MITRobotics @MITRobotics

We are the Interactive Robotics Group at MIT, a part of the Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Aero/Astro Department. interactive.mit.edu Cambridge, MA Joined November 2011

Tweets

331
Followers

3K
Following

70
Likes

91

MIT CSAIL Alliances @csail_alliances

5 months ago

.@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

0 3 6 398 0

Download Image

Felix Wang @felixwyw

9 months ago

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!

2 19 91 19K 39

Download Video

Shen Li @ShenLiRobot

9 months ago

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?…

Shen Li @ShenLiRobot

12 months ago

0 2 5 1K 0

Download Image

0 4 6 1K 0

Download Image

Mike Hagenow @hagenowrobotics

10 months ago

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.

1 3 5 831 1

Download Video

MITRobotics @MITRobotics

3 years ago

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

0 0 2 650 0

MITRobotics @MITRobotics

3 years ago

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

Felix Wang @felixwyw

3 years ago

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

1 9 19 3K 7

Download Video

0 1 9 1K 2

Mycal Tucker @MycalTucker

3 years ago

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)

2 25 166 0 71

Download Gif

Mycal Tucker @MycalTucker

3 years ago

Super grateful for this chance to continue exciting *interdisciplinary* research. Thanks to my advisor, @julie_a_shah, but also so many collaborators from other departments (@roger_p_levy and @NogaZaslavsky) and inspiring labmates and researchers.

Amazon Science @AmazonScience

3 years ago

0 5 14 0 1

1 3 15 0 0

Mycal Tucker @MycalTucker

3 years ago

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…

1 4 15 0 1

Mycal Tucker @MycalTucker

3 years ago

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

2 1 3 0 0

Mycal Tucker @MycalTucker

3 years ago

It's Monday morning, which means it's the perfect time to start thinking about information theory, brains, and neural nets! Submit to #InfoCog2022 @NeurIPSConf Organized by @NogaZaslavsky @gershbrain @sepalmerNeuro @C4COMPUTATION sites.google.com/view/infocog-n…

1 1 5 0 0

Noga Zaslavsky @NogaZaslavsky

3 years ago

📣 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 @NeurIPSConf

1 28 102 0 18

Mycal Tucker @MycalTucker

3 years ago

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.