류형규

가요 음반수집가

[Junghee Ryu @drjungheeryu]

“Jensen, our model beats yours!” “Oh RLWRLD! I know you!”

[류형규 @xfactor_ryu]

RLWRLD with Jensen

[Junghee Ryu @drjungheeryu]

Jensen & RLWRLD @ GTC Taipei 2026 Keynote.

[Jinwoo Shin @JinwooShin0417]

RLDX-1 took the first place "officially" in the RoboCasa365 benchmark!

https://t.co/CvkX3XUuHT

Tech report: https://t.co/AKJxLy8qhr

[Junghee Ryu @drjungheeryu]

Without the support of #NVIDIA, #RLDX-1 would not have been possible. Huge thanks to Amit Goel and the entire NVIDIA team for the incredible support and collaboration. Let’s push the frontier of Physical AI together!

[류형규 @xfactor_ryu]

RLDX-1 (RealDex), RLWRLD’s first robotics foundation model, has just been released!

[RLWRLD @RLWRLD_ai]

Today, RLWRLD unveils RLDX-1 — our proprietary Robotics Foundation Model.

Across all 8 public benchmarks, RLDX-1 outperforms leading SOTA models including #NVIDIA #GR00T and Physical Intelligence #π0 — delivering state-of-the-art performance among open robotics foundation models.

🎯 A 'Dexterity-First' Philosophy
The industry assumes dexterity will follow once intelligence is solved. We see it the other way around.

Dexterity isn't downstream of intelligence — it's the path intelligence must take to act in the physical world. Real industrial work with five-finger robotic hands depends on signals vision alone can't capture: force (torque), tactile feedback, and the precise moment of contact.

🧠 MSAT — Multi-Stream Action Transformer
Where conventional VLAs collapse every input into a single transformer stream, MSAT gives each modality — vision, language, action, touch, memory — its own dedicated stream, then unifies them through joint attention. Force, tactile signals, and long-term memory are handled by purpose-built Physics and Memory modules.

The result: one model that can see, feel, remember, and adapt.

📊 Performance Highlights
RoboCasa Kitchen — 70.6: the first VLA model to cross the 70-point threshold
GR-1 Tabletop — 58.7: +10.7 percentage points over NVIDIA GR00T N1.6
LIBERO-Plus — 86.7%: top score across 7 robustness variables

Pot-to-Cup Pouring on WIRobotics ALLEX — 70.8%: nearly 2× the comparison models, which remained in the high-30% range.

We're also releasing DexBench — our industry-grounded benchmark for dexterous manipulation, defined across five domains: Grasp Diversity, Spatial Precision, Temporal Precision, Contact Precision, and Context Awareness.

🔓 Open Release
Three checkpoints (8.1B parameters each), live now on GitHub and Hugging Face:

RLDX-1-PT — pre-training
RLDX-1-MT-ALLEX — mid-training for ALLEX
RLDX-1-MT-DROID — mid-training for DROID

⚙️ Built on NVIDIA's Cloud-to-Edge Stack
Training and simulation on Isaac GR00T, Isaac Lab, Isaac Sim, and cuRobo. Compute on NVIDIA H100 and A100 GPUs. Edge inference on Jetson AGX Thor with TensorRT. Our collaborations with NVIDIA, AWS, and Microsoft continue across both research and deployment.

🌍 What's Next: The 4D+ World Model
Video-based world models will never surface what isn't in the pixels — contact torque, tactile signals, robot state. Our 4D+ World Model integrates these directly with vision, language, and action across the temporal dimension, predicting and generating the full physical world. RLDX-1 is the first milestone on that roadmap.

📍 Join us at Dexterity Night in San Francisco on May 13 — followed by launch events in Japan and Korea.

🔗 Explore RLDX-1 on GitHub and Hugging Face.

https://t.co/kT6aX3qo8P

#RLWRL #RLDX1 #PhysicalAI #RoboticsFoundationModel #VLA #Humanoid #Dexterity #FoundationModel #Robotics #AI

[류형규 @xfactor_ryu]

@Raoulian 한잔?

[류형규 @xfactor_ryu]

@kwabang2827 저건 병규형이 옛날에 만든 시스템 제안서 같은데…

[류형규 @xfactor_ryu]

@jucklee 그때 뵙겠습니다. 티케팅에서 성공하길 스스로에게 기원하며! ^^

[Chris Paxton @chris_j_paxton]

This is a bold video choice and more impressive than the hundredth dancing robot

[RLWRLD @RLWRLD_ai]

Pouring milk.
A simple act for humans—an extraordinary challenge for robots.
This is where dexterity meets intelligence.
#RLWRLD #PhysicalAI

[RLWRLD @RLWRLD_ai]

Our brand film is here.
A glimpse into what drives us: building robots with human-level dexterity and intelligence.
This is just the beginning.
#RLWRLD #PhysicalAI #Robotics

[RLWRLD @RLWRLD_ai]

Something special is coming.
ALLEX just completed one of our key demos flawlessly—this is the energy in the room.
Full demo video drops soon.
#RLWRLD #Demo #PhysicalAI #dexterity

[RLWRLD @RLWRLD_ai]

Just saw this awesome demo by @kaysorin — really proud to share ALLEX in action at the OpenAI Seoul Open Event! Watching it move, interact, and demonstrate real-world dexterity was something special. 🤖🙌

Huge shoutout to everyone involved — pushing the boundaries of what’s possible with physical AI.

#RLWRLD #OpenAI #Robotics #PhysicalAI #Dexterity #Innovation #Seoul

[RLWRLD @RLWRLD_ai]

Watch ALLEX in action.
From delicate gestures to precise object handling, our humanoid shows next-level hand dexterity and Physical AI at the @OpenAI Seoul Open Event.
This is how @RLWRLD_ai is redefining real-world robotics 🤖✨

#RLWRLD #OpenAI #PhysicalAI #dexterity #AIrobotics #Seoul

[Junghee Ryu @drjungheeryu]

Big thanks to @adcock_brett for the interest in ALLEX! RLWRLD is stepping in next — shaping the Robotics Foundation Model space, just as Helix does for Figure.

[류형규 @xfactor_ryu]

#우리의무대를지켜주세요 #saveourstages

확대하시면 타임테이블을 보실 수 있습니다!!

[류형규 @xfactor_ryu]

팬더믹 시대에 사라져가는 인디 라이브 공연장을 지키기 위한 온라인 공연 페스티벌 (3/8-3/14)
티켓 예매/후원은 https://t.co/yI64vU9ViU
#saveourstages #우리의무대를지켜주세요

[류형규 @xfactor_ryu]

@MorningFog_ 취향에 맞았다니 다행입니다 ㅎㅎ 당시 플레이리스트는 요거입니다.

플레이리스트를 말씀주시는 분들이 있어서.. ㅎㅎ 이때 틀었던 노래들은 아래와 같습니다. https://t.co/wtTDlnnX0g

[류형규 @xfactor_ryu]

@hoont0107 오 반갑습니다. 도움이 되었다니 다행이에요. 클하를 불규칙적으로 하고 있어서 언제 뵐지 모르겠지만 생각보다 많은 시간을 거기서 보내고 있는지라 (ㅠㅠ) 곧 뵈지 않을까 싶습니다 ㅎㅎ

[류형규 @xfactor_ryu]

@Mearinam 굿