Chengkun Li
@ckli.bsky.social
PhD student @ EPFL ๐จ๐ญ | Prev: research intern @ Google DeepMind, ByteDance AI Lab | https://charlieleee.github.io
and of course a good base policy!
November 8, 2025 at 10:40 PM
and of course a good base policy!
Training another musculoskeletal system @xiaotiansu.bsky.social for tennis, after having trained other musculoskeletal systems for soccer and pingpong.
With cognitive function, reward learning, and some sort of teacher distillation, this system learns a quite robust forehand within 36,000 steps๐
With cognitive function, reward learning, and some sort of teacher distillation, this system learns a quite robust forehand within 36,000 steps๐
November 8, 2025 at 10:37 PM
Training another musculoskeletal system @xiaotiansu.bsky.social for tennis, after having trained other musculoskeletal systems for soccer and pingpong.
With cognitive function, reward learning, and some sort of teacher distillation, this system learns a quite robust forehand within 36,000 steps๐
With cognitive function, reward learning, and some sort of teacher distillation, this system learns a quite robust forehand within 36,000 steps๐
Reposted by Chengkun Li
Something exciting just left the gym -- meet Arnold the first generalist musculoskeletal control policy!
The human body has 600+ muscles, yet we seamlessly coordinate them for everything from whispering a syllable to felling a forrest. How? www.arxiv.org/abs/2508.18066
The human body has 600+ muscles, yet we seamlessly coordinate them for everything from whispering a syllable to felling a forrest. How? www.arxiv.org/abs/2508.18066
September 4, 2025 at 8:45 AM
Something exciting just left the gym -- meet Arnold the first generalist musculoskeletal control policy!
The human body has 600+ muscles, yet we seamlessly coordinate them for everything from whispering a syllable to felling a forrest. How? www.arxiv.org/abs/2508.18066
The human body has 600+ muscles, yet we seamlessly coordinate them for everything from whispering a syllable to felling a forrest. How? www.arxiv.org/abs/2508.18066
Interesting study, do check this out ๐ช
๐ Call for Participants!
Weโre testing a new JupyterLab plugin that compares how different notebooks tackle the same problem.
๐ง Who can join?
โข Data analysis learners
โข University instructors/students
โข Machine learning engineers
๐ When: Aug 18โ29, 2025
๐ Where: Zoom or in person
๐ฐ Pay: 25 CHF/h
Weโre testing a new JupyterLab plugin that compares how different notebooks tackle the same problem.
๐ง Who can join?
โข Data analysis learners
โข University instructors/students
โข Machine learning engineers
๐ When: Aug 18โ29, 2025
๐ Where: Zoom or in person
๐ฐ Pay: 25 CHF/h
August 9, 2025 at 3:46 PM
Interesting study, do check this out ๐ช
The more you use JAX, the more you feel its power.. like wielding the sharpest knife in your toolbox ๐ก๏ธ
July 30, 2025 at 10:06 PM
The more you use JAX, the more you feel its power.. like wielding the sharpest knife in your toolbox ๐ก๏ธ
glad to see distill.pub revived at anthropic :)
March 28, 2025 at 8:19 PM
glad to see distill.pub revived at anthropic :)
Itโs pretty strange they donโt have this in zurich. At EPFL, all stem masterโs students have a mandatory internship, and we get the chance to intern at big tech companies
February 26, 2025 at 3:34 PM
Itโs pretty strange they donโt have this in zurich. At EPFL, all stem masterโs students have a mandatory internship, and we get the chance to intern at big tech companies
Quick life update: I recently started my PhD back in the beautiful Lac Lรฉman region at EPFL Campus Biotech.
Just wanted to show off the office a bit! ๐
More nature views coming soonโฆ
Just wanted to show off the office a bit! ๐
More nature views coming soonโฆ
February 18, 2025 at 8:42 PM
Quick life update: I recently started my PhD back in the beautiful Lac Lรฉman region at EPFL Campus Biotech.
