Загрузка видео...

Не удалось загрузить видео

На главную

zero shot towel folding attempt. RL next

k7agar's profile picture

atharva ☆

12,134 subscribers

20,459 просмотров • 2 месяцев назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 17

Фото профиля atharva ☆
atharva ☆2 месяцев назад

📍

Фото профиля Lucas
Lucas2 месяцев назад

you should train a reward model on how smooth or elegant a motion is, pairwise with a bunch of uni or teleop samples. GRPO with that comes out so much better!

Фото профиля Jim Bohnslav
Jim Bohnslav2 месяцев назад

info on the hardware?

Фото профиля Chidhambararajan R (a.k.a Chidha)
Chidhambararajan R (a.k.a Chidha)2 месяцев назад

Are those 2 s0101 arms?

Фото профиля OT
OT2 месяцев назад

BIG YAM spotted

Фото профиля 별별이
별별이2 месяцев назад

lets go higher!!

Фото профиля abhi
abhi2 месяцев назад

wowza

Фото профиля Andrew I. Christianson
Andrew I. Christianson2 месяцев назад

this is good stuff 🔥🔥🔥

Фото профиля Mr. Rc
Mr. Rc2 месяцев назад

woahhhhhhhhhhhhhhhhhhh

Фото профиля Sibhi Balamurugan
Sibhi Balamurugan2 месяцев назад

Waww

Фото профиля Tirth Gada
Tirth Gada2 месяцев назад

lessgoo

Фото профиля Dev
Dev2 месяцев назад

cooked 🫡

Фото профиля Sahil Apage
Sahil Apage2 месяцев назад

lessgo finally!!

Фото профиля Rishikesh
Rishikesh2 месяцев назад

Insane, are you in Bangalore?

Фото профиля ishaan
ishaan2 месяцев назад

arm kit? do share any blog you write on this newbie here starting again after a long time :)

Фото профиля sarayu
sarayu2 месяцев назад

my goat

Фото профиля 4nshh
4nshh2 месяцев назад

Finallyyyy

Похожие видео

Oops, towel folding i2RT
0:25

Oops, towel folding i2RT

ETH Robotics Club

25,222 просмотров • 11 месяцев назад

A reward model that works, zero-shot, across robots, tasks, and scenes? Introducing Robometer: Scaling general-purpose robotic reward models with 1M+ trajectories. Enables zero-shot: online/offline/model-based RL, data retrieval + IL, automatic failure detection, and more! 🧵 (1/12)
2:01

A reward model that works, zero-shot, across robots, tasks, and scenes? Introducing Robometer: Scaling general-purpose robotic reward models with 1M+ trajectories. Enables zero-shot: online/offline/model-based RL, data retrieval + IL, automatic failure detection, and more! 🧵 (1/12)

Jesse Zhang ✈️ CoRL 2026

103,572 просмотров • 8 месяцев назад

connor has him folding under zero pressure
0:22

connor has him folding under zero pressure

ilya bizanov

134,066 просмотров • 7 месяцев назад

Midnight will help stop Kelp DAO hacks with next gen private DEXs, Trusted Execution Environments, Multi-Party Computation, and folding zero-knowledge proofs.
1:06

Midnight will help stop Kelp DAO hacks with next gen private DEXs, Trusted Execution Environments, Multi-Party Computation, and folding zero-knowledge proofs.

Input Output Group

18,160 просмотров • 6 месяцев назад

jeongin was done with his towel so he was folding it really neatly and cutely 🥹🫳
0:21

jeongin was done with his towel so he was folding it really neatly and cutely 🥹🫳

lena ✰

22,986 просмотров • 1 год назад

Ready for the next RL
0:21

Ready for the next RL

Rolling Loud

241,232 просмотров • 1 год назад

RL from Next talks about Brandy
0:56

RL from Next talks about Brandy

Dionne

12,947 просмотров • 9 месяцев назад

Meet BFM-Zero: A Promptable Humanoid Behavioral Foundation Model w/ Unsupervised RL👉 🧩ONE latent space for ALL tasks ⚡Zero-shot goal reaching, tracking, and reward optimization (any reward at test time), from ONE policy 🤖Natural recovery & transition
1:17

