Ropedia (@ropedia_ai) - Twitter Profili | Zamantika Mersobahis Locabet

Sabitlenmiş Tweet

Ropedia@ropedia_ai·17 Mar

Today Ropedia releases Xperience-10M at #GTC day 1 — World largest real human 4D interaction dataset at 10M scale. Each trajectory aligns: • visual observations • spatial structure • human motion • interaction dynamics • task semantics A new foundation for physical and spatial AI, try it out @huggingface huggingface.co/datasets/roped…

English

4

25

95

48.4K

Ropedia@ropedia_ai·2d

Ropedia team @Frozen_Burning @hongfz16 spoke with Former Deputy Prime Minister Heng Swee Keat of Singapore🇸🇬 about physical intelligence and real-world data at the launch of NTU × UOB Innovation Hub. Honoured to be invited by @NTUsg. More to come. #EmbodiedAI #PhysicalAI #AI #Deeptech #Singapore #Startup

English

0

9

18

3K

Ropedia@ropedia_ai·3d

Calling everyone in Singapore, we will be at @NTUsg 's NBS building tomorrow — full team on site. Limited Ropedia merch 👕 Come find us. Follow @ropedia_ai. #embodiedai #physicalintelligence #robotics #singapore #tech

English

0

4

12

769

Ropedia@ropedia_ai·19 Mar

Hot take: "More data" won't fix AI. If the data is static, you just get a bigger model that still doesn't understand the real world. Intelligence lives in sequences. Not snapshots. That's why we're building systems that act in the physical world — long-horizon sequential tasks, dozens of precise actions, zero room for error. End to end. Full demo here → x.com/ropedia_ai/sta… #EmbodiedAI #Robotics #LongHorizonPlanning #AI #FutureOfAI

English

0

8

32

13.5K

Ropedia retweetledi

AK@_akhaliq·17 Mar

Ropedia Xperience-10M is out on Hugging Face a large-scale egocentric multimodal dataset of human experience for embodied AI, robotics, world models, and spatial intelligence It contains 10 million experiences (interaction) and 10,000 hours of synchronized first-person recordings with six video streams, audio, stereo depth, camera pose, hand mocap, full-body mocap, IMU, and hierarchical language annotations dataset: huggingface.co/datasets/roped…

English

7

16

68

10K

Ropedia retweetledi

Ziwei Liu@liuziwei7·17 Mar

🤩The World's Largest Human-Centric Dataset for Physical AI🤩 We @Ropedia are excited to announce 🙆Xperience-10M🙆‍♀️, *10M real human 4D interaction dataset* with - Visual Observations - Spatial Structure - Human Motion - Interaction Dynamics - Task Semantics 🌏A new data foundation for physical and spatial AI @huggingface: huggingface.co/datasets/roped…

Ropedia@ropedia_ai

Today Ropedia releases Xperience-10M at #GTC day 1 — World largest real human 4D interaction dataset at 10M scale. Each trajectory aligns: • visual observations • spatial structure • human motion • interaction dynamics • task semantics A new foundation for physical and spatial AI, try it out @huggingface huggingface.co/datasets/roped…

English

2

28

149

22.8K

Ropedia retweetledi

Zhaoxi Chen@Frozen_Burning·17 Mar

After 3 months of cooking with HOMIE, today @ropedia_ai launch Xperience-10M, the largest multimodal 4D human dataset for robotics, world models and multimodal contextual AI. 10M episodes of real-world human experience including: - 10000 hours of video with audio - 576M frames full-body motion - 16M caption sentences - 350K object - 1PB in total storage That’s the future we’re building at Ropedia. Github Toolkit: github.com/Ropedia/HOMIE-… @huggingface dataset: huggingface.co/datasets/roped…

Ropedia@ropedia_ai

Today Ropedia releases Xperience-10M at #GTC day 1 — World largest real human 4D interaction dataset at 10M scale. Each trajectory aligns: • visual observations • spatial structure • human motion • interaction dynamics • task semantics A new foundation for physical and spatial AI, try it out @huggingface huggingface.co/datasets/roped…

English

0

10

22

2.5K

Ropedia retweetledi

Fangzhou Hong@hongfz16·17 Mar

Really excited to finally share Xperience-10M🚀 It represents the kind of data I believe physical AI needs: not isolated frames, but real trajectories where perception, space, motion, interaction, and task intent come together. And as a 3D vision nerd, it was really cool to just look at the visualization. Truly a dream come true moment. Huge kudos to the team for making this happen! 🦾✨

