Alex Robey
@AlexRobey23
AI researcher. Current postdoc at @mldcmu, Ph.D. from @Penn, B.S. & B.A. from @Swarthmore, working with @GraySwanAI, formerly @GoogleAI, @Livermore_Lab.
Chatbots like ChatGPT can be jailbroken to output harmful text. But what about robots? Can AI-controlled robots be jailbroken to perform harmful actions in the real world? Our new paper finds that jailbreaking AI-controlled robots isn't just possible. It's alarmingly easy. 🧵
[@icmlconf thread] I'll be giving an #ICML2025 expo talk on computational safety for #GenAI (4pm, July 13th) and an invited talk (No Free Lunch in AI Safety) at DIG-BUGS workshop on July 19th icml.cc/virtual/2025/w… See you in Vancouver! @IBMResearch @trustworthy_ml @AISecHub
If you are interested in safety/security jailbreaking of LLMs, defenses against them, and how the safety issues become more complicated when we design agentic workflows, this tutorial by @HamedSHassani, @aminkarbasi, @AlexRobey23 is highly recommended
Our dataset of open algebraic combinatorics questions received an oral, and is being presented today at ICML! the talk is happening now, and poster presentation is from 11 am to 1:30 pm (West B2-B3 503).
How useful are AI tools to working mathematicians? We are releasing a suite of challenging (many of them open!) research-level questions in algebraic combinatorics to test conjecturing ability in pure math.
🚨 Postdoc Hiring: I am looking for a postdoc to work on rigorously evaluating and advancing the capabilities and safety of computer-use agents (CUAs), co-advised with @ysu_nlp @osunlp. We welcome strong applicants with experience in CUAs, long-horizon reasoning/planning,…
At #ICML2025, I am super excited to introduce STAMP. This is a marriage b/w dataset inference & watermarking that finally(!) lets creators PROVE their content was used to train LLMs🔍 Its a MAJOR push taking the academic problem into real world. w/Saksham Rastogi @danish037 🧵
Honored to get the outstanding position paper award at @icmlconf :) Come attend my talk and poster tomorrow on human centered considerations for a safer and better future of work I will be recruiting PhD students at @stonybrooku @sbucompsc coming fall. Please get in touch.
Very excited for a new #ICML2025 position paper accepted as oral w @mbodhisattwa & @TuhinChakr! 😎 What are the longitudinal harms of AI development? We use economic theories to highlight AI’s intertemporal impacts on livelihoods & its role in deepening labor-market inequality.
Today @ChenHenryWu and I will be presenting our #ICML work on creativity in the Oral 3A Reasoning session (West Exhibition Hall C) 10 - 11 am PT Or please stop by our poster right after @ East Exhibition Hall A-B #E-2505 11am-1:30pm. (Hope you enjoy some silly human drawings!)
I will be at ICML next week. If you are interested in chatting about anything related to generalization, exploration, and algorithmic information theory + computation, please get in touch 😀 (DM or email)! My coauthors and I will be presenting 2 papers 👇:
Super excited to share that we have an Oral presentation for this paper next week at ICML! It will be on Tuesday at 10am (Oral 1E) in West Ballroom D, I'll be presenting 4th at 10:45am :) Our poster will be on Wednesday at 11am and I encourage you to stop by and chat!
The wait is over. Our full recap of the Agent Red Teaming Challenge is here... featuring breakdowns from top winners Clovis Mint & Wyatt Walls. Inside: real exploits, winning strategies, & lessons for anyone serious about AI security. Read it: Link below
We're excited to announce the Call for Papers for SaTML 2026, the premier conference on secure and trustworthy machine learning @satml_conf We seek papers on secure, private, and fair learning algorithms and systems. 👉 satml.org/call-for-paper… ⏰ Deadline: Sept 24
LoRA is amazing for finetuning large models cheaply, but WHERE you place the adapters makes a huge difference. Most people are just guessing where to put them (Attention, MLP, etc). Meet "PLoP" (Precise LoRA Placement) 🎯, our new method for automatic LoRA placement 🧵
WOW! 🤯 this groundbreaking dataset from Meta’s Chief AI Scientist has revolutionized the way that we understand vision 👀 🚀 is this one of the highest-impact releases of all time?? ⏳🔥 10 crazy examples below: 🧵
A mental model I find useful: all data acquisition (web scrapes, synthetic data, RL rollouts, etc.) is really an exploration problem 🔍. This perspective has some interesting implications for where AI is heading. Wrote down some thoughts: yidingjiang.github.io/blog/post/expl…
We now know RL agents can zero-shot crush driving benchmarks. Can we put them on a car and replace the planning stack? We're hiring a postdoc at NYU to find out! Email me if interested and please help us get the word out.
Congrats, Dr. @BruceLeeIII, for your epic Ph.D. on learning-enabled control! And I'm glad you finally got to show off that stick balancing trick you've been working on for the last five years 🚀🚀🚀
Congratulations Dr.@BruceLeeIII on your brilliant thesis defense! An absolute tour de force on statistical limits and efficient algorithms for learning-enabled control. It's been a pleasure to work with and learn from you, and excited to see what you do next @ETH_AI_Center!
🥳🥳🥳I defended my PhD thesis today! Special thanks to my wonderful advisor @zicokolter and committee members @rsalakhu @gneubig @LesterMackey! 🎉🎉🎉I am joining @OpenAI as a researcher, super excited to keep working on frontier models and meet everyone in SF!
Attending RSS at USC next week? We are organizing a workshop on "Statistical Uncertainty Quantification in the Era of AI-Enabled Robots" and have a fantastic lineup of speakers from academia and industry: sites.google.com/view/rss2025-w…. Looking forward to seeing many of you 😎