Just wanted to show off the office a bit! ๐
More nature views coming soonโฆ
Just wanted to show off the office a bit! ๐
More nature views coming soonโฆ
Reposted by Chengkun Li
Ep 2 of #InsideAI is out! ๐๏ธ๐
We sat with Google Fellow Urs Hรถlzle. From optimizing data centers to AI efficiency, AGI, autonomous vehicles & Europeโs AI outlookโdonโt miss this insightful conversation.
On Spotify: open.spotify.com/episode/5Tu9...
or Apple Podcast: podcasts.apple.com/us/podcast/c...
We sat with Google Fellow Urs Hรถlzle. From optimizing data centers to AI efficiency, AGI, autonomous vehicles & Europeโs AI outlookโdonโt miss this insightful conversation.
On Spotify: open.spotify.com/episode/5Tu9...
or Apple Podcast: podcasts.apple.com/us/podcast/c...
Conversation with Urs Hรถlzle
Podcast Episode ยท Inside AI ยท 01/29/2025 ยท 1h 7m
podcasts.apple.com
January 29, 2025 at 5:15 PM
Ep 2 of #InsideAI is out! ๐๏ธ๐
We sat with Google Fellow Urs Hรถlzle. From optimizing data centers to AI efficiency, AGI, autonomous vehicles & Europeโs AI outlookโdonโt miss this insightful conversation.
On Spotify: open.spotify.com/episode/5Tu9...
or Apple Podcast: podcasts.apple.com/us/podcast/c...
We sat with Google Fellow Urs Hรถlzle. From optimizing data centers to AI efficiency, AGI, autonomous vehicles & Europeโs AI outlookโdonโt miss this insightful conversation.
On Spotify: open.spotify.com/episode/5Tu9...
or Apple Podcast: podcasts.apple.com/us/podcast/c...
Stopped by BAAI (Beijing Academy of AI) to visit a friend! โ๏ธ The coffee was great, and itโs right between Chinaโs top two universities. Sadly, the hanging garden is closed for now. Overall a quite nice place to do research
#Beijing
#Beijing
January 29, 2025 at 6:10 AM
Stopped by BAAI (Beijing Academy of AI) to visit a friend! โ๏ธ The coffee was great, and itโs right between Chinaโs top two universities. Sadly, the hanging garden is closed for now. Overall a quite nice place to do research
#Beijing
#Beijing
Awesome work, congrats!
January 17, 2025 at 11:42 AM
Awesome work, congrats!
Reposted by Chengkun Li
We are hiring 1 PhD in energy modeling!
The PhD investigates policies to accelerate supply chain development for net-zero technologies like hydrogen through agent-based and energy system modeling.
Details: emea2.softfactors.com/job-opening/...
Apply until 31.01.2025.
Please share!
The PhD investigates policies to accelerate supply chain development for net-zero technologies like hydrogen through agent-based and energy system modeling.
Details: emea2.softfactors.com/job-opening/...
Apply until 31.01.2025.
Please share!
January 6, 2025 at 9:13 AM
We are hiring 1 PhD in energy modeling!
The PhD investigates policies to accelerate supply chain development for net-zero technologies like hydrogen through agent-based and energy system modeling.
Details: emea2.softfactors.com/job-opening/...
Apply until 31.01.2025.
Please share!
The PhD investigates policies to accelerate supply chain development for net-zero technologies like hydrogen through agent-based and energy system modeling.
Details: emea2.softfactors.com/job-opening/...
Apply until 31.01.2025.
Please share!
Reposted by Chengkun Li
I've put together a starter pack of EPFL researchers across all labs and domains! ๐จ๐ญ Would love to expand this list and showcase more amazing work happening at EPFL. Drop a reply to be added!
#EPFL #academicsky
go.bsky.app/73zdbtp
#EPFL #academicsky
go.bsky.app/73zdbtp
November 22, 2024 at 2:41 PM
I've put together a starter pack of EPFL researchers across all labs and domains! ๐จ๐ญ Would love to expand this list and showcase more amazing work happening at EPFL. Drop a reply to be added!
