Jiafei Duan (@DJiafei) / X

Jiafei Duan

1,822 posts

Jiafei Duan

@DJiafei

Assistant Professor at @NUScomputing| Robotics & AI PhD @uwcse| Host of @RoboPapers| Ex-@allen_ai, @NVIDIA my opinion is my alone.

Seattle, WA

Joined January 2021

Pinned
Jiafei Duan
@DJiafei
May 5
Most capable generalist robotics models today are closed or at best, open weights. But robotics won’t reach its ChatGPT moment without real openness. That GPT moment was built on years of open tools and datasets such as Python, PyTorch, ImageNet and more, that let researchers
00:00
01:41
Ai2
@allen_ai
May 5
Robotics models often struggle outside controlled environments. Ours is built to work in real ones. Today we're launching MolmoAct 2, which can assist with a host of chores & lab tasks, plus the MolmoAct 2-Bimanual YAM dataset—the largest open robotics dataset of its kind. 🧵
107K
Jiafei Duan
@DJiafei
Feb 9, 2025
I am always activately looking for talented, passionate and hardworking students to work/collaborate/mentor with. Anyone interested, feel free to sign up here: forms.gle/oJPLR2pLTt8kLC…
69K
Jiafei Duan
@DJiafei
Aug 12, 2025
Reasoning is central to purposeful action. Today we introduce MolmoAct — a fully open Action Reasoning Model (ARM) for robotics. Grounded in large-scale pre-training with action reasoning data, every predicted action is interpretable and user-steerable via visual trace. We are
00:00
This post is unavailable.
100K
Jiafei Duan
@DJiafei
Jan 30, 2025
Can we build a generalist robotic policy that doesn’t just memorize training data and regurgitate it during test time, but instead remembers past actions as memory and conditions its decisions on them?🤖💡 Introducing SAM2Act—a multi-view robotic transformer-based policy that
00:00
111K
Jiafei Duan
@DJiafei
Jan 20, 2025
Every time I watch this video, I can't help but wonder: why don't we have robot butlers in our homes yet? The hardware seemed capable 14 years ago with teleoperation. Is it just the "robot brain" we're missing, or is there more to the puzzle?
00:00
47K
Jiafei Duan
@DJiafei
Jun 28, 2024
🚀 Excited to share our latest work: MANIPULATE-ANYTHING! 🦾 This scalable method pushes the boundaries of real-world robotic manipulation through zero-shot task execution and automated BC data generation. Here's a quick overview:👇 robot-ma.github.io
00:00
55K
Jiafei Duan
@DJiafei
Sep 6, 2025
We have now open-source the checkpoints from all training stages along with the full training and fine-tuning code. Check it out here: github.com/allenai/MolmoA…
Jiafei Duan
@DJiafei
Aug 12, 2025
Reasoning is central to purposeful action. Today we introduce MolmoAct — a fully open Action Reasoning Model (ARM) for robotics. Grounded in large-scale pre-training with action reasoning data, every predicted action is interpretable and user-steerable via visual trace. We are
00:00
22K
Jiafei Duan
@DJiafei
Feb 14, 2024
For large-scale robotic deployment🤖 in the real-world 🌏, robots must adapt to changes in environment and objects. Ever questioned the generalizability of your robot's manipulation policy? Put it to the test with The Colosseum 🏛️. Check out our project: robot-colosseum.github.io
00:00
37K
Jiafei Duan
@DJiafei
Jun 18, 2024
Humans use pointing to communicate plans intuitively. Compared to language, pointing gives more precise guidance to robot behaviors. Can we teach a robot how to point like humans? Introducing RoboPoint 🤖👉, an open-source VLM instruction-tuned to point. Check out our new work:
00:00
64K
Jiafei Duan
@DJiafei
Dec 31, 2024
🚀🤖 Top 10 Robot Learning Papers of 2024 is out!🔥 With 2 rounds of nominations & voting, plus 330+ individual votes, these standout papers shine across diverse categories: 1️⃣ π0: Vision-Language-Action Flow Model for General Robot Control 2️⃣ Closed-Loop Open-Vocabulary Mobile
30K
Jiafei Duan
@DJiafei
Jan 11, 2025
📢We are currently hiring for multiple roles at the @Ai2Prior @allen_ai 🚀 to build next-generation multimodal large language models 🤖, foundation models for robotics 🦾, and embodied AI 🧠. If open science research in these areas excites you 🔬✨, please apply here: Research
23K
Jiafei Duan
@DJiafei
Feb 10, 2025
🚨 Why do robots fail under out-of-distribution perturbations? Can we diagnose these failures in advance—and 'prescribe' the right data to fix them? 🚨 Our new paper, RoboMD introduces a systematic framework for diagnosing and improving robot manipulation policies. 🤖💡
00:00
13K
Jiafei Duan
@DJiafei
Mar 14, 2025
Exciting news! This summer, I’ll be joining @allen_ai as a Research Scientist Intern, working on scaling robotics foundation models. Looking forward to that!
GIF
13K
Jiafei Duan
@DJiafei
Sep 4, 2025
Robot paper of the day: RoboBallet: Planning for multirobot reaching with graph neural networks and reinforcement learning UCL + Google DeepMind + Intrinsic built an AI planner that choreographs teams of arms to work in tight spaces without collisions—planning in seconds, not
00:00
15K