Alex Robey
@AlexRobey23
Followers
1K
Following
11K
Media
104
Statuses
649
AI researcher. Current postdoc at @mldcmu, Ph.D. from @Penn, B.S. & B.A. from @Swarthmore, working with @GraySwanAI, formerly @GoogleAI, @Livermore_Lab.
Pittsburgh, PA
Joined July 2020
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. 🧵
21
141
404
RT @steph_milani: 🌻 Excited to announce that I’ve moved to NYC to start as an Assistant Prof/Faculty Fellow at @nyuniversity! . If you’re i….
0
20
0
RT @HaiminHu: Excited to share some life updates:. I successfully defended my thesis, written under the guidance of my advisor Prof. Jaime….
0
9
0
RT @LarsLindemann2: We’re excited to host the 8th Learning for Dynamics & Control (L4DC) Conference at the University of Southern Californi….
0
11
0
RT @maksym_andr: 🚨 Incredibly excited to share that I'm starting my research group focusing on AI safety and alignment at the ELLIS Institu….
0
89
0
RT @andyzou_jiaming: We deployed 44 AI agents and offered the internet $170K to attack them. 1.8M attempts, 62K breaches, including data l….
0
394
0
RT @abeirami: If you are interested in safety/security jailbreaking of LLMs, defenses against them, and how the safety issues become more c….
0
17
0
RT @davisbrownr: Our dataset of open algebraic combinatorics questions received an oral, and is being presented today at ICML! the talk is….
0
1
0
RT @hhsun1: 🚨 Postdoc Hiring:.I am looking for a postdoc to work on rigorously evaluating and advancing the capabilities and safety of comp….
0
30
0
RT @pratyushmaini: At #ICML2025, I am super excited to introduce STAMP. This is a marriage b/w dataset inference & watermarking that finall….
0
15
0
RT @TuhinChakr: Honored to get the outstanding position paper award at @icmlconf :) Come attend my talk and poster tomorrow on human center….
0
13
0
RT @_vaishnavh: Today @ChenHenryWu and I will be presenting our #ICML work on creativity in the Oral 3A Reasoning session (West Exhibition….
0
18
0
The tutorial website is still under construction :). Following the tutorial, all of our slides + a write-up of our talk, extended references, links to code, and more will be available at
0
0
8
On Monday, I'll be presenting a tutorial on jailbreaking LLMs + the security of AI agents with @HamedSHassani and @aminkarbasi at ICML. I'll be in Vancouver all week -- send me a DM if you'd like to chat about jailbreaking, AI agents, robots, distillation, or anything else!.
2
9
77
RT @yidingjiang: I will be at ICML next week. If you are interested in chatting about anything related to generalization, exploration, and….
0
9
0
RT @pinyuchenTW: [@icmlconf thread] .I'll be giving an #ICML2025 expo talk on computational safety for #GenAI (4pm, July 13th) and an invit….
0
4
0
RT @nmallinar: Super excited to share that we have an Oral presentation for this paper next week at ICML!. It will be on Tuesday at 10am (O….
0
3
0
RT @GraySwanAI: The wait is over. Our full recap of the Agent Red Teaming Challenge is here. featuring breakdowns from top winners Clovis….
0
3
0
RT @mlsec: We're excited to announce the Call for Papers for SaTML 2026, the premier conference on secure and trustworthy machine learning….
0
15
0
RT @hayou_soufiane: LoRA is amazing for finetuning large models cheaply, but WHERE you place the adapters makes a huge difference. Most peo….
0
5
0
RT @willccbb: WOW! 🤯 this groundbreaking dataset from Meta’s Chief AI Scientist has revolutionized the way that we understand vision 👀 🚀 is….
0
47
0