Please check out our website/paper/code!
🌐 Website: ppsteering.github.io
📝 Paper: arxiv.org/abs/2609.09148
💻 Code: github.com/TritiumR/pps
Thanks to my collaborator @TerryWang300, and to my supervisors @weichiuma and @KuanFang!
See you in Austin! #CoRL
🌐 Website: ppsteering.github.io
📝 Paper: arxiv.org/abs/2609.09148
💻 Code: github.com/TritiumR/pps
Thanks to my collaborator @TerryWang300, and to my supervisors @weichiuma and @KuanFang!
See you in Austin! #CoRL
0
0
3
441
After pivoting to embodied AI last year, this is our first time submitting to #CoRL 2026, and I’m excited to share that Show Lab has 3 out of 3 papers accepted! 🎉
Huge congratulations to the students behind these papers — all were 1st-year PhD or master students, completely new tremendous efforts to pick up the know-how of robot learning 🤖
1. Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos
How robot can learn from human demo video? Video gen model can edit human video as robot video, but how to use these generated human-edit-as-robot video for training robot?
Instead of hoping to learn how to control, we propose to guide robot learning with the geometry in the human-edit-as-robot video.
2. Where Success Breaks: Failure-Boundary Learning for Robust Vision-Language-Action Models
When training VLAs, we often focus on successful executions. But failures contain equally important information about where a robot is starting to go wrong.
We introduce Failure-Boundary Learning, reframing robust VLA adaptation as the problem of discovering, localizing, and shaping the boundary between recoverable deviations and task failure.
3. From Video Frames to Robot Meta-Frames: A Unified Latent Interface for World Action Models
World Action Models such as Cosmos Policy show great potential for jointly predicting actions and video. However, different robot signals — images, proprioception, actions, future states, and values — are typically represented as separate images, making inference computationally costly.
We introduce MetaWAM, which packs these different modalities into a single unified meta-frame in the latent space. On RoboCasa, MetaWAM achieves 68.9% success, while reducing inference latency by 39%.
Huge congratulations to the students behind these papers — all were 1st-year PhD or master students, completely new tremendous efforts to pick up the know-how of robot learning 🤖
1. Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos
How robot can learn from human demo video? Video gen model can edit human video as robot video, but how to use these generated human-edit-as-robot video for training robot?
Instead of hoping to learn how to control, we propose to guide robot learning with the geometry in the human-edit-as-robot video.
2. Where Success Breaks: Failure-Boundary Learning for Robust Vision-Language-Action Models
When training VLAs, we often focus on successful executions. But failures contain equally important information about where a robot is starting to go wrong.
We introduce Failure-Boundary Learning, reframing robust VLA adaptation as the problem of discovering, localizing, and shaping the boundary between recoverable deviations and task failure.
3. From Video Frames to Robot Meta-Frames: A Unified Latent Interface for World Action Models
World Action Models such as Cosmos Policy show great potential for jointly predicting actions and video. However, different robot signals — images, proprioception, actions, future states, and values — are typically represented as separate images, making inference computationally costly.
We introduce MetaWAM, which packs these different modalities into a single unified meta-frame in the latent space. On RoboCasa, MetaWAM achieves 68.9% success, while reducing inference latency by 39%.
1
6
40
2,017
How robot can learn from human demo video? Video gen model can edit human video as robot video, but how to use these generated human-edit-as-robot video for training robot?
Congrats @DanzerChan and the team on the #CoRL paper "Supervise What Survives" arxiv.org/abs/2606.24448 🎊 which proposes to guide robot learning with geometry in the human-edit-as-robot video.
Congrats @DanzerChan and the team on the #CoRL paper "Supervise What Survives" arxiv.org/abs/2606.24448 🎊 which proposes to guide robot learning with geometry in the human-edit-as-robot video.
🎉 Excited to share that Supervise What Survives has been accepted to #CoRL2026!
Generated robot videos are cheap but label-free. We show that human2robot generation preserves geometry while erasing control, so instead of reconstructing what's gone, GRA supervises what survives.
