What a great start of IEEE ICRA. The #icra2022 workshop on #cobots and Work of the Future MIT organised by Nadia Figueroa, PhD, Julie Shah, Chris Fourie, Ben Armstrong & co-organisers was wonderful! sites.google.com/view/icra22ws-…

New paper (to appear in ICML)! Using a new prototype-based classifier, we show how notions of fair and hierarchical classification are tightly related, and how we can directly control "concept relationships" to switch between modes.

📣 Very excited to announce our in-person #NeurIPS2022 workshop on Information-Theoretic Principles in Cognitive Systems! Check out our lineup of invited speakers and CFP, submit short papers by September 19 sites.google.com/view/infocog-n… #InfoCog2022 NeurIPS Conference

It's Monday morning, which means it's the perfect time to start thinking about information theory, brains, and neural nets! Submit to #InfoCog2022 NeurIPS Conference Organized by Noga Zaslavsky Sam Gershman Stephanie E. Palmer Jessica Flack sites.google.com/view/infocog-n…

Happy to announce... Well, this paper didn't get in, but I still think it's neat. Using the same probe-based method for testing if language models use representations of syntax, we can "fix" RL agent perception (e.g., notice an oncoming car): arxiv.org/abs/2201.12938

New journal paper on Latent Space Alignment! Neural agents learn latent representations spaces, but often each agent learns its own idiosyncratic space. How can we align those space among agents or even with humans? tandfonline.com/doi/full/10.10…

Super grateful for this chance to continue exciting *interdisciplinary* research. Thanks to my advisor, Julie Shah, but also so many collaborators from other departments (Roger Levy and Noga Zaslavsky) and inspiring labmates and researchers.

Before everyone flees twitter... new paper coming out at NeurIPS! Humans compress meanings into complexity limited discrete representations (words). Can neural nets learn similar communication? Yes! (1/7)

Neat work combining ideas from formal methods, stable control policies, and imitation learning!

Talk to Serena at AAAI about how standard reward tuning via trial-and-error has many lurking dangers!

Announcing Versatile Demonstration Interface (VDI) – a tool for collaborative robots that makes it easier to collect task demonstrations using three common Learning from Demonstration approaches.

Want your robot to clean the kitchen your way? 🧹✨ 🔗yanweiw.github.io/itps/" Introducing Inference-Time Policy Steering: a training-free method that lets you specify where and how to manipulate objects, so you can guide non-interactive policies to align with your preferences!

Excited to present our #NeurIPS2024 Oral talk! 🚀 Enhancing Preference-based Linear Bandits via Human Response Time Coffee or tea? If you choose instantly, you likely have a strong preference. How can AI leverage this psychological insight to better learn human preferences?

.MIT CSAIL PhD candidate Felix Yanwei Wang is in the final year of his program working with the lab’s Interactive Robotics Group, researching robot learning, specifically inference-time policy alignment through human interactions. Read more about Felix: bit.ly/445dEtA