Fu-En (Fred) Yang

@FuEnYang1

Research Scientist @NVIDIAAI | Ph.D. @NTU_TW | Prev. Research Intern @NVIDIAAI | Unifying World, Language & Action for Generalist Robotics

fuenyang1127.github.io

Joined February 2020

1,714 Following

1,098 Followers

Replies Reposts Media

Pinned
Fu-En (Fred) Yang
@FuEnYang1
Oct 28
🤖 What if robots could reason not just in words, but through the dynamics of the physical world? 🚀 Introducing 𝗧𝗵𝗶𝗻𝗸𝗪𝗼𝗿𝗹𝗱 from @NVIDIAAI ! 💡 By reasoning through shared physical dynamics, robots could learn from human experience and transfer motion intelligence
11
Fu-En (Fred) Yang
@FuEnYang1
Nov 4
🎥 What if video diffusion models could learn a universal language of actions across humans and robots? 🚀 Introducing 𝗗𝗿𝗲𝗮𝗺𝗫: Video Diffusion Model Is a Universal Latent Action Learner! DreamX extracts compact, transferable latent actions directly from pretrained video
2
Fu-En (Fred) Yang
@FuEnYang1
Oct 28
Thanks @_akhaliq for sharing our work! Paper: arxiv.org/abs/2610.37666 Webpage: thinkworld-project.github.io
AK
@_akhaliq
Oct 28
ThinkWorld World Imagination Reinforces Chain-of-Dynamics Reasoning paper: huggingface.co/papers/2610.37…
Fu-En (Fred) Yang
@FuEnYang1
Oct 28
Thanks so much @_bbelousov for highlighting our ThinkWorld work! Excited to push forward world-grounded motion reasoning for generalizable robot intelligence!
Boris Belousov
@_bbelousov
Oct 28
ThinkWorld from @NVIDIAAI and KAIST is a VLA that can also learn from videos without action labels: before acting, it reasons in motion tokens and is rewarded when the future it predicts from them matches what the video shows next. Reasoning • A Qwen3-VL-2B model first writes
Quote
Fu-En (Fred) Yang
@FuEnYang1
Oct 28
🤖 What if robots could reason not just in words, but through the dynamics of the physical world? 🚀 Introducing 𝗧𝗵𝗶𝗻𝗸𝗪𝗼𝗿𝗹𝗱 from @NVIDIAAI ! 💡 By reasoning through shared physical dynamics, robots could learn from human experience and transfer motion intelligence
Fu-En (Fred) Yang
@FuEnYang1
Jun 2
I’ll be attending #CVPR2026 from June 3–7. Looking forward to reconnecting with old friends and meeting new ones! I’d be happy to chat about recent frontiers in robotics, as well as our continuing research on reasoning and generalization in VLA models. Always excited to exchange
Fu-En (Fred) Yang
@FuEnYang1
Feb 23
🚀 Excited to share that our paper Fast-ThinkAct has been accepted to #CVPR2026! 🎉 Efficient Vision-Language-Action reasoning via verbalizable latent planning — enabling embodied agents to think fast internally without lengthy textual reasoning. ⚡ Achieves 9.3× faster
1

Fu-En (Fred) Yang

Fu-En (Fred) Yang’s posts