Been Kim
@_beenkim
Research Scientist at Google DeepMind, PhD from MIT. Make machines empower people.
‼️Skibidi for Machines! :) Developing language 🔠 between humans🧒 and machines🤖 has long been a dream - the language that will help us expand what we know so that we can communicate with machines better, and create machines better align with us. With @johnhewtt's amazing…
Understanding and control are two sides of the problem of communicating differing concepts between humans and machines. New position paper: Robert Geirhos, @_beenkim, and I argue we must develop neologisms - new words - for human and machine concepts to understand and control AI
The one and only @_beenkim on Agentic Interpretability and Neologism: What LLMs Can Offer Us!
Come chat with me at our ICML poster about interpretability as a communication problem, and the need to derive new words for referencing language model concepts! 4:30PM-7, East Exhibition Hall A-B #E-500 We Can’t Understand AI Using our Existing Vocabulary
Understanding and control are two sides of the problem of communicating differing concepts between humans and machines. New position paper: Robert Geirhos, @_beenkim, and I argue we must develop neologisms - new words - for human and machine concepts to understand and control AI
Join us at 09:10 for Been’s talk on Agentic Interpretability and Neologism: what LLMs can offer us.
Going to #ICML2025 tomorrow - Sat morning! If you are graduating this year with a PhD, and you are interested in Google DeepMind, send me a message. Where I will be: 0. Wed 1pm @WiMLworkshop Mentoring Table and 2pm panel discussion 1. Wed 4:30pm East Exhibition Hall A-B…
Talk panel“The Unsolved Problems of AI: What We’re Still Getting Wrong” 🤦♀️ Featuring Ana Lucic, Been Kim, Furong Huang, moderated by Natasha Jaques. Enough with LLM hype 🥱 Is transformer enough to scale AGI? Does architecture matter much? #WiML #ICML2025
Say hi 👋to @ziwphd ,@MeeraHahn, @_beenkim, Wenjun Zeng and Rich Galt at #ICML2025 if you're interested in learning more about what we've been cooking on proactive T2I agents @GoogleDeepMind. Schedule 👇 Paper: arxiv.org/abs/2412.06771 Google DeepMind Booth Demo: 🕐 9:30am PDT,…
Check out our tech report on proactive T2I agents that ask clarification questions to reduce uncertainty! With this agent, we obtain 2 times higher VQAScore in just 5 turns!🤯 We've open-sourced our agent code powered by #Gemini @GoogleDeepMind! 🚀 Code:github.com/google-deepmin…
Going to #ICML2025 tomorrow - Sat morning! If you are graduating this year with a PhD, and you are interested in Google DeepMind, send me a message. Where I will be: 0. Wed 1pm @WiMLworkshop Mentoring Table and 2pm panel discussion 1. Wed 4:30pm East Exhibition Hall A-B…
Excited to give the opening keynote at bidirectional human AI alignment workshop time at 9am! And adding a picture with @ylecun after being stopped every second by folks who wanted to take pictures with him (we were just walking out of ICLR board meeting). The peer pressure was…
🚀 #ICLR2025 & #CHI2025 are just around the corner — and we’re excited to welcome you to our Bidirectional 👫Human-AI🤖 Alignment events! 🏅 "Golden Sponsors"🏅 A heartfelt thank you to our two generous Golden Sponsors: 🌟@Prolific and 🌟@Layer6AI of @TDBank_US! Their…
Huge thanks to the #ICLR2025 Organizing Committee (including many who couldn't make it to the conference) 👏👏👏
See you in Singapore! #ICLR2025
🚀 #ICLR2025 & #CHI2025 are just around the corner — and we’re excited to welcome you to our Bidirectional 👫Human-AI🤖 Alignment events! 🏅 "Golden Sponsors"🏅 A heartfelt thank you to our two generous Golden Sponsors: 🌟@Prolific and 🌟@Layer6AI of @TDBank_US! Their…
As AI becomes increasingly complex, new language is needed to improve communication between humans and machines, @GoogleDeepMind senior staff research scientist @_beenkim said in a lecture @Princeton Watch the talk: bit.ly/4jhz5Mi
Thrilled and grateful for the invitation from @HDRUNDP to share our research on proactive AI. Such a valuable opportunity to discuss its potential impact on creating beneficial AI for all - insights that hopefully resonate with the UN Human Development Report!
We are grateful to @ziwphd of @GoogleDeepMind for sharing insights from her research on proactive agents for more accessible and inclusive human-#AI co-creation and its broader implications for creating beneficial AI that serves a diverse global community.
♟️♟️Now our work on teaching superhuman chess strategies to grandmasters (one of whom @DGukesh who became the latest and the youngest world chess champion) is published on PNAS! 🎉🎉 Yes, we can transfer machine knowledge to humans to push the frontier of human. knowledge.…
Excited to share that our paper "Bridging the human–AI knowledge gap through concept discovery and transfer in AlphaZero" is now out in PNAS! With @weballergy, @banburismus_, @demishassabis, @ulrichpaquet, @_beenkim 🎉 📄 doi.org/10.1073/pnas.2…
🥁Introducing Gemini 2.5, our most intelligent model with impressive capabilities in advanced reasoning and coding. Now integrating thinking capabilities, 2.5 Pro Experimental is our most performant Gemini model yet. It’s #1 on @lmarena_ai leaderboard. 🥇