#EPFL #academicsky
go.bsky.app/73zdbtp
#EPFL #academicsky
go.bsky.app/73zdbtp
Super interesting example! The trained model seems to understand the colliding better than rolling (the colliding part looks more natural)
December 16, 2024 at 9:54 PM
Super interesting example! The trained model seems to understand the colliding better than rolling (the colliding part looks more natural)
the benchmark section looks amazing! congrats! ๐
December 16, 2024 at 5:41 PM
the benchmark section looks amazing! congrats! ๐
December 16, 2024 at 4:28 PM
Another interesting project I worked on at @icepfl.bsky.social Kudos to @sjaved.bsky.social and all the co-authors!
The findings in MQAT highlight the potential of exploiting modularity in neural networks for efficient and performant compression/adaptation.
Check out the #TMLR paper for details!
The findings in MQAT highlight the potential of exploiting modularity in neural networks for efficient and performant compression/adaptation.
Check out the #TMLR paper for details!
๐ Excited to share our TMLR publication on Modular Quantization-Aware Training (MQAT)!
We show how modular mixed-precision quantization boosts performance & reduces model size for edge devices! ๐ฏ
๐ Page: saqibjaved1.github.io/MQAT_/
#DeepLearning #Robotics #AI #6Dpose #edgeAI
We show how modular mixed-precision quantization boosts performance & reduces model size for edge devices! ๐ฏ
๐ Page: saqibjaved1.github.io/MQAT_/
#DeepLearning #Robotics #AI #6Dpose #edgeAI
December 16, 2024 at 1:14 PM
Another interesting project I worked on at @icepfl.bsky.social Kudos to @sjaved.bsky.social and all the co-authors!
The findings in MQAT highlight the potential of exploiting modularity in neural networks for efficient and performant compression/adaptation.
Check out the #TMLR paper for details!
The findings in MQAT highlight the potential of exploiting modularity in neural networks for efficient and performant compression/adaptation.
Check out the #TMLR paper for details!
Congrats Saqib! Enjoyed working with you!
December 16, 2024 at 1:08 PM
Congrats Saqib! Enjoyed working with you!
Ilyaโs full talk at neurips 2024 "pre-training as we know it will end" at #NeurIPS
youtu.be/6gTjxQLwK4o?...
source: Vincent Weisser
youtu.be/6gTjxQLwK4o?...
source: Vincent Weisser
pre-training as we know it will end
YouTube video by Charlie Li
youtu.be
December 14, 2024 at 1:01 AM
Ilyaโs full talk at neurips 2024 "pre-training as we know it will end" at #NeurIPS
youtu.be/6gTjxQLwK4o?...
source: Vincent Weisser
youtu.be/6gTjxQLwK4o?...
source: Vincent Weisser
Yeah, back in the day interns at bd had some serious access permissions, but this is taking it too far;
still imo retracting the paper is unlikely, I wonder how neurips will react
still imo retracting the paper is unlikely, I wonder how neurips will react
December 12, 2024 at 11:27 AM
Yeah, back in the day interns at bd had some serious access permissions, but this is taking it too far;
still imo retracting the paper is unlikely, I wonder how neurips will react
still imo retracting the paper is unlikely, I wonder how neurips will react
Reposted by Chengkun Li
Last chance! #AMLDEPFL2025 early bird ticket sales end tomorrow December 11. Get yours๐https://buff.ly/3UYv8Cr. Join us for inspiring speakers, comprehensive tracks, cutting-edge exhibition, hands-on workshops, and unmatched networking. February 11-14, 2025 SwissTech Convention Center EPFL Lausanne
December 10, 2024 at 9:05 AM
Last chance! #AMLDEPFL2025 early bird ticket sales end tomorrow December 11. Get yours๐https://buff.ly/3UYv8Cr. Join us for inspiring speakers, comprehensive tracks, cutting-edge exhibition, hands-on workshops, and unmatched networking. February 11-14, 2025 SwissTech Convention Center EPFL Lausanne
Perhaps instead of solely focusing on preventing forgetting in AI systems, we should be asking: How can we implement more selective, adaptive forgetting mechanisms similar in a continual learning framework? [4/4]
Thoughts?
#continual
Thoughts?
#continual
December 9, 2024 at 7:01 PM
Perhaps instead of solely focusing on preventing forgetting in AI systems, we should be asking: How can we implement more selective, adaptive forgetting mechanisms similar in a continual learning framework? [4/4]
Thoughts?
#continual
Thoughts?
#continual