Ropedia@ropedia_ai

Today Ropedia releases Xperience-10M at #GTC day 1 — World largest real human 4D interaction dataset at 10M scale. Each trajectory aligns: • visual observations • spatial structure • human motion • interaction dynamics • task semantics A new foundation for physical and spatial AI, try it out @huggingface huggingface.co/datasets/roped…

English

0

6

15

2K

Ropedia retweetledi

Ropedia@ropedia_ai·17 Mar

Today Ropedia releases Xperience-10M at #GTC day 1 — World largest real human 4D interaction dataset at 10M scale. Each trajectory aligns: • visual observations • spatial structure • human motion • interaction dynamics • task semantics A new foundation for physical and spatial AI, try it out @huggingface huggingface.co/datasets/roped…

English

4

25

95

48.4K

Ropedia@ropedia_ai·16 Mar

@Frozen_Burning Indeed! We have a live animation here: ropedia.com/blog/20260316_…

English

0

43

Zhaoxi Chen@Frozen_Burning·16 Mar

@ropedia_ai A fun fact: total number of human movement has reached 39000km, one circle around the earth!

English

1

0

1

37

Ropedia@ropedia_ai·12 Mar

A robot picking up a tennis ball. Looks simple. But behind it is something the internet can’t teach. The physical world. The Grasp. Throw. Consequence. This is the kind of experience AI needs next. We’re getting ready to share what we’ve been building. Stay tuned. #AI #Robotics #PhysicalAI #EmbodiedAI #AIResearch #Tech

English

0

2

6

1.3K

Ropedia@ropedia_ai·11 Mar

Robots don’t just need data. They need experience： - Movement - Spatial Reasoning - Interactions - Consequences The intelligence for the future lives in the physical world. More coming soon next week. #PhysicalAI #Robotics #EmbodiedAI #AIInfrastructure #AI #DeepTech #FrontierTech

English

0

6

14

3.6K

Ropedia@ropedia_ai·27 Şub

We’ve trained AI on text, images, and code. But not on how humans actually experience the world. That layer, multi-modal, continuous, real-world interaction is still largely missing, and we’re working on changing that. Stay tuned. Interested in free early access? Sign up here：docs.google.com/forms/d/e/1FAI… #EmbodiedAI #AI #DeepLearning #MultimodalAI #HumanExperienceAI

English

0

4

11

1.3K

Ropedia retweetledi

Ropedia@ropedia_ai·16 Ara

🧵1/ Today we’re introducing Ropedia 🚀 AI needs more human Xperience 👀✋🚶🌍 to unlock interactive intelligence We’re building the system to capture & scale it 📡 Example 👇🍅🍳 (tomato & egg stir-fry)

English

5

25

112

62.6K

Ropedia retweetledi

Ziwei Liu@liuziwei7·18 Ara

We also believe in the power of learning from real human experiences. And @ropedia_ai is here to scale it.

Sergey Levine@svlevine

It turns out that VLAs learn to align human and robot behavior as we scale up pre-training with more robot data. In our new study at Physical Intelligence, we explored this "emergent" human-robot alignment and found that we could add human videos without any transfer learning!

English

2

21

135

24.8K

Ropedia@ropedia_ai·17 Ara

We bet on this: physical intelligence needs diverse human Xperience. Embodiment agnostic representations emerge with pretraining scale where HOMIE (#homie" target="_blank" rel="nofollow noopener">ropedia.com/blog/20251216_…) offers such capabilities as an all-in-one suite to capture in the wild.

Physical Intelligence@physical_int

We discovered an emergent property of VLAs like π0/π0.5/π0.6: as we scale up pre-training, the model learns to align human videos and robot data! This gives us a simple way to leverage human videos. Once π0.5 knows how to control robots, it can naturally learn from human video.

English

2

3

18

3.4K

Ropedia@ropedia_ai·16 Ara

We’re giving out 49 early prototypes 🎁 to teams & researchers who want to explore, experiment, and shape what we build next Join the waitlist 👇 Early access. Real input. Real impact ✨ docs.google.com/forms/d/e/1FAI…

English

0

2

5

1.4K

Ropedia@ropedia_ai·16 Ara

Want the full story behind Ropedia, HOMIE, and human Xperience? 📖 We wrote it up here 👇 🔗 Read the blog ropedia.com/blog/20251216_…

English

1

2

6

1.6K

Ropedia

Keşfet