←
bagel.com422 posts
bagel.com avatar

bagel.com

@bageldotcom

General World Models. We're hiring: bagel.com/careers

◷ Joined June 2023▧ 43 Photos and videos
bagel.com avatar
bagel.com@bageldotcom·Oct 14

Our first-party foundation model is controlling this robot to make coffee, fully autonomously. We are looking for robotics teams to work with on real world applications. Tell us what you are building. bagel.com/partner

This fully autonomous demo shows a Bagel Labs foundation model controlling a robot to make coffee. We previously released WorldDiT, our lightweight architecture for robot foundation models. At the time of release, it was on the Pareto frontier for model size and performance. We have since been refining this architecture to handle longer horizon, more useful tasks fully autonomously. Making coffee means getting a whole sequence of actions right. Each step depends on the result of the last, so small mistakes can build up as the task continues. Getting this to work with a small model is especially challenging. This demo is an example of what the model can do today. If you are deploying robots or have existing hardware you want to make autonomous, we would like to partner with you. bagel.com/partner

1:32
bagel.com avatar
bagel.com@bageldotcom·Nov 5

A relevant talk if you want to understand which industries are adopting Physical AI today!

I will be talking about physical AI at @WebSummit lisbon center stage next week. Anyone there next week interested in the same topics, please HMU!

Post attachment
Bidhan Roy avatar
⟳ bagel.com retweeted
Bidhan Roy@bidhan·Nov 5

I will be talking about physical AI at @WebSummit lisbon center stage next week. Anyone there next week interested in the same topics, please HMU!

Post attachment
Bidhan Roy avatar
⟳ bagel.com retweeted
Bidhan Roy@bidhan·Oct 14

This fully autonomous demo shows a Bagel Labs foundation model controlling a robot to make coffee. We previously released WorldDiT, our lightweight architecture for robot foundation models. At the time of release, it was on the Pareto frontier for model size and performance. We have since been refining this architecture to handle longer horizon, more useful tasks fully autonomously. Making coffee means getting a whole sequence of actions right. Each step depends on the result of the last, so small mistakes can build up as the task continues. Getting this to work with a small model is especially challenging. This demo is an example of what the model can do today. If you are deploying robots or have existing hardware you want to make autonomous, we would like to partner with you. bagel.com/partner

1:32
Bidhan Roy avatar
⟳ bagel.com retweeted
Bidhan Roy@bidhan·Sep 30

Toronto Robotics night was back for ROSCon. And it was a blast!

Post attachmentPost attachmentPost attachmentPost attachment

ROSCon is in Toronto this week. Tonight, we’re hosting Toronto Robotics Night for people here for the conference and the local robotics community. Come by after the sessions for drinks and appetizers. We start at 6:30, a 5 minute walk from the ROSCon venue. RSVP to join: luma.com/501ufk17

bagel.com avatar
bagel.com@bageldotcom·Sep 24

ROSCon is in Toronto this week. Tonight, we’re hosting Toronto Robotics Night for people here for the conference and the local robotics community. Come by after the sessions for drinks and appetizers. We start at 6:30, a 5 minute walk from the ROSCon venue. RSVP to join: luma.com/501ufk17

mirian avatar
⟳ bagel.com retweeted
mirian@mirimayer·Sep 21

we're hosting a ROSCon special edition of Bagel's Toronto Robotics Night this week! we're gathering people who are globally shaping physical AI in one room to wrap up the conference together for researchers, founders, robotics engineers, and builders RSVP here: luma.com/501ufk17

Bidhan Roy avatar
⟳ bagel.com retweeted
Bidhan Roy@bidhan·Aug 28

The first toronto robotics night was a grand success!

Post attachmentPost attachmentPost attachmentPost attachment

Some of the most interesting work in robotics now sits between world models and real machines. We’re bringing the people working on both together this Thursday at the first ever Toronto Robotics Night. Come by if you're in town : luma.com/83qrbegr

bagel.com avatar
bagel.com@bageldotcom·Aug 26

Some of the most interesting work in robotics now sits between world models and real machines. We’re bringing the people working on both together this Thursday at the first ever Toronto Robotics Night. Come by if you're in town : luma.com/83qrbegr

Bidhan Roy avatar
⟳ bagel.com retweeted
Bidhan Roy@bidhan·Jul 28

Hardware is a big constraint in robotics, that's why we don't think the answer will be increasingly larger VLM models as action backbones. We tried to solve that issue with WorldDiT, which is at the pareto frontier for size-performance. Now I want to see how far we can scale it without losing this tradeoff. Here's a simulation demo.

0:16

We are releasing WorldDiT, a unified architecture for robotics world modeling and control. On the LIBERO benchmark, it performs the best among all publicly released methods that do not need a VLM to generate actions. Its size and performance sit on the reported Pareto frontier.

Post attachment
Santiago avatar
⟳ bagel.com retweeted
Santiago@svpino·Jul 28

The new WorldDiT robotics model is really cool: It's very small (< 1B parameters), yet it can perform prediction and control in a single model. • It can predict how the world will change • It then decides what the robot should do Models are getting smaller and more capable. We are doing more with way less.

We are releasing WorldDiT, a unified architecture for robotics world modeling and control. On the LIBERO benchmark, it performs the best among all publicly released methods that do not need a VLM to generate actions. Its size and performance sit on the reported Pareto frontier.

Post attachment
bagel.com avatar
bagel.com@bageldotcom·Jul 28

We are releasing the paper, model checkpoints, a self contained inference runtime, and a LIBERO evaluator. You can find everything below. 📜 arxiv.org/abs/2607.23909 🤗 huggingface.co/bageldotcom/w…

bagel.com avatar
bagel.com@bageldotcom·Jul 28

During inference, WorldDiT acts for a few steps, observes what changed, and replans. World modeling stays in training, while light-weight deployment remains action only.

Post attachment
bagel.com avatar
bagel.com@bageldotcom·Jul 28

WorldDiT learns to sample robot actions and predict a future view of the world in parallel through one diffusion backbone. That richer signal helps it reach strong LIBERO results with far fewer parameters. Table below shows the full benchmark comparison.

Post attachment