🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

#NeurIPS2023 all week. let's discuss building robust code generators that interacts with humans. e.g.: leveraging human test-cases (quote), interactive programming with LLM (arxiv.org/abs/2305.18498), and annotating soft-body manipulations (openreview.net/forum?id=ecRaD…) DMs are open

I recently gave a lecture on Image-Text Modeling for Multilingual NLP at CMU and thought I'd share my slides in case interested folks may find it useful! drive.google.com/file/d/1iHrnC1… Here are a few things covered in the slides. (1/n)

Awesome to see Shashwat Goel ✈️ ICML 2025 and Nikhil Chandak getting recognized for this work 🏆🎉 Congratulations!

last monday I went to my old highschool. It was their career day, and I explained to ~100 students on what it is like being a scientist. here's a re-recording of it, hopefully it is useful to some: youtu.be/DhxGRhUkb8c?si…

We are thrilled to have Mahathi Vempati as our next speaker! She will discuss their work on an exponential separation between parallel quantum and classical query models. The talk is tomorrow (Monday at 8pm IST). Details are on the poster and website: braqiiit.github.io/Talks.html

Super excited to be presenting this at #ICLR2024 next week! Swing by during Poster Session 2 on 7 May, at 4:30pm CEST 😃 I'm also excited to see folks in Vienna, so if you want to chat about grounded communication in context (especially about programs), reach out on DM or email!

I am thrilled to announce that I will be joining Duke University Duke CompSci as an Assistant Professor in summer 2025. Super excited for the next chapter! Stay tuned for the launch of my lab 🧠🤖

Humans often use non-literal language to communicate –like hyperboles for added emphasis or sarcasm to offer polite criticism with humor AI systems should be able to decipher the real intent behind these words, and respond appropriately! 📜arxiv.org/abs/2405.08760 #ACL2024 main🎉

I’m excited to share some news: My group and I are moving to NYU Psychology! I’ll be affiliated with both cognition/perception and social psych, and I am SO thrilled about this unique opportunity to help bridge the two programs 🤗

Hila Gonen Nora Belrose Special shoutout to Shashwat Singh, who approached me as an undergrad to kickstart this project. It was an absolute pleasure working with him! (8/8)

Students at IIIT Hyderabad, supposed to be one of the top engineering colleges in the country, are in an ongoing health crisis caused due to appalling mismanagement and negligence going on since well over a year. 🧵👇on mass typhoid breakouts, food poisoning, underreporting..

Highly encourage chatting with Evan if you're interested in communication and programs! I'm also very excited about the paper--we prove a surprising property of RSA over binary lexicons, and use this to speed up pragmatic program synthesis by 100x. Validated in human study too!

Check out our work on pragmatic reasoning for program synthesis using a learned ranking function! I’m very excited about the idea of rankings in this work and how it might relate to preference feedback. Reach out if you want to chat about it!

Introducing the commit0 interactive environment for coding agents. Challenge: generate Python libraries from scratch. Commit0 is designed with interactivity, dependencies, and specifications as first-class considerations. We include a benchmark with 50+ challenging libraries.

Can LLMs cater to diverse cultures in text generation? We find: 1️⃣lexical variance across nationalities 2️⃣culturally salient words 3️⃣weak correlation w/ cultural values 📜arxiv.org/abs/2406.11565 🤗huggingface.co/datasets/shail… 💻github.com/shaily99/eecc 🎉EMNLP 2025🎉 w/ Fernando Diaz 🧵

New ARC-AGI paper ARC Prize w/ fantastic collaborators Wen-Ding Li @ ICLR'25 Keya Hu Zenna Tavares evanthebouncy Basis For few-shot learning: better to construct a symbolic hypothesis/program, or have a neural net do it all, ala in-context learning? cs.cornell.edu/~ellisk/docume…

I've recently started my job as an asst professor at NTU, Singapore. If you are ever in town come say hi :)

new multi-turn instruction grounding dataset with Will McCarthy and Saujas Vaduguru - multi-modal instruction : drawing + txt - verifiable execution : 2D CAD gym env - easy eval : API → score - baselines : human vs VLMs - large : 15,163 inst-exe rounds github.com/AutodeskAILab/… [1/n]

Just look at these multi-modal refinement instructions! How would we ground them into reasonable executions?? joint work with Will McCarthy Saujas Vaduguru Judy Fan Daniel Fried Karl D.D. Willis Justin Matejka

Are code agents good at software design, ie building general and reusable code? We present Librarian, a new refactoring method, and MiniCode, a verifiable refactoring benchmark that requires agents to design libraries that jointly minimizes code from multiple repos 🧵