Rajeev Alur
@RajeevAlur
Followers
2K
Following
1K
Media
14
Statuses
197
Professor of Computer Science at @Penn, researcher in Formal methods, Programming languages, Safe AI, Cyber-physical systems
Philadelphia, PA
Joined March 2022
Congratulations to @_ziyang_ for his outstanding thesis that advances theory, tools and applications of neurosymbolic AI, looking forward to his contributions as he sets up his own research group.
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
0
0
19
Looking forward to discuss the promise of neurosymbolic approaches to trustworthy AI at @NSF CISE
1
5
31
RT @zgives: Excited that Phillip Hilliard (co-advised with @RajeevAlur) will present work on adaptively processing stream queries with ML o….
0
2
0
RT @ucsd_cse: Meet Prof. @lorisdanto!🙌 A first-gen student from Italy to @UCSanDiego CSE, he’s making code more accessible using formal me….
0
4
0
Pot of gold at the end of obstacle course with conference submission deadlines: a PhD! Congratulations to Dr. Anton Xue! @AntonXue
3
2
87
RT @PennAsset: We can’t wait to host the 2025 NeuS Conference here in Amy Gutmann Hall from May 28 - May 30! If you want to learn more or r….
0
2
0
Congratulations to Swarat Chaudhuri (PhD, @PennCIS 2007) for this wonderful honor from Guggenheim Foundation
0
6
42
Honored to be highlighted in NSF CISE monthly newsletter, and grateful for the support from @NSF to do basic research over the years #SupportNSF
7
9
70
It was great to host NSF workshop to bring together many folks working to make AI safe and trustworthy #SupportNSF.
The @pennasset's @nsf Workshop on the Science of Safe AI brought together researchers to explore the future of AI safety. Watch the highlights in this video. @rajeevalur @cis_penn @pennengineers #SafeAI
1
3
25
RT @PennAsset: ASSET Center welcomes @mjagadeesan25 on Wednesday, February 5th! Can’t wait to hear more about steering machine learning eco….
0
3
0
If you are interested in neurosymbolic problems, and feel overwhelmed at ML conferences and abandoned at traditional CS conferences, you will find a home here!.
Besides traditional research papers, we also invite tutorials, surveys, and a special disruptive ideas track where five selected entries will receive $100K each of seed funding from DARPA.
0
3
31
Besides traditional research papers, we also invite tutorials, surveys, and a special disruptive ideas track where five selected entries will receive $100K each of seed funding from DARPA.
The goal of this meeting is to bring together researchers in AI/ML + PL/FM and AI/ML + CPS/Control, all interested in developing neurosymbolic solutions to challenging system design problems.
0
1
15
The goal of this meeting is to bring together researchers in AI/ML + PL/FM and AI/ML + CPS/Control, all interested in developing neurosymbolic solutions to challenging system design problems.
Consider submitting to Conference on Neurosymbolic Systems to be held at Penn in late May.
0
2
11
Consider submitting to Conference on Neurosymbolic Systems to be held at Penn in late May.
0
9
22
Timely topic, great attendees, now back to Penn
Shonan meeting 217 on Trusted Automatic Programming is currently underway in Japan this week! The discussions are buzzing with topics like Large Language Models, Agents, Verification, and the future of software. Exciting times ahead! 🇯🇵💻 #Programming #SoftwareDevelopment
0
1
15
Logicbreaks is a step towards understanding how logical reasoning works in transformers, and will be presented at #ICLR2025.
Happy to present our recent work: "Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference".📝 Blog: 🧐 arXiv: 🤖 Code:
0
3
34
Having a great time at Shonan meeting on Trusted Automatic Programming, learning how LLM agents can be effective in many SE tasks
0
3
38
RT @PennEngAI: Snapshots from #NeurIPS2024 in Vancouver. This year, over 40 Penn researchers participated, showcasing their work ranging fr….
0
4
0
Stop by on Thursday evening poster session at #NeurIPS2024 to learn about our work on how to integrate black box components in learning pipelines.
Introducing neural programming: end-to-end learning of neural models composed with any black-box program, even those that call GPT-4. Paper: Blog: Code:
0
3
20
Looking forward to give a talk on "Compositional Reinforcement Learning" at Compositional Learning workshop at #NeurIPS2024 on Sunday.
1
1
19