@olivia_y_lee profile picture
Olivia Lee @olivia_y_lee

AI Engineer @Figure_robot building Helix | Prev. Robot Learning @StanfordAILab @StanfordIPRL

Joined February 2022
  • Posts 20
  • Following 177
  • Followers 282
4 Photos and videos
Pinned Post
Olivia Lee@olivia_y_lee
Jan 27
All sensors in. All actuators out: Helix 02 connects every onboard sensor - vision, touch, and proprioception - directly to every actuator through one unified visuomotor neural network. This unlocks the full dexterity potential of five-fingered hands for intricate manipulation.
Figure
@Figure_robot
Jan 27
Replying to @Figure_robot
Helix 02’s tactile sensing and palm cameras unlock manipulation tasks beyond pure vision‑based policies We demonstrate four tasks at the frontier of multi-fingered dexterity
0:09
5
14
134
13,736
Olivia Lee reposted
Brett Adcock
@adcock_brett
May 22
We just wrapped what began as an 8-hour challenge - and it ran for 200 hours without a failure Shoutout to the team for the hardcore engineering behind F.03 and the robust Helix models powering it
0:32
814
1,201
10,483
4,982,122
Olivia Lee reposted
The Humanoid Hub
@TheHumanoidHub
May 14
Figure just set a new standard in unedited humanoid demos. They completed 24 hours of autonomous work on a live stream, where three Figure 03 robots took turns processing delivery packages. At a rate of ~21 packages/minute, that is less than 3 seconds per package.
0:37
Figure
@Figure_robot
May 14
Day 2 is Live: Watch humanoid robots Bob, Frank, and Gary running 24/7. This is fully autonomous running Helix-02 x.com/i/broadcasts/1rxmqoaVg…
34
78
952
86,105
Olivia Lee reposted
Figure
@Figure_robot
Mar 9
Today we're showing Helix 02 that can tidy a living room fully autonomously Figure is designed so when you leave the house, your home resets exactly how you like it
2:28
722
1,282
9,542
2,115,206
Olivia Lee reposted
The Humanoid Hub
@TheHumanoidHub
Jan 27
Figure 03 demonstrating autonomous coordinated bimanual dexterity with the help of tactile sensing and palm cameras: - Unscrewing a bottle cap - Picking a pill from a medicine box - Dispensing exactly 5 ml from a syringe - Sorting metal pieces
0:45
The Humanoid Hub
@TheHumanoidHub
Jan 27
Figure introduces Helix 02: achieving full-body autonomy via a single neural network controlling walking, manipulation, and balance as one continuous system. - 4-minute end-to-end autonomous dishwasher unload/reload in a kitchen, a record in complex loco-manipulation task of this kind by a humanoid. - introduced a new foundational layer, System 0, a learned whole-body controller from >1,000 hours human motion data. - all sensors (vision, palm cameras, tactile, proprioception) directly to all actuators. Unified hierarchy (System 2: semantic → System 1: visuomotor → System 0: 1kHz control) enables seamless autonomy across the entire room.
3:36
16
73
522
48,966
Olivia Lee reposted
Figure
@Figure_robot
Jan 27
Introducing Helix 02 It's our most powerful model to date - it's using the whole body to do dishes end-to-end and it's fully autonomous
3:36
366
772
5,034
1,091,424
Olivia Lee reposted
Figure
@Figure_robot
9 Oct 2025
Introducing Figure 03
6:19
616
1,700
7,910
1,621,499
Olivia Lee reposted
Figure
@Figure_robot
7 Oct 2025
Figure 03 coming 10/9
0:48
436
998
7,574
1,426,360
Olivia Lee reposted
Stanford AI Lab
@StanfordAILab
27 Sep 2025
The Stanford AI Lab community is proud to showcase over 20 research papers at CoRL 2025! Read about them here : ai.stanford.edu/blog/corl-20… @corl_conf
7
34
205
21,850
Enabling robots to improve autonomously via RL will be powerful, and dense shaping rewards can greatly facilitate RL. Our #IROS2025 paper presents a method leveraging VLMs to derive dense rewards for efficient autonomous RL. ⚡🦾 #Robotics #ReinforcementLearning 🧵1/5
0:17
4
12
119
9,775
On 4 real-world tasks, KAGI enables success in 30K online fine-tuning steps, improving performance of systems using only sparse rewards. Furthermore, KAGI shows robustness to a 5x reduction in expert demos, achieving similar performance in 45K online fine-tuning steps. 🚀 🧵4/5
1:01
1
2
465
This work has been a long time coming! Special thanks to my collaborators Annie Xie and @KuanFang, as well as @KarlPertsch @chelseabfinn for their guidance. 📖 Paper: arxiv.org/abs/2407.10341 🌐 Website: sites.google.com/view/afford… 🧵5/5

Affordance-Guided Reinforcement Learning via Visual Prompting

Robots equipped with reinforcement learning (RL) have the potential to learn a wide range of skills solely from a reward signal. However, obtaining a robust and dense reward signal for general...

arxiv.org
3
407
Olivia Lee reposted
Jeannette Bohg@leto__jean
30 May 2025
Enabling robots to learn from humans would be a game changer! But humans may manipulate objects in a way that is impossible for robots. To cross this embodiment gap, Human2Sim2Robot follows this key insight: Don't imitate a demonstration but instead use it to guide RL.
Tyler Lum@tylerlum23
30 May 2025
🧑🤖 Introducing Human2Sim2Robot!  💪🦾 Learn robust dexterous manipulation policies from just one human RGB-D video. Our Real→Sim→Real framework crosses the human-robot embodiment gap using RL in simulation. #Robotics #DexterousManipulation #Sim2Real 🧵1/7
0:11
3
9
45
5,297
Excited to share our recent work! Our framework crosses the human-robot embodiment gap for dexterous manipulation. With just one human video demo to guide RL in sim, the robot learns optimal strategies for its own embodiment instead of imitating human motion. Details in the 🧵
Tyler Lum@tylerlum23
30 May 2025
🧑🤖 Introducing Human2Sim2Robot!  💪🦾 Learn robust dexterous manipulation policies from just one human RGB-D video. Our Real→Sim→Real framework crosses the human-robot embodiment gap using RL in simulation. #Robotics #DexterousManipulation #Sim2Real 🧵1/7
0:11
1
18
1,605
Olivia Lee reposted
Jeremy Hsu (@jeremyhsu.bsky.social)@jeremyhsu
13 Jun 2022
My first for @newscientist is about a robot learning to harness both sound and vision while searching for keys in a bag. Necessary skills for a complex world. Thanks to @chelseabfinn @du_maximilian @SurajNair_1 @olivia_y_lee at @StanfordAILab newscientist.com/article/232…

Robot can find keys in a bag just by listening as it rummages around

A robotic arm with an attached microphone learned to locate objects in a bag based on the sound they make, including a ring of keys and a bag of crisps

newscientist.com
3
9
Excited to share our work on learning policies end-to-end from vision and audio to complete tasks with occlusion, like extracting keys from a bag. Leveraging vision, sound, and memory can help robots resolve partial observability. Check out our #RSS2022 paper and project website!
Chelsea Finn
@chelseabfinn
1 Jun 2022
Can robots deal with occlusion? We put a microphone on a robot's gripper & found that audio helps robots learn to solve tasks amidst occlusion. #RSS2022 paper: arxiv.org/abs/2205.14850 w/ @du_maximilian, Olivia Lee, @SurajNair_1 🧵(1/4)

ALT A video of a robot arm taking keys out of a paper bag.
4
Load more