Excited to share our new paper: "Instruction Following by Boosting Attention of Large Language Models"! We introduce Instruction Attention Boosting (InstABoost), a simple yet powerful method to steer LLM behavior by making them pay more attention to instructions. (🧵1/7)

Do come to our poster tomorrow if you're attending @iclr_conf and are interested in AI safety / Automated reasoning / Formal logic with LLMs!

#ICLR2025 Oral LLMs often struggle with reliable and consistent decisions under uncertainty 😵‍💫 — largely because they can't reliably estimate the probability of each choice. We propose BIRD 🐦, a framework that significantly enhances LLM decision making under uncertainty. BIRD

I am looking for 1-2 PhD students interested broadly in computer systems, compilers, and/or PL! If you would like to do your PhD in a vibrant city with great weather, next to the sea 🌊, and the mountains 🏔️, make sure to apply to UCLA and mark my name as a potential advisor!

Reminder to apply to join the software engineering group@Cornell! https://t.co/ZbThrdTDjq RT!

It was really fun to work w/ @AntonXue @RajeevAlur @SurbhiGoel_ and @RICEric22! We attempt to understand how (and why) LLMs can be attacked to err on tasks with simple in-context instructions (user-provided rules, safety prompts, etc.). See the original thread for more details!

Are you an undergraduate interested in doing research in Programming 🖥️ Languages 🗣️? Then you should apply to REPL ( https://t.co/C9CAKZBiGi), a 10-week summer program to do research with PL students and faculty at Penn. All REPL students get a stipend 💸 Deadline: March 1st!

Two highly talented undergrads in my research group are looking for SWE internship roles in Summer 2024. ✨✨ Do you need someone to build a beautiful front-end for a new product? (1/3)

It's that time of the year again, so re-surfacing this: https://t.co/PYXi5hAchQ (It is not advice from me, it is just a dump of my bookmarks to helpful articles from when I was applying to grad school)

Hey Friends, I am looking for a new role as a Research Engineer/Associate Researcher, MLE or even a SWE(I think I am pretty good!). I have had the chance to work @Microsoft as a predoctoral research fellow and @prodigaltech as a SWE.

How can we seamlessly combine Language Models and Symbolic Reasoners to get the best of both worlds? Introducing our work appearing at #ACL2023 this week: Paper: https://t.co/BJhojTyaI9 Code: https://t.co/4AiaYNk10F 🧵👇 (1/6)

The PROSE team is hiring Research Fellows in India to work on program synthesis⚡This is a 1-year appointment to do applied research that will impact millions of people using Excel, Visual Studio, Power Query, and more! https://t.co/QGL6gYwPAa

I am excited to share that we are presenting our work: "Repair Is Nearly Generation: Multilingual Program Repair with LLMs" at #AAAI23 this week! My ever-charming advisor, @josepablocam, will present the poster on 12th Feb in person. If you are attending, please visit! (1/n)

A few amazing folks placed during the Day 1 hiring drive at BITS Pilani were at the unfortunate end of getting their offers rescinded by a $100Mn+ venture backed startup. Incase your firm is hiring for SDE 1 roles, kindly DM 🙏 I'll share the resumes with you. RT for Karma!🙌

First top conf paper, "Incremental Learning for Animal Pose Estimation using RBF k-DPP," got accepted at BMVC! Glad we were able to change the mind of reviewer #2 from reject to borderline accept :P Project page coming soon :)

@Avishreekh and @het__shah are presenting their results for #ML4Land What is ML4Land? The projects aims at detecting #Earth heating patterns using #MachineLearning to learn the mapping between #ERA5 variables & #satelliteobservations of skin temperature

New dates are out! We will be having the AI Symposium on the weekend of 2nd and 3rd October. Registrations are free! For more details: Website: https://t.co/GYpguaJpFy Registration: https://t.co/0YgfHd2dcK Mailing List: https://t.co/xpLyTzrDDv See you there!

A wonderful initiative by @SforAiDL and it's free for all ☺️. Do attend for some great talks on AI!

ML4Land aims to detect #Earth heating patterns using #MachineLearning to learn the mapping between #ERA5 variables & #satelliteobservations of skin temperature 🎧 their developers @het__shah @Avishreekh 🗣️: https://t.co/WEsbpVB6Bn https://t.co/ycvAbTLqe5 @ECMWF @CopernicusECMWF

Interested in Earth's observation data, Climate reanalysis & Machine Learning❓ @Avishreekh and @het__shah will present their ML4Land #ESoWC2021 project during our #AMA webinar on 15 July #Register now to the even at this link👇 https://t.co/NQWnrjt6bH @ECMWF @CopernicusECMWF