Simon LC (@simonlc_) header
Simon LC (@simonlc_) profile picture

Simon LC

@simonlc_

research scientist @ the AI institute robotics & optimization phd @ stanford

 New York
Joined September 2019
  • Tweets95
  • Following237
  • Followers608
38Media
Photo by Simon LC (@simonlc_)Photo by Simon LC (@simonlc_)Photo by Simon LC (@simonlc_)Photo by Simon LC (@simonlc_)Photo by Simon LC (@simonlc_)Photo by Simon LC (@simonlc_)Photo by Simon LC (@simonlc_)Photo by Simon LC (@simonlc_)Photo by Simon LC (@simonlc_)Photo by Simon LC (@simonlc_)
Our new paper shows how task representations learned via temporal alignment enable compositional generalization for conditional policies. This allows robots to solve compound tasks by implicitly decomposing them into subtasks.
Vivek Myers (@vivek_myers) profile pictureVivek Myers@vivek_myers13 Feb 2025
Current robot learning methods are good at imitating tasks seen during training, but struggle to compose behaviors in new ways. When training imitation policies, we found something surprising—using temporally-aligned task representations enabled compositional generalization. 1/
1
3
16
3,490
Learning bimanual, contact-rich robot manipulation policies that generalize over diverse objects has long been a challenge. Excited to share our work: Planning-Guided Diffusion Policy Learning for Generalizable Contact-Rich Bimanual Manipulation! glide-manip.github.io 🧵1/n
1
20
4
74
20,999
ICYMI: For #CoRL2024 we released a dataset of 3.5M (!) dexterous grasps, with multi-trial labels and perceptual data for 4.3k objects. Our takeaways: scale matters, and refining grasps > better sampling. Hoping our data can enable more vision-based grasps in hardware!
Albert Li (@albert_h_li) profile pictureAlbert Li@albert_h_li4 Nov 2024
There have been many recent big grasping datasets, but few demos of real-world grasping using generative models. How do we achieve this? Introducing: Get a Grip (#corl2024)! We show that instead of generative models, discriminative models can attain sim2real transfer! 👀🧵👇
1
15
1,163
Excited to share our new📰, DROP: Dexterous Reorientation via Online Planning! Overview: 🔹We tackle cube rotation🧊♻️on hardware 🔹DROP is the first 🧊♻️sampling-based MPC demo. No reinforcement learning! 🔹Median 30.5 rotations w/o dropping, max of 81👑🦾 See 🧵below👇
1
26
7
101
16,252
Excited to share our latest work, Vision-Language Frontier Maps – a SOTA approach for semantic navigation in robotics. VLFM enables robots to navigate and find objects in novel environments using vision-language foundation models, zero-shot! Accepted to #ICRA2024! 🧵
1
36
3
200
37,428
want your next robot 🤖 to move like your favorite pet 🐶? youtube videos might be all you need. checkout our recent work -- SLoMo paper: rexlab.ri.cmu.edu/papers/slo… website: slomo-www.github.io/website/ video: youtu.be/bvoM-nBd7lM?si=9f2g…
5
50
1
253
18,789
Some screen-captures of MuJoCo MPC's Quadruped task. 100% open-source, go play! youtu.be/esLuwaWz4oE
2
12
82
10,040
Introducing 𝗥𝗼𝗯𝗼𝗣𝗶𝗮𝗻𝗶𝘀𝘁 🎹🤖, a new benchmark for high-dimensional robot control! Solving it requires mastering the piano with two anthropomorphic hands. This has been one year in the making, and I couldn’t be happier to release it today! Some highlights below:
49
224
44
1,154
260,183
What happens when we train the largest vision-language model and add in robot experiences? The result is PaLM-E 🌴🤖, a 562-billion parameter, general-purpose, embodied visual-language generalist - across robotics, vision, and language. Website: palm-e.github.io
26
487
136
2,105
1,272,971
📢Excited to share our #ICRA2023 work on robotic table wiping via RL + optimal control! 📖 arxiv.org/abs/2210.10865 🎥 youtu.be/inORKP4F3EI 💡RL (for high-level planning) + trajectory optimization (for precise control) can solve complex tasks without on-robot data collection ⬇️
3
7
5
45
11,576
Replying to @kevintracy48
@kevintracy48 presenting our entry guidance work @aiaa #AIAASciTech
Image from Zac Manchester (@zacinaction)
2
8
1,244
Yours truly, delivering the MIT Robotics Seminar about our new MJPC tool. youtu.be/2xVN-qY78P4
MIT Robotics - Yuval Tassa - Predictive Sampling: Real-time behavior synthesis with MuJoCo

