New paper out! 🎉 SHIFT: Steering Hidden Intermediates in Flow Transformers — activation steering, but for DiT diffusion models.
arxiv.org/abs/2604.09213
🧵 thread:
Is it possible to build a multi-domain action model capable of adapting to unseen dynamics?
Check out our new #ICLR2026 paper! We pushed in-context RL scaling further and released Vintix II.
👇👇👇
🤩Excited to share our #AAAI2026 Oral on #EmbodiedAI:
How can robots learn from noisy, unlabeled videos—like those on the internet—without action labels?
Our new work, Object-Centric Latent Action Learning, tackles exactly this.
Thread ↓
Thanks to @RealAAAI for the conference. So many interesting new connections. Hope that now more people are aware of the beauty of latent actions for robotics 🤖
#aaai2026 #robots#ai#aaai#Singapour
Don't forget to visit my oral or/and poster today on scalable imitation learning via object-centric pretraining.
Oral: Garnet 218 @ 9:50 am
Poster: Hall 4
Also, feel free to reach out if you want to chat about continual, imitation and/or reinforcement learning while at AAAI!
🤩Excited to share our #AAAI2026 Oral on #EmbodiedAI:
How can robots learn from noisy, unlabeled videos—like those on the internet—without action labels?
Our new work, Object-Centric Latent Action Learning, tackles exactly this.
Thread ↓
9/9 If you're at AAAI or interested in world models, imitation learning, or object-centric RL, check out our paper: arxiv.org/abs/2502.09680
Oral session: Jan 22, 9:30-10:00 Garnet 218
Poster session: Jan 22, Hall 4
Code (coming soon): github.com/dunnolab/objec…
🤩Excited to share our #AAAI2026 Oral on #EmbodiedAI:
How can robots learn from noisy, unlabeled videos—like those on the internet—without action labels?
Our new work, Object-Centric Latent Action Learning, tackles exactly this.
Thread ↓
We released 87 hours of @LeRobotHF SO 100/101 datasets.
It is a unified, cleaned, and annotated repackage of 598 open-source community datasets (SO100 and SO101), totaling 22,709 episodes, ~9.4M frames, and 563 tasks.
I’m asking for help. I was meant to start my PhD with @_rockt and @robertarail at UCL, but my UK background check was refused. My appeal seems unlikely to succeed, so I’m urgently searching for any PhD or research positions in academia or industry. Any help is appreciated.
🚀 Introducing cadrille: a new SOTA model for CAD reconstruction from images, point clouds, and text—all in one framework with the use of RLVR.
Multimodal inputs + RLVR = clean, editable 3D models.
🧵👇
LLMs are amazing because they can learn in context — read, adapt, and act.
Can we do the same for reinforcement learning? That’s the promise of In-Context RL (ICRL).
But existing offline ICRL methods don’t even optimize rewards.
Our new paper shows why RL matters
🧵
9 Followers 192 FollowingTeaching Assistant at National University of Science and Technology POLITEHNICA Bucharest, Faculty of Automatic Controls and Computers, Bucharest, Romania
2K Followers 2K FollowingNLP postdoc at @SheffieldNLP
Ex @Imperial_NLP PhD, @Apple AI/ML Scholar, @UCL MSc
Model robustness and now uncertainty quantification
4K Followers 2K FollowingHead of Volumetric 3D Video at Meta
Prev Projects: Hyperscape, MapAnything, Dynamic 3D Gaussian Splatting, SplaTAM, HOTA +more
Prev PhD at RWTH + CMU + Oxford
329 Followers 5K FollowingAGI Safety researcher (Independent), MARS Fellow(Cambridge AI Safety Hub), BASIS Fellow @UCBerkeley, Get Published or Die Trying.
3K Followers 2K Following発言は個人の見解に基づくものであり,所属組織を代表するものではありません
自律移動,脚ロボの強化学習,アームの模倣・基盤モデル
SLAM, Localization, Navigation,
Reinforcement Learning,
BC, Foundation Model for all robots
590K Followers 52K FollowingSan Francisco/Silicon Valley AI | Robots, holodecks, BCIs, analysis of new things | Ex-Microsoft, Rackspace, Fast Company | Wrote eight books about the future.
203 Followers 678 FollowingPhD student @JHUCLSP. Interested in LLM agents, computer systems, and economics of computation. Previously @BrownBigAI, @AWS. 🦋 is same handle
343 Followers 364 FollowingPost-Doc @IkimUme
Phd. in Causal Discovery from CISPA Helmholtz Center for Information Security, Saarbruecken |
@[email protected]. | Opinions are my own
52 Followers 137 FollowingNovelty Search & Neural Evolution
Q: "What makes someone truly creative? What is the main driving force?"
BSc & MSc in Mathematics
4K Followers 1K FollowingAssistant Professor @BristolUni, PhD @UCL AI Center, prev. intern @TikTok & @Microsoft. ✨ Reinforcement Learning, Causality, World Models. 🎮 Game Fan!
46K Followers 905 FollowingCreator of bitsandbytes. Professor @CarnegieMellon and Research Scientist @allen_ai . I blog about deep learning and PhD life at https://t.co/Y78KDJJFE7.
5K Followers 1K Followingrecent phd graduate @CMU_Robotics, working on the algorithmic foundations and science of interactive decision-making. prefers email. on the job market!
2K Followers 2K FollowingNLP postdoc at @SheffieldNLP
Ex @Imperial_NLP PhD, @Apple AI/ML Scholar, @UCL MSc
Model robustness and now uncertainty quantification
590K Followers 52K FollowingSan Francisco/Silicon Valley AI | Robots, holodecks, BCIs, analysis of new things | Ex-Microsoft, Rackspace, Fast Company | Wrote eight books about the future.
329 Followers 5K FollowingAGI Safety researcher (Independent), MARS Fellow(Cambridge AI Safety Hub), BASIS Fellow @UCBerkeley, Get Published or Die Trying.
203 Followers 678 FollowingPhD student @JHUCLSP. Interested in LLM agents, computer systems, and economics of computation. Previously @BrownBigAI, @AWS. 🦋 is same handle
152K Followers 7K FollowingCompiling in real-time, the race towards AGI.
The Largest Show on X for AI.
🗞️ Get my daily AI analysis newsletter to your email 👉 https://t.co/6LBxO8215l
31K Followers 93 FollowingFounded in 1979, AAAI is an international, nonprofit, scientific society devoted to promote research in, and responsible use of Artificial Intelligence.