Chenhao Li's banner

Chenhao Li

@breadli428 • 7,794 subscribers

Doctoral fellow @ETH_en | Prev. @MIT, @ETH_en, @MPI_IS.

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

People: robots are replacing humanity. Real: robot dance show at a leading robotic conference without moving a toe.

People: robots are replacing humanity. Real: robot dance show at a leading robotic conference without moving a toe.

1,354,872 views • 1 year ago

What happens if you invite your non-robotics-research friend to “fight” your robots 👇

What happens if you invite your non-robotics-research friend to “fight” your robots 👇

128,595 views • 10 months ago

🧠Model-Based RL shows promises but has seen limited success in real-world robotics. 🌎Introducing Robotic World Model, a black-box end-to-end neural dynamics model that bridges this gap, where policies are trained purely in imagination. NeurIPS Conference 🎯

🧠Model-Based RL shows promises but has seen limited success in real-world robotics. 🌎Introducing Robotic World Model, a black-box end-to-end neural dynamics model that bridges this gap, where policies are trained purely in imagination. NeurIPS Conference 🎯

109,493 views • 11 months ago

Crazy 180kg ball-shaped robot by Zhejiang University smashingly rolling at #IROS2025!! ⚽️ 🏀 Coolest robot ever! 🤖

Crazy 180kg ball-shaped robot by Zhejiang University smashingly rolling at #IROS2025!! ⚽️ 🏀 Coolest robot ever! 🤖

90,196 views • 1 year ago

🌎World models can predict, but controlling real robots from imagination sees a long-standing failure due to hallucination. 🧠Introducing Uncertainty-Aware RWM: a black-box, end-to-end neural dynamics model with long-horizon uncertainty propagation. 🎯

🌎World models can predict, but controlling real robots from imagination sees a long-standing failure due to hallucination. 🧠Introducing Uncertainty-Aware RWM: a black-box, end-to-end neural dynamics model with long-horizon uncertainty propagation. 🎯

Chenhao Li @ CoRL

60,269 views • 9 months ago

I appreciate the confidence by Rainbow Robotics when they drove the robot dog into crowds. #CoRL2025 Very swift and agile. I rarely call a locomotion controller elegant but this is how it felt. Long video in 🧵

I appreciate the confidence by Rainbow Robotics when they drove the robot dog into crowds. #CoRL2025 Very swift and agile. I rarely call a locomotion controller elegant but this is how it felt. Long video in 🧵

70,249 views • 1 year ago

Dexterous manipulation demo by ROBOTIS. Surprisingly fast responses. Perfect for messaging. 💆

Dexterous manipulation demo by ROBOTIS. Surprisingly fast responses. Perfect for messaging. 💆

48,136 views • 1 year ago

🤷What if we want to learn from human data... without human data? In our work NIL (No-data Imitation Learning) #CVPR2026, we explore a simple but ambitious question: Can robots learn directly from AI-generated videos without any curated demonstration data? 🔗

🤷What if we want to learn from human data... without human data? In our work NIL (No-data Imitation Learning) #CVPR2026, we explore a simple but ambitious question: Can robots learn directly from AI-generated videos without any curated demonstration data? 🔗

22,062 views • 5 months ago

Physical Intelligence Physical Intelligence coffee demo at #NeurIPS2025. What’s the hot take?

Physical Intelligence Physical Intelligence coffee demo at #NeurIPS2025. What’s the hot take?

37,714 views • 11 months ago

✨ICLR 2024 Spotlight Still hand-labeling phases or tuning GANs with your trajectories? We propose FLD, a self-supervised representation method that extracts spatial-temporal relationships in high-dimensional trajectories. RL policies informed by FLD show extended generality.🧵

✨ICLR 2024 Spotlight Still hand-labeling phases or tuning GANs with your trajectories? We propose FLD, a self-supervised representation method that extracts spatial-temporal relationships in high-dimensional trajectories. RL policies informed by FLD show extended generality.🧵

81,988 views • 2 years ago

An incredibly fun demo of a modular legged wheel design that merges into a single unit by Direct Drive Innovation at #IROS2025. Currently, it is being driven by two people by hand 🤖

An incredibly fun demo of a modular legged wheel design that merges into a single unit by Direct Drive Innovation at #IROS2025. Currently, it is being driven by two people by hand 🤖

27,367 views • 1 year ago

✈️ Train policies ULTRA FAST without a simulator.

✈️ Train policies ULTRA FAST without a simulator.

18,088 views • 9 months ago

🪞Symmetry helps shape RL policies. 🧠Can it also improve memory and task understanding? ✅We introduce Symmetry-Guided Memory Augmentation, combining structured experience augmentation with memory-based context inference to boost learning efficiency. 🔗

🪞Symmetry helps shape RL policies. 🧠Can it also improve memory and task understanding? ✅We introduce Symmetry-Guided Memory Augmentation, combining structured experience augmentation with memory-based context inference to boost learning efficiency. 🔗

14,863 views • 7 months ago

I'm uploading a recording here to make up for the cut-off during our onsite presentation NeurIPS Conference #NeurIPS2025. 🙏We are deeply grateful for your previous support and the encouragement to upload this recording. ⭐️Despite the interruption, our work was recognized with an Outstanding Paper award.

I'm uploading a recording here to make up for the cut-off during our onsite presentation NeurIPS Conference #NeurIPS2025. 🙏We are deeply grateful for your previous support and the encouragement to upload this recording. ⭐️Despite the interruption, our work was recognized with an Outstanding Paper award.

18,277 views • 10 months ago

No more content to load