Niharika Jain

not all treasure is silver and gold, mate

[Skild AI @SkildAI]

We just hit 100M ARR within 10 months of starting deployments.

We are in factory lines. On construction sites. In kitchens. In data centers.

Cleaning. Welding. Building. Cooking.

Deploying.

[Shikhar Bahl @shikharbahl]

In-context learning!!

We’ve spent years in robotics assuming a new task means new data. Collect demos —> finetune —> eval —> repeat.

S1 is much more elegant and intuitive: show it one video of an unseen and the model just works. No fine-tuning or gradient updates needed.

It can do so many complex tasks, even ones that run for 10 minutes or longer. It’s especially impressive to see completely new behaviors emerge at test time, like flipping a pancake, even though that behavior never appeared in the training data.

It’s amazing to see S1 pick up a new task from a single example - something I really thought was still years away.

[Skild AI @SkildAI]

Introducing S1, our new foundation model that learns from one example.

It can be taught 10-minute long tasks that it has never seen before, from one video prompt without any fine-tuning.

Watch S1 operate in real-time via in-context learning:

[Skild AI @SkildAI]

Humans learn by watching. Robots should too.

[ICMR @ICMRDELHI]

Hon'ble HFM @JPNadda lauds "Vishanu Yuddh Abhyas" – A groundbreaking pandemic preparedness drill under the National One Health Mission! DHR-ICMR along with other Central & state organizations united to assess & strengthen our readiness for zoonotic outbreaks. @PMOIndia

[Shikhar Bahl @shikharbahl]

🚀 Beyond excited to be part of the stellar team @SkildAI! It’s been an amazing journey so far, and a privilege working with and learning from my incredible colleagues! I’m really looking forward to what’s ahead. If you would like to join our journey towards general-purpose robots please reach out: https://t.co/xxqq1fm3Vw!

[CMU School of Computer Science @SCSatCMU]

New research from @CMU_Robotics @deepakpathak enables robots to learn household chores by watching videos of people performing everyday tasks in their homes.
https://t.co/fTPxbG7UdX

[TechXplore @TechXplore_com]

Researchers expand ability of robots to learn from videos @carnegiemellon https://t.co/0XOas2QXh8

[AI Breakfast @AiBreakfast]

Robots have developed the skill to learn by watching videos:

The Visual-Robotics Bridge (VRB) model can teach a robot a new task in roughly 25 minutes using only reference video - without needing human interaction or a simulated environment.

[TechCrunch @TechCrunch]

Robots learn to perform chores by watching YouTube https://t.co/vpjWQ6BSm0 by @bheater

[Deepak Pathak @deepakpathak]

🤖 Robotics often faces a chicken and egg problem: no web-scale robot data for training (unlike CV or NLP) b/c robots aren't deployed yet & vice-versa.

Introducing VRB: Use large-scale human videos to train a *general-purpose* affordance model to jumpstart any robotics paradigm!

[AK @_akhaliq]

Affordances from Human Videos as a Versatile Representation for Robotics

abs: https://t.co/GY8tG95aHY
project page: https://t.co/MfjxsBfwdy

[Shikhar Bahl @shikharbahl]

Nice overview article covering our RSS 2022 work (WHIRL) and home robotics in general!

[Shikhar Bahl @shikharbahl]

Super excited to share recent work on WHIRL: In-the-Wild Human Imitating Robot Learning - the robot learns in just 1-2 hours of interaction!

[Deepak Pathak @deepakpathak]

How can we enable robots to perform diverse tasks? Designing rewards or demos for each task is not scalable.

We propose WHIRL which learns by watching a single human video followed by autonomous exploration *directly* in the real world (no simulation)!

https://t.co/7XlOf4OyEm

[AK @_akhaliq]

Human-to-Robot Imitation in the Wild
abs: https://t.co/npKpj0ORFS
project page: https://t.co/yFi5xJuA1q

[Niharika Jain @Njainn]

@aditya_bahl YES everyone come!!!

[Shikhar Bahl @shikharbahl]

Excited to share our paper at RSS 2021 this week on Hierarchical Neural Dynamic Policies (H-NDPs)!

Can robots perform tasks in a dynamic fashion, just like humans? Can we learn *real-world dynamic skills* in a *generalizable* manner?
https://t.co/WRoJzyYBgZ

1/9

[OfficialJayKing @__JayyKing]

Dear UPS, USPS, FedEx, & Amazon employees..

Thank you.

[Niharika Jain @Njainn]

@umzkrish FACTS.