←
bigAI260 posts
bigAI avatar✓

bigAI ✓

@BrownBigAI

Brown Integrative, General Artificial Intelligence @BrownUniversity

◷ Joined April 2019▧ 38 Photos and videos
bigAI avatar
bigAI@BrownBigAI·21 Aug 2019

Excited to officially announce the Brown Integrative, General Artificial Intelligence (bigAI) initiative! Our mission is to facilitate the creation of embodied, general-purpose AI that is beneficial for humanity. Follow us to hear about our latest research and more! 🤖❤️

bigAI avatar
bigAI@BrownBigAI·Sep 20

This is how we should be parameterizing skills! System 1 decision making + system 2 planning (with an autoregressive model). These Atari games are a great example of closer to system 1 decision making.

Shivam Vats avatar
⟳ bigAI retweeted
Shivam Vats@ShivaamVats·Sep 8

How can robots keep learning once deployed in the messy, ever-changing real world? Excited to announce our #CoRL2026 workshop on “Robot Learning at Deployment”! We’ll explore how robots can continually adapt and improve under real-world constraints. 🧵

Post attachment
Hongyu Li ✈️ NeurIPS avatar
⟳ bigAI retweeted
Hongyu Li ✈️ NeurIPS@Hongyu_Lii·Aug 20

What if robots, humans, and video models could all describe action in the same language? Introducing Hydra-0🐍: a generalist world model that represents robot actions as action flow. One interface. Many embodiments, tasks, and environments. 🧵1/7

1:52
Yixuan Huang avatar
⟳ bigAI retweeted
Yixuan Huang@YixuanHuang13·Jul 8

🤖 Curious about the connection between Task and Motion Planning (TAMP) and robot learning? 📄 Check out our new survey on Learning By and For Task and Motion Planning! We organize the growing literature on TAMP + learning, introduce a taxonomy of TAMP learning, clarify the state of the art, and highlight promising directions for future research. 🚀 🔗 prpl-group.com/tamp-learning…

Hongyu Li ✈️ NeurIPS avatar
⟳ bigAI retweeted
Hongyu Li ✈️ NeurIPS@Hongyu_Lii·Jul 7

Can a world model 🌏 learn to predict how 198 different deformable objects move -- not just one rope or cloth? That question motivated Deform360: 1,980 real-world interactions captured from 41 synchronized views with bimanual touch sensors, which becomes crucial when vision is occluded. Accepted at #ECCV2026. 🧵 1/5

0:10
David Tao avatar
⟳ bigAI retweeted
David Tao@Taodav·May 21

Reinforcement learning on visual first-person environments is costly: rendering engines are expensive! Enter JAXenstein: a lightning fast benchmark of first-person environments based on a pure JAX reimplementation of the Wolfenstein 3D rendering engine. (1/n)

0:06
bigAI avatar
bigAI@BrownBigAI·May 11

Checkout our new #RSS paper on improving BC policies through Online RL !

0:09
Lakshita Dodeja avatar
⟳ bigAI retweeted
Lakshita Dodeja@lakshitadodeja·Mar 18

Residual RL is a powerful strategy for adapting a pretrained base policy, but it struggles when: ❌ Exploration is uncontrolled ❌ Base policies are stochastic We tackle this in our new RAL paper “Accelerating Residual Reinforcement Learning with Uncertainty Estimation” (1/5)

0:28
bigAI avatar
bigAI@BrownBigAI·Mar 15

If you are also at #HRI2026 this week, please reach out to @IvyXHe, and @jasonxyliu about their work on using multimodal observation, foundation models, and POMDP to enable robots to reason over uncertainty about the task and the environment!

Jiahui Fu avatar
⟳ bigAI retweeted
Jiahui Fu@jiahuifu_carol·Mar 3

🤖 How can we enable robots to solve complex, multi-step manipulation tasks without a single demonstration or any task-specific training? Introducing NovaPlan: a hierarchical framework for zero-shot long-horizon manipulation. It unifies closed-loop video language planning with grounded execution, allowing robots to “imagine” visual plans, execute robustly, and autonomously recover from failures. [1/5] 🔗 Project page: nova-plan.github.io/ #EmbodiedAI #Robotics #Manipulation #FoundationModels

0:38
Gregory J. Stein avatar
⟳ bigAI retweeted
Gregory J. Stein@GregoryJStein·Feb 11

Our new paper develops robots that don’t just complete tasks: they anticipate how their actions impact what comes next. Example: when putting objects away, organizing them neatly isn’t just aesthetic—it makes future retrieval faster and easier. 📝🧵👇

0:29
Dan Haramati avatar
⟳ bigAI retweeted
Dan Haramati@DanHrmti·Feb 4

Learning accurate World Models for long horizon planning is hard. So what minimal aspect of world dynamics must a model capture to achieve complex goals? We find a simple and effective solution in our #ICLR2026 paper, which we will present as an Oral at @worldmodel_26. (1/n)

0:20