Yiming Dou (@_YimingDou) header
Yiming Dou (@_YimingDou) profile picture

Research intern @ Amazon FAR | PhD student @ Cornell | 👀🖐️👂🤖

SH ↔️ NYC ↔️ SF
Joined March 2022
Photo by Yiming Dou (@_YimingDou)Photo by Yiming Dou (@_YimingDou)Photo by Yiming Dou (@_YimingDou)Photo by Yiming Dou (@_YimingDou)Photo by Yiming Dou (@_YimingDou)Photo by Yiming Dou (@_YimingDou)Photo by Yiming Dou (@_YimingDou)Photo by Yiming Dou (@_YimingDou)Photo by Yiming Dou (@_YimingDou)Photo by Yiming Dou (@_YimingDou)
Can a robot manipulate a rope, granular objects or cloth to reach precise 3D shapes? 🚨Introducing DefFlow: a goal-conditioned 3D World Action Modelling approach that learns to manipulate deformable objects into diverse goal shapes using 3D point flows. A thread🧵(1/n)
2
27
6
132
12,170
Yiming Dou retweeted
First day in CoRL, introducing our real-time world simulator led by @_YimingDou . A lot of people asked where we were hiding the robot 😆 Nope, no robot here! Everything is generated by our awesome world model, one that actually works! Come play with (and stress-test) our model at the demo booth on the 3rd floor of JW Marriott, right next to the Amazon booth! We will be here until the end of Tuesday.
Introducing DreamFAR, a world model trained from scratch using only robot data, without internet pretraining. It supports: 🎮 Real-time teleoperation ⏱️ Minutes of long-horizon rollout 🧩 Generalization across 1,000+ tasks yimingdou.com/DreamFAR 🧵 (1/8)
1
2
18
856
Robots that learn should generalize. Locomotion should show generalization across terrain; manipulation across object categories. Here is a video of “Pick Anything”, demonstrating human like grasps for 66 different objects, ranging in size and shape from air pods to dumbbells to pipe wrenches, using a *single* policy. The system uses the stereo camera head for vision (no wrist cameras) & Sharpa Wave hands for manipulation. It was trained using video and RL (zero teleoperation data). This is research from our Dex-Hands team at Amazon FAR and we will be doing live demos of the system at CoRL 2026 ( Demo 12, Nov. 9 &10). Please come by!
15
45
15
364
44,944
Yiming Dou retweeted
Full episode dropping soon! Geeking out with @JiahengHu1 and @SteveTod1998 on “SimEX: Simulation-Integrated Robotics AutoResearch.” robo-simex.github.io/ Co-hosted by @micoolcho and @DJiafei
7
17
2,473
💪 We teach humanoids where to move and how hard to apply force, using human demonstrations collected without a robot. Introducing 🌺 FLoRe: Learning Force-Reactive Humanoid Loco-Manipulation. Our policy learns to predict actions and forces for each hand. A hybrid compliance whole-body controller tracks these commands while the robot walks and balances. 🧵 (1/6)
19
44
8
229
13,272
Can learning to grasp teach a robot to use tools? 🤖🖐️ Introducing our #CoRL2026 paper: “From Grasps to Dexterity: Large-Scale Grasp Pretraining for Dexterous Manipulation” We turn grasp data into pretraining for autonomous tool use. 🎥 Project & videos: yingyuan0414.github.io/grasp… 🧵👇 (1/9)
5
19
1
86
3,940
❓I keep coming back to this: what tactile representation does manipulation need? We introduce PanoTac: A dense three-axis Tactile Sensor. In the demo, the robot reorients and inserts a tube, then wiggles the stopper free while the tube sits loosely in the rack. The right side show the tactile signals that helps robot detect when the stopper releases and when to switch from wiggling to lifting. (1/7)
8
35
7
172
11,086
Yiming Dou retweeted
An interactive 3D world simulator just dropped! This world simulator operates in a unified 3D representation space spanning point clouds, voxels, and 3D Gaussians, and renders multi-view consistent RGB-D images. Try the interactive 3D demo on our website - you can drag both the gripper and the camera around. The cloth dynamics are insanely good! You can stretch, crumple, and even drop the cloth. Check it out!
We introduce 3D World Simulator, an interactive world model that runs at 50+ FPS on an RTX 5090. Our model predicts in a unified 3D representation space, capable of generating: • Novel view appearance • Multi-view consistent RGB-D • 3D geometry • Spatially aligned tactile signals Play with the world model now at jwang771.github.io/3dworldsi…!