MIT Robotics - Yuval Tassa - Predictive Sampling: Real-time behavior synthesis with MuJoCo

MIT - December 2, 2022Yuval Tassa"Predictive Sampling: Real-time ...

youtube.com
2
31
1
160
Super excited to kick off this new project with collaborators @CMU_ECE @CMU_Robotics @cmurexlab @blucia0a
Carnegie Mellon University (@CarnegieMellon) profile pictureCarnegie Mellon University
@CarnegieMellon18 Aug 2022
With a grant from @NSF, @CMUengineering researchers are creating constellations of nanosatellites to extract valuable data and transmit it back to earth, while still in orbit. cmu.is/nanosatellites
Satellite in orbit around Earth.

ALT Satellite in orbit around Earth.

6
27
Got to share our lab's work at the ETH Autonomy Talks organized by @GioeleZardini yesterday. Super proud of the work by my students @simonlc_, @taylorhowell, @kevintracy48, Shuo Yang, and Chi Yen Lee. Check it out: youtube.com/watch?v=4H-lThQQ…
Autonomy Talks - Zac Manchester: Composable Optimization for Contac...

Autonomy Talks - Zac Manchester: Composable Optimization for Contac...

Autonomy Talks - 02/08/2022Speaker: Prof. Zachary Manchester, Car...

youtube.com
1
5
25
we built a new differentiable optimizer for robotics: CALIPSO paper: arxiv.org/abs/2205.09255 code: github.com/thowell/CALIPSO.j… slides: slides.com/taylorhowell/cali…
2
5
33
differentiable physics for robotics workshop talk at RSS w/ @simonlc_
Image from taylor howell (@taylorhowell)
3
5
41
Come check out this workshop on Monday at #RSS2022! I'll be presenting (poster + spotlight) our latest work on multiscale sensor fusion architectures for continuous-time control using Neural CDEs.
Ajay Mandlekar (@AjayMandlekar) profile pictureAjay Mandlekar@AjayMandlekar24 Jun 2022
Our #RSS2022 workshop on "Overlooked Aspects of Imitation Learning" is this Monday June 27 - join us virtual or in-person! We have a wonderful lineup of speakers (@ancadianadragan @ankurhandos @chelseabfinn @LerrelPinto Mohi Khansari @shimon8282) See: tinyurl.com/2pjt86uk
Image from Ajay Mandlekar (@AjayMandlekar)
3
15
We're excited to announce our @ieee_ras_icra workshop "Motion Planning with Implicit Neural Representations of Geometry!" We'll discuss the future of INRs -- like DeepSDFs, NeRFs, and more -- in robotics. Submissions due April 15. neural-implicit-workshop.sta…
1
24
2
132
presenting work on differentiable simulators for robotics at @Stanford SystemX lunch w/ @simonlc_ – at Stanford, CA
Image from taylor howell (@taylorhowell)
1
7
Our paper "Ultra-Fine Pointing for Nanosatellite Telescopes With Actuated Booms" with @zacinaction and @e_douglas was awarded best paper in avionics and electronics for space applications at @IEEEAeroConf! paper: roboticexplorationlab.org/pa…
Image from Kevin Tracy (@kevintracy48)
2
4
15
Load more