Meet BFM-Zero: A Promptable Humanoid Behavioral Foundation Model w/ Unsupervised RL👉 🧩ONE latent space for ALL tasks ⚡Zero-shot goal reaching, tracking, and reward optimization (any reward at test time), from ONE policy 🤖Natural recovery & transition

Yitang Li

84,263 просмотров • 1 год назад

New video of Figure's Helix AI model in action: a human keeps tossing a towel in the middle, the humanoid robot keeps folding away.
1:10

New video of Figure's Helix AI model in action: a human keeps tossing a towel in the middle, the humanoid robot keeps folding away.

The Humanoid Hub

115,642 просмотров • 1 год назад

2pac ft RL of Next - Until The End Of Time
4:30

2pac ft RL of Next - Until The End Of Time

HomeOfHipHop

21,018 просмотров • 1 месяц назад

RL from Next Perform 'Too Close' on The Cadillac Chronicles
0:46

RL from Next Perform 'Too Close' on The Cadillac Chronicles

RNB RADAR

566,476 просмотров • 1 год назад

Which Raptor threw a towel at Josh after he shot em up?
0:54

Which Raptor threw a towel at Josh after he shot em up?

New York Basketball

993,758 просмотров • 9 месяцев назад

"NEXT DOESN'T HAVE THE DISCOGRAPHY FOR A VERZUZ." - RL?‼️🤔
1:14

"NEXT DOESN'T HAVE THE DISCOGRAPHY FOR A VERZUZ." - RL?‼️🤔

SoulFood66

64,815 просмотров • 12 дней назад

Shai flopped on every single shot attempt.
0:36

Shai flopped on every single shot attempt.

House of Lowlights

23,112,119 просмотров • 5 месяцев назад

Boston Dynamics taught Atlas a Rabona kick. Learned from human mocap, retargeted to Atlas, trained in sim via RL, deployed zero-shot to the real robot. Soccer skills demand whole-body coordination, and similar recipe transfers to warehouse work.
0:58

Boston Dynamics taught Atlas a Rabona kick. Learned from human mocap, retargeted to Atlas, trained in sim via RL, deployed zero-shot to the real robot. Soccer skills demand whole-body coordination, and similar recipe transfers to warehouse work.

The Humanoid Hub

11,338 просмотров • 5 месяцев назад

Our model can now learn from its own experience with RL! Our new π*0.6 model can more than double throughput over a base model trained without RL, and can perform real-world tasks: making espresso drinks, folding diverse laundry, and assembling boxes. More in the thread below.
3:50

Our model can now learn from its own experience with RL! Our new π*0.6 model can more than double throughput over a base model trained without RL, and can perform real-world tasks: making espresso drinks, folding diverse laundry, and assembling boxes. More in the thread below.

Physical Intelligence

713,202 просмотров • 11 месяцев назад

RL of Next Takes Us Back With “Butta Love” #live #music #performance #nostalgia
0:58

RL of Next Takes Us Back With “Butta Love” #live #music #performance #nostalgia

Cadillac Chronicles

11,949 просмотров • 1 месяц назад

Introducing RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning. 7 real robot tasks, 900/900 successes. Up to 250 consecutive trials in one task, running 2 hours nonstop without failure. High success rate against physical disturbances, zero-shot, and few-shot adaptation Our first step toward a deployable robot learning system.
3:26

Introducing RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning. 7 real robot tasks, 900/900 successes. Up to 250 consecutive trials in one task, running 2 hours nonstop without failure. High success rate against physical disturbances, zero-shot, and few-shot adaptation Our first step toward a deployable robot learning system.

Kun Lei

92,873 просмотров • 1 год назад

Every Clutch Shot Attempt From Arkansas Darius Acuff Jr.
3:49

Every Clutch Shot Attempt From Arkansas Darius Acuff Jr.

NBA Replays

122,930 просмотров • 4 месяцев назад

Every clutch shot attempt from 2004 playoff Tim Duncan
1:12

Every clutch shot attempt from 2004 playoff Tim Duncan

Pitless

45,559 просмотров • 5 месяцев назад