2
10
86
5,821
Yiming Dou retweeted
Human videos bring scale and motion priors to robot pretraining. But video mainly captures human states, leaving intended actions implicit. Applied forces help fill that gap. Introducing FACT: learning dexterous manipulation from human video and force. 🧵
5
19
128
6,823
Thrilled to share CARD: Contact-Anchored Retargeting for Dexterous manipulation. So far, collecting robot data, teleop, UMI, kinesthetic teaching, has run into the same two problems: 1) the mapping is largely kinematics only, and 2) the human has to act through the robot and hope the interaction works out. CARD instead treats contact and forces as the interface, from recording to replay, which is what lets it handle dexterous tasks that motion-only methods struggle with. 🧵 below 1/
Can you believe these are open-loop rollouts? Excited to introduce CARD 🃏 — Contact-Anchored Retargeting for Dexterous Manipulation. Almost every method today is limited to kinematics alone as the 𝐢𝐧𝐭𝐞𝐫𝐟𝐚𝐜𝐞 between the human and the robot. With CARD, we track real world contact and forces alongside kinematics to perform unprecedented dexterous tasks through tactile reactive replay! CARD is scalable: 📹 Multiple input sources 🤖 Multiple robot hands ⚡ needs no object models, no simulator, 10 Hz
6
15
5
53
5,852
Can you believe these are open-loop rollouts? Excited to introduce CARD 🃏 — Contact-Anchored Retargeting for Dexterous Manipulation. Almost every method today is limited to kinematics alone as the 𝐢𝐧𝐭𝐞𝐫𝐟𝐚𝐜𝐞 between the human and the robot. With CARD, we track real world contact and forces alongside kinematics to perform unprecedented dexterous tasks through tactile reactive replay! CARD is scalable: 📹 Multiple input sources 🤖 Multiple robot hands ⚡ needs no object models, no simulator, 10 Hz
11
59
27
280
48,430
Yiming Dou retweeted
Collecting data for dexterous hands is hard. Teleop needs a full setup. Bringing UMI-like devices to 20-dof hands is challenging. Introducing DexPort 🖐️: a hand-held interface w/ a real robot hand. No embodiment gap, recorded joint state AND actions, easy to use.
11
44
7
196
25,320
Your robot's shape shouldn't limit its sense of touch. Meet OpenTac: an open ecosystem for custom tactile skins that sense normal + shear forces. Very excited about this collaborative project! Can’t wait to see what the community builds with it. 🧵👇 opentac.github.io
9
26
9
131
14,169
Robots can’t always see the physics they act under: hidden mass, friction, kinematic constraints. A scalar reward only says "failed." The outcome of an action says much more. Introducing SCOUT: test-time policy adaptation from action-outcome feedback. Sim-trained, adapts in the real world in a few tries 🧵👇 #CORL2026
6
26
3
127
9,914
Yiming Dou retweeted
Your navigation model already found the goal. It just doesn't know when to stop. Introducing StopWatch, a navigation agent that grounds the goal explicitly before every action. It sets a new state of the art on six object-goal navigation benchmarks. Watch the flower vase episode below. Both agents reach the goal. StopWatch stops there. LightNav-0 turns away and keeps going. Code, models and data are open source 👉 stopwatch-nav.github.io/ Work done at Amazon FAR w/ @yunshengtian @QiuYuhengQiu @pabbeel @peterxichen @GuanyaShi @simonforrest 🧵 [1/n]
2
8
2
27
1,761
Can we make dexterous robots compliant without sacrificing precise control? Excited to introduce FOMO-Dex: Force-Modulated Dexterity! 🖐️ FOMO-Dex brings force-aware compliance to dexterous teleoperation, enabling robots to pick up thin cards and chips 🃏, cut paper 🔪, turn nuts 🔩, and use screwdrivers 🪛. These force-aware demonstrations also train better autonomous policies! 🎥 Videos & paper: yingyuan0414.github.io/fomo-… 🧵👇 (1/8)
11
40
4
168
14,079
What to remember in the past to act—spatial, temporal or motion details? We often assume what’s useful, but that’s hard to know in advance. Meet IMPRINT 🧠: retain rich memory first, then learn to use it for control. Compact latents keep inference fast as history grows. 🧵 1/10
5
29
11
185
22,289
Yiming Dou retweeted
Now autoregressive video models can remember. 🧠 Introducing MosaiChunk: persistent visual memory for long-horizon autoregressive video generation🧩. Instead of remembering everything, it remembers the right things. ✍️ 1/6
4
58
9
298
32,724
Yiming Dou retweeted
🤖 For parallel-jaw grippers, high-level plans can already be executed with mature primitives such as grasping. What about dexterous hands? Introducing GOTT (General Object Trajectory Tracking): object trajectories to dexterous execution with a reusable cross-embodiment contact primitive. The same primitive supports diverse real-world tasks including sweeping, pouring, whiteboard erasing, and hammering. With one checkpoint, GOTT reaches 90-96% grasp-and-lift success across multiple objects on three real-world arm-hand platforms. Check videos 👇
12
36
7
144
14,655
Yiming Dou retweeted
Practice makes perfect. A truly agentic robot shouldn’t just know what to do. It should also figure out how to get better. What if a robot could watch a demonstration, figure out what it needs to practice, and learn how to get better through practice? Introducing RPG: Guided Self-Improvement for Embodied Agents, a real-to-sim-to-real pipeline that turns real-world demonstrations into targeted practice. RPG reconstructs practice tasks from demonstrations, uses demo videos to guide skill improvement, and continually updates a shared skill system from failures. On real robots, RPG achieves 30/30 successes across 3 tasks. In simulation, it reaches 95.0% success across 22 manipulation tasks after 15 rounds of self-improvement. Demo → Reconstruct → Guided Practice → Self-Improve → Go Real
10
53
15
228
167,262