←
Sirui Chen ✈️ CoRL2026206 posts
Sirui Chen ✈️ CoRL2026 avatar

Sirui Chen ✈️ CoRL2026

@eric_srchen

PhD in Stanford CS, Prev Undergrad at HKU. Interested in robotics

◷ Joined September 2023▧ 23 Photos and videos
Sirui Chen ✈️ CoRL2026 avatar
Sirui Chen ✈️ CoRL2026@eric_srchen·Jun 29

Humanoids excel in free space but struggle with real-world contact. Meet SceneBot 🤖 the first unified RL framework for ALL free-space locomotion, terrain traversal and object interaction! By conditioning on per-link contact labels, it masters complex, interaction-rich tasks like carrying a box upstairs. Code & data open-sourcing soon! 📦 🪜 Paper: arxiv.org/abs/2606.27581 Website: ericcsr.github.io/scenebot/

0:38
Carlo Sferrazza avatar
⟳ Sirui Chen ✈️ CoRL2026 retweeted
Carlo Sferrazza@carlo_sferrazza·Nov 10

I'm at #CoRL2026! Check out our posters tonight, 5–6:30pm, JW Marriott: #63 FPO++: Flow Policy Gradients for Robot Control (also an oral this morning by @redstone_hong) #140 TACTX: Learning Shared Tactile Representations Across Diverse Sensors #184 PRISM: Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation @Z1hanW #189 VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes @wangyenjen @jiaman01

Guy Tevet avatar
⟳ Sirui Chen ✈️ CoRL2026 retweeted
Guy Tevet@GuyTvt·Nov 9

We'll be presenting #Cloak tomorrow (Nov 10) at 5 PM at #CoRL! Come by poster #33 to chat about zero-shot cross-embodiment transfer for VLAs. We also recently released the code and a hardware guide to fully reproduce our setup. Check it out: tml.stanford.edu/cloak/

The robotics community has collected enormous robot datasets on grippers, but what happens when the hardware changes? How do we make robot data outlive the hardware it was collected on? We introduce Cloak, a training recipe for zero-shot cross-embodiment transfer. We never collect ANY embodiment-specific data. 🧵

0:14
Yuke Zhu avatar
⟳ Sirui Chen ✈️ CoRL2026 retweeted
Yuke Zhu@yukez·Nov 9

Meet GR00T 2, our new generation of world-action models (WAMs): it imagines how the physical world will unfold and generates the actions that get it there. One model runs on parallel grippers, dexterous hands, and humanoids. research.nvidia.com/labs/gea…

1:31
Qiayuan Liao avatar
⟳ Sirui Chen ✈️ CoRL2026 retweeted
Qiayuan Liao@qiayuanliao·Nov 8

Wanted to get into manipulation. Decided to first build a full stack that scales. Plan: copy @GeneralistAI's gripper. Fun weekend project. It was not. So @t_k_233 and I documented every design choice and lesson along the way. Meet Specialist: fully open-source hardware, data pipeline, training, and deployment code. specialist-ai.github.io/

1:41
Jitendra MALIK avatar
⟳ Sirui Chen ✈️ CoRL2026 retweeted
Jitendra MALIK@JitendraMalikCV·Nov 8

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!

2:42
Daniel Morton avatar
⟳ Sirui Chen ✈️ CoRL2026 retweeted
Daniel Morton@danielpmorton·Nov 4

Humanoid retargeting and IK in microseconds [no GPU required] Orders of magnitude speedups, with perfect contact handling: accelerate your robots today at github.com/StanfordASL/frax w/ @drmapavone

0:35
Sihang Li ✈️ CoRL avatar
⟳ Sirui Chen ✈️ CoRL2026 retweeted
Sihang Li ✈️ CoRL@SihangLi659492·Nov 3

💪 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)

0:18
C. Zhang avatar
⟳ Sirui Chen ✈️ CoRL2026 retweeted
C. Zhang@ChongZzZhang·Oct 31

leggedrobotics.github.io/ACP… ACP yourself. Video 1: vault, climbing, jumping, get up, Video 2: sit Video 3: ultra-hard standing on vaulting wall PC & Phone both supported. (more scenes still under construction)

0:38
0:11
0:10
Kaizhe Hu ✈️ CoRL avatar
⟳ Sirui Chen ✈️ CoRL2026 retweeted
Kaizhe Hu ✈️ CoRL@hkz222·Oct 30

Have you ever considered drawing as a robotic task? Meet BURGER 🍔: a benchmark for long-horizon language grounding, multimodal behavior and generalization—with robot data we can control and scale systematically. A simple canvas can reveal surprising weaknesses in VLAs. 🧵 1/7

0:51
Cunxi (Jimmy) Dai avatar
⟳ Sirui Chen ✈️ CoRL2026 retweeted
Cunxi (Jimmy) Dai@JimmyDai218776·Oct 28

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

6:35
Yiming Dou avatar
⟳ Sirui Chen ✈️ CoRL2026 retweeted
Yiming Dou@_YimingDou·Oct 29

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)

1:14
Reward AI avatar
⟳ Sirui Chen ✈️ CoRL2026 retweeted
Reward AI@RewardAI_·Oct 27

We deploy OM-1 on more humanoid tasks in both indoor and outdoor environments. OM-1 can power humanoids to do useful things robustly that other models or form factors cannot. - last-mile delivery from a Cybertruck - manipulation on stairs

1:17
Amber Xie avatar
⟳ Sirui Chen ✈️ CoRL2026 retweeted
Amber Xie@amberxie_·Oct 26

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.

2:41