Chengkun Li @ckli.bsky.social · 08/11/2025Training 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 steps👍 210
Reposted by Chengkun LiAlexander Mathis @trackingskills.bsky.social · 04/09/2025Something 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 38121
Chengkun Li @ckli.bsky.social · 30/07/2025The more you use JAX, the more you feel its power.. like wielding the sharpest knife in your toolbox 🗡️ 030
Chengkun Li @ckli.bsky.social · 26/02/2025It’s pretty strange they don’t have this in zurich. At EPFL, all stem master’s students have a mandatory internship, and we get the chance to intern at big tech companies 120
Chengkun Li @ckli.bsky.social · 18/02/2025Quick life update: I recently started my PhD back in the beautiful Lac Léman region at EPFL Campus Biotech. Just wanted to show off the office a bit! 😎 More nature views coming soon… 040
Reposted by Chengkun LiEPFL AI Center @epfl-ai-center.bsky.social · 29/01/2025Ep 2 of #InsideAI is out! 🎙️🎉 We sat with Google Fellow Urs Hölzle. From optimizing data centers to AI efficiency, AGI, autonomous vehicles & Europe’s AI outlook—don’t miss this insightful conversation. On Spotify: open.spotify.com/episode/5Tu9... or Apple Podcast: podcasts.apple.com/us/podcast/c...podcasts.apple.comConversation with Urs HölzlePodcast Episode · Inside AI · 01/29/2025 · 1h 7m 082
Chengkun Li @ckli.bsky.social · 29/01/2025Stopped by BAAI (Beijing Academy of AI) to visit a friend! ☕️ The coffee was great, and it’s right between China’s top two universities. Sadly, the hanging garden is closed for now. Overall a quite nice place to do research #Beijing 020
Reposted by Chengkun LiAlejandro Nuñez-Jimenez @anunezjimenez.com · 06/01/2025We 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! 045
Reposted by Chengkun LiChengkun Li @ckli.bsky.social · 22/11/2024I've put together a starter pack of EPFL researchers across all labs and domains! 🇨🇭 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 7103
Reposted by Chengkun LiSepideh Mamooler@ACL🇦🇹 @smamooler.bsky.social · 17/12/2024🚀 Introducing PICLe: a framework for in-context named-entity detection (NED) using pseudo-annotated demonstrations. 🎯 No human labeling needed—yet it outperforms few-shot learning with human annotations! #AI #NLProc #LLMs #ICL #NER 1128
Chengkun Li @ckli.bsky.social · 16/12/2024Super interesting example! The trained model seems to understand the colliding better than rolling (the colliding part looks more natural) 010
Chengkun Li @ckli.bsky.social · 16/12/2024Goodbye sunny Barcelona Hello again Zürich #photography #barcelona 050
Chengkun Li @ckli.bsky.social · 16/12/2024Another 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! 020
Chengkun Li @ckli.bsky.social · 14/12/2024Ilya’s full talk at neurips 2024 "pre-training as we know it will end" at #NeurIPS youtu.be/6gTjxQLwK4o?... source: Vincent Weisseryoutu.bepre-training as we know it will endYouTube video by Charlie Li 030
Chengkun Li @ckli.bsky.social · 12/12/2024Yeah, 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 100
Reposted by Chengkun Liappliedmldays.bsky.social @appliedmldays.bsky.social · 10/12/2024Last chance! #AMLDEPFL2025 early bird ticket sales end tomorrow December 11. Get yours👉https://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 001
Chengkun Li @ckli.bsky.social · 09/12/2024Perhaps 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 010
Chengkun Li @ckli.bsky.social · 09/12/2024So probably, the real challenge isn't preventing ALL forgetting - it's developing mechanisms to identify which patterns should be preserved vs. discarded. This is where biological systems could excel through social feedback, interactions, expert guidance, and iterative refinement. [3/4] 100
Chengkun Li @ckli.bsky.social · 09/12/2024In both natural and artificial learning systems, selective forgetting (perturbation/regularization) could help escape local optima and unlearn inefficient or corrupted patterns (especially relevant given concerns about poisoned training data) [2/4] 100
Chengkun Li @ckli.bsky.social · 09/12/2024💭When reading continual learning literature, there's always the term 'catastrophic forgetting' being discussed as a major challenge. But looking at some efficient learning systems (e.g. biological-based ones), it's hard to not notice forgetting isn't necessarily a bug - it's sometimes a merit. [1/4] 100
Reposted by Chengkun LiPaul Vicol @paulvicol.bsky.social · 08/12/2024Introducing the @tmlr-pub.bsky.social account, that is now posting the latest TMLR published papers! Check it out! 15220
Reposted by Chengkun LiMartin Mundt @martinmundt.bsky.social · 07/12/2024Three days left to apply for a PhD in my group! ⬇️⬇️ Come join us to work on the forefront of adaptive