engine that uses joint embeddings to match natural language queries with source code results. Thought-provoking ideas from Gu et al... blog.acolyer.org/2018/06/26/dee…
The talk is gonna be exciting! I'm even more excited about our follow-up discussions tomorrow! 👩🏻💻 Let's connect if you too have a similar interest in #ml4code ✨
Interesting time to work in #ML4Code. Were I to guess, close to $10^9 in funding for AI coding startups. IDK if they realize how tough the devtools market really is / hope they have a moat. @Replit @Sourcegraph @tabnine @phindsearch @morph_labs @anysphere @magicailabs @codeiumdev
Prediction: AB will acquire JB within five years. Both working on #ML4Code. Both invested in dev tools and software teamwork. Language and culture fit. Strategic way to offset MS/GH/OAI monopoly. Hope I'm wrong.
Prediction: MS will acquire GH within five years. If the #ML4Code stuff delivers for MS, acquisition is highly likely. Although it would have been cheaper a few years ago. blog.github.com/2018-05-07-int…
Happy to share that our research paper, "An Empirical Study of Large Language Models for Type and Call Graph Analysis in Python and JavaScript" has been accepted for publication in Empirical Software Engineering (EMSE) journal. #LLM #ML4Code #EMSE #AI
Excited to be in Vienna for @icmlconf to present “Class-Level Code Generation from Natural Language Using Iterative, Tool-Enhanced Reasoning over Repository” (github.com/microsoft/repo…) at @DMLRWorkshop 4PM today. Excited to connect with #ML4Code & LLM Agent enthusiasts! #icml
I'm wondering how much better is @openai's newest model, GPT-4o, in coding tasks like HumanEval(+) compared to GPT-4 released last year. I'd like to see some improvement after a year.🙂 #GPT4o #AI #ML4Code
Interesting time to work in #ML4Code. Were I to guess, close to $10^9 in funding for AI coding startups. IDK if they realize how tough the devtools market really is / hope they have a moat. @Replit @Sourcegraph @tabnine @phindsearch @morph_labs @anysphere @magicailabs @codeiumdev
What happens when Moderne’s fast, 100% accurate code refactoring automation meets #generativeAI? 🚀 Check out this blog from our CTO to learn what it takes to auto-remediate code at scale—and how #ML4Code 🤖can make this even better. hubs.ly/Q01Z35G90
moderne.ai
Generative AI for Automating Code Remediation at Scale | Moderne
Learn how to use generative AI for automated code refactoring at scale and why code remediation needs more than an in-line AI assistant.
You can go to ml4se.dev to access our GitHub repo containing papers, theses, datasets, and tools related to the application of Machine Learning for Software Engineering. #ml4se #ml4code #ai4se #SE #papers #code
@DanielNichols10's work in collaboration with Aniruddha Marathe and @tgamblin explores the use of deep learning to model the performance impact of code changes across git commits as a function of AST diffs. #HPC #DeepLearning #ML4code
Yesterday I defended my PhD thesis on neural networks for source code processing at @CS_HSE! Huge thanks to my advisor, Dmitry Vetrov, for his valuable guidance, to the committee for insightful questions and to @bayesgroup for friendly support during these 4 years! #PhD #ML4Code
For further research investigating how program structure can push #ML4Code forward, hopeful that python_graphs continues to prove useful!
Hi @Stanford students - I'll be teaching CS329M, a new grad/adv undergrad course on machine programming, starting in Sept. 2022. Please register if you have interest in #AI/#ML for code (#ml4code)! More details here: sites.google.com/view/gottschli… Please RT!
The talk is gonna be exciting! I'm even more excited about our follow-up discussions tomorrow! 👩🏻💻 Let's connect if you too have a similar interest in #ml4code ✨
Happy to see that Type4Py will be presented and discussed at the "Deep Learning for Big Code" seminar this month, which is organized by @the_sri_lab of ETH Zurich. sri.inf.ethz.ch/teaching/bigco… #ML4Code #DL #bigcode #ML4SE #type4py
sri.inf.ethz.ch
Deep Learning for Big Code
Graduate seminar on new methods and systems for learning from programs.
Here is the list of accepted papers at the Deep Learning for Code workshop (part of ICLR). Check it out if you're interested in the ML4SE research. The DL4Code workshop takes place on Apr. 29th. openreview.net/group?id=ICLR.… #DL4Code #ML4SE #ML4Code #workshop #ICLR
Prediction: AB will acquire JB within five years. Both working on #ML4Code. Both invested in dev tools and software teamwork. Language and culture fit. Strategic way to offset MS/GH/OAI monopoly. Hope I'm wrong.
Prediction: MS will acquire GH within five years. If the #ML4Code stuff delivers for MS, acquisition is highly likely. Although it would have been cheaper a few years ago. blog.github.com/2018-05-07-int…
.. and the companion website for easy exploration and navigation of added papers - tusharma.in/ML4SCA/ #ml4se #ml4code #ml4sca
Yesterday I defended my PhD thesis on neural networks for source code processing at @CS_HSE! Huge thanks to my advisor, Dmitry Vetrov, for his valuable guidance, to the committee for insightful questions and to @bayesgroup for friendly support during these 4 years! #PhD #ML4Code
@DanielNichols10's work in collaboration with Aniruddha Marathe and @tgamblin explores the use of deep learning to model the performance impact of code changes across git commits as a function of AST diffs. #HPC #DeepLearning #ML4code
Something went wrong.
Something went wrong.
United States Trends
- 1. Veterans Day 210K posts
- 2. Veterans Day 210K posts
- 3. Luka 69.6K posts
- 4. Nico 111K posts
- 5. Mavs 25K posts
- 6. #csm220 3,796 posts
- 7. Gambit 19.5K posts
- 8. Kyrie 5,908 posts
- 9. Dumont 20K posts
- 10. Wike 47.4K posts
- 11. #MFFL 2,024 posts
- 12. Arlington National Cemetery 8,615 posts
- 13. Vets 19.4K posts
- 14. Mantis 3,129 posts
- 15. Venom 16.9K posts
- 16. United States Armed Forces 1,442 posts
- 17. Made in China 4,685 posts
- 18. Wanda 21.4K posts
- 19. Armistice Day 17.7K posts
- 20. Mavericks 28.1K posts