0
3
16
2,368
My first submission to #CoRL got accepted! 🤖
A symbolic planner will happily tell a robot to pick up something it physically can't reach. REAP learns feasibility from the very motion policies it later uses, and solves rearrangement tasks efficiently! 🧵
elicited-preconditions.github.io
A symbolic planner will happily tell a robot to pick up something it physically can't reach. REAP learns feasibility from the very motion policies it later uses, and solves rearrangement tasks efficiently! 🧵
elicited-preconditions.github.io
0
0
7
170
THE COUNTDOWN BEGINS!
A new chapter in blockchain innovation is about to unfold.
✨ Digitally Powered. Physically Secured.
📅 Official Launch: 27 June 2026
#CoralCoin #CORL #CoralBlockchain #CoralScan #CryptoLaunch #BlockchainInnovation #Web3 #DeFi #DigitalAssets #Crypto
A new chapter in blockchain innovation is about to unfold.
✨ Digitally Powered. Physically Secured.
📅 Official Launch: 27 June 2026
#CoralCoin #CORL #CoralBlockchain #CoralScan #CryptoLaunch #BlockchainInnovation #Web3 #DeFi #DigitalAssets #Crypto
50
9
81
6,966
🚀 The countdown has begun!
Introducing CORAL COIN (CORL) — a new era of blockchain innovation designed for security, transparency, and real-world utility.
coralscan.org
#CoralCoin #CORL #CoralBlockchain #Blockchain #Crypto #Cryptocurrency #Web3 #DigitalAssets #DeFi
Introducing CORAL COIN (CORL) — a new era of blockchain innovation designed for security, transparency, and real-world utility.
coralscan.org
#CoralCoin #CORL #CoralBlockchain #Blockchain #Crypto #Cryptocurrency #Web3 #DigitalAssets #DeFi
28
3
40
2,298
@yhbryankimiq #corl It's listed on Binance Alpha. The hype seems to be there right now. Maybe new $siren. It dropped from $200M cap to $200K. I hope it makes a nice rise soon. $corl Please do your own research. 🧐 dyor
0
0
1
222
🪸 #CoralFinance ($CORL) is currently trading at approx. 0.045 according to the coin market cap. It's showing solid growth since its listing.
#CORL is gaining traction and it's real.
Join here linktr.ee/coralfinance to be a part of the growing team.
#DeFi
#CORL is gaining traction and it's real.
Join here linktr.ee/coralfinance to be a part of the growing team.
#DeFi
1
0
2
231
BiKingEx🐯 Morning Market Report 📣
🔥Top Gainers by 4h on Coinglass
As of 02:11 (UTC) Today📊
#PUP: $0.00787 +49.15%
#OL: $0.03371 +11.11%
#CORL: $0.04279 +10.65%
#APR: $0.39815 +10.24%
#WBAI: $0.02255 +9.84%
🔥#ADA #HYPE #VISA
Visa will accept stablecoin payments across four conversion to fiat currency.
🔍Discover insights👇
🔥Top Gainers by 4h on Coinglass
As of 02:11 (UTC) Today📊
#PUP: $0.00787 +49.15%
#OL: $0.03371 +11.11%
#CORL: $0.04279 +10.65%
#APR: $0.39815 +10.24%
#WBAI: $0.02255 +9.84%
🔥#ADA #HYPE #VISA
Visa will accept stablecoin payments across four conversion to fiat currency.
🔍Discover insights👇
0
2
1
282
It’s all about early alpha 🚀
@Coral_Finance brings AI-powered DeFi rewards to @Gate’s CandyDrop!
Trade CORL & win up to 2,000 CORL 🍬
🔗 gate.com/candy-drop/det…
#GateCandyDrop #CORL #DeFAI #Airdrop
@Coral_Finance brings AI-powered DeFi rewards to @Gate’s CandyDrop!
Trade CORL & win up to 2,000 CORL 🍬
🔗 gate.com/candy-drop/det…
#GateCandyDrop #CORL #DeFAI #Airdrop
0
0
9
3,197
Another CandyDrop — another chance to earn!
@Gate & @Coral_Finance join forces to gift users up to 2,000 CORL 🎁
AI meets DeFi — join now 👇
gate.com/candy-drop/det…
#GateCandyDrop #CORL #DeFAI #Airdrop
@Gate & @Coral_Finance join forces to gift users up to 2,000 CORL 🎁
AI meets DeFi — join now 👇
gate.com/candy-drop/det…
#GateCandyDrop #CORL #DeFAI #Airdrop
20
0
0
3,439