Mayur Naik
@AI4Code
Followers
2K
Following
2K
Media
55
Statuses
404
Misra Family Professor @CIS_Penn. I do research on neurosymbolic AI and cybersecurity.
Philadelphia, PA
Joined January 2019
RT @aaditya_naik: Swing by our poster session today at 11 if you're at ICML to learn more about speeding up neurosymbolic learning! We will….
0
3
0
RT @RajeevAlur: Very much enjoyed advocating for symbolic reasoning for Trustworthy AI in my NSF CISE lecture, the recording is now availab….
nsf.gov
CISE Distinguished Lecture Series
0
12
0
Congratulations to Dr. Ziyang Li (@_ziyang_) on defending his dissertation today! Titled "Neurosymbolic Programming in Scallop: Design, Implementation, and Applications", this dissertation proposed Scallop, a unified programming system for combining the otherwise complementary
7
7
77
RT @RajeevAlur: Looking forward to discuss the promise of neurosymbolic approaches to trustworthy AI at @NSF CISE
nsf.gov
CISE Distinguished Lecture Series
0
5
0
RT @AndrewYNg: One of the most effective things the U.S. or any other nation can do to ensure its competitiveness in AI is to welcome high-….
0
400
0
Foundation models can now perform many reasoning tasks via prompting alone. So do we still need to train neuro-symbolic systems? Our position paper argues that neuro-symbolic prompting, not training, is the path to generalizable and interpretable reasoning.
🧠 Foundation models are reshaping reasoning. Do we still need specialized neuro-symbolic (NeSy) training, or can clever prompting now suffice?.Our new position paper argues the road to generalizable NeSy should be paved with foundation models. 🔗 (🧵1/9)
1
0
14
RT @AndrewYNg: I am alarmed by the proposed cuts to U.S. funding for basic research, and the impact this would have for U.S. competitivenes….
0
476
0
RT @aaditya_naik: We are excited to share Dolphin, a programmable framework for scalable neurosymbolic learning, to appear at ICML 2025! Li….
0
6
0
RT @PennAsset: We can’t thank @awscloud enough for the support! We are excited to see the developments in our students research!.
0
1
0
Do you use SAST (Static Application Security Testing) tools at work and wish they could become more powerful using modern LLMs? Please take 15 minutes to complete a survey:. This survey is part of a user study we are conducting to extend IRIS, an
1
3
6
As a computer science faculty and a PL / AI researcher, the part I am most fascinated about is this:. @Replit feels magical. I am supposed to know how this stuff works, but I don't -- at least not just by playing with it as a user. - What parts of the app are being generated by.
2
0
6
The year marks the dawn of the era of "vibe coding", where you code by just typing or speaking in natural language. The term was first coined and elegantly described by @karpathy here: . Here's an example interaction session by my 12 yo while building the
There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper.
1
0
6
This weekend I gave @Replit's AI agent a try with my 12 yo who has no formal training in computer science. In ten minutes each, he built and deployed two working apps. The number of CS technologies involved is mind-boggling:.- web dev (Flask/React).- application logic (Python/JS)
3
6
40
RT @baishakhir: Updating real-world large legacy projects like binutils? Meet ( C2SaferRust: leveraging program ana….
arxiv.org
In recent years, there has been a lot of interest in converting C code to Rust, to benefit from the memory and thread safety guarantees of Rust. C2Rust is a rule-based system that can...
0
2
0
All 11 talks in a chronological playlist on YouTube:. Links to individual talks:. 1. Scalable Evaluation of Large Language Models.Yann Dubois, Stanford University (now OpenAI). 2. Preference Optimization for Large Language Models.
1
15
51
Happy New Year! The lectures of all 11 guest speakers in my LLM course from Fall 2024 are now available. Thanks to all the speakers:.- Hanjun Dai (@hanjundai), Thang Luong (@lmthang), and Denny Zhou (@denny_zhou) from Google DeepMind;.- Jason Wei (@_jasonwei), Hyung Won Chung.
6
42
253
RT @RajeevAlur: Stop by on Thursday evening poster session at #NeurIPS2024 to learn about our work on how to integrate black box components….
0
3
0