Ajay @ajay0x

these are the good old days / ML, Ads, LLMs @ DoorDash, Amazon Science, Microsoft Research, UIUC linkedin.com/in/ajay0 San Francisco, CA Joined September 2017

Tweets

11
Followers

110
Following

205
Likes

77

Nagarajan Natarajan @naga86

9 months ago

Microsoft Research India is excited to announce applications are open for our Research Fellow program (deadline 15th Feb 2025). Details of the program and the application are here: 🔗 Research Fellow program: aka.ms/msrirf @MSFTResearch

3 48 141 38K 88

Lingming Zhang @LingmingZhang

12 months ago

Excited to announce #LLM4Code2025 (submission DDL: Nov 18) colocated with @ICSEconf! We hope to create a platform for researchers/practitioners to discuss the latest in LLM4Code across various relevant fields including SE, PL, ML, and beyond: llm4code.github.io

LLM4Code @llm4code

12 months ago

1 12 39 13K 5

Download Image

1 6 24 3K 1

Lingming Zhang @LingmingZhang

a year ago

Introducing OpenAutoCoder-Agentless😺: A simple agentless solution solves 27.3% GitHub issues on SWE-bench Lite with ~$0.34 each, outperforming all open-source AI SW agents! It's fully open-source, try it out: 🧑‍💻github.com/OpenAutoCoder/… 📝huggingface.co/papers/2407.01…

20 129 636 96K 553

Download Image

Nagarajan Natarajan @naga86

2 years ago

Our latest work on comprehensive evaluation of code language models on real-world code editing scenarios and metrics beyond functional correctness is up now. With this, we are releasing a new benchmark suite 'NoFunEval' (non-functional evaluation). arxiv.org/pdf/2401.15963…

4 10 76 18K 20

Download Image

AK @_akhaliq

2 years ago

Magicoder: Source Code Is All You Need paper page: huggingface.co/papers/2312.02… introduce Magicoder, a series of fully open-source (code, weights, and data) Large Language Models (LLMs) for code that significantly closes the gap with top code models while having no more than 7B…

8 179 819 127K 591

Download Image

LLM4Code @llm4code

2 years ago

📢🚨 Call for Papers Interested in Large Language Models for Code? Consider submitting to the 1st LLM4Code workshop at @ICSEconf 2024! #LLM4Code 🌟Website: llm4code.github.io 🌟Deadline: Dec 7, 2023 🌟8-page research paper or 4-page position paper Please help retweet! 🧵

1 15 41 14K 8

Lingming Zhang @LingmingZhang

3 years ago

🚨LLMs are Zero-Shot Fuzzers! Excited to share our TitanFuzz🤖 work @issta23: #LLMs can be directly applied for both generative and mutative fuzzing, while being fully automated, generalizable, and applicable to domains challenging for traditional fuzzers (such as DL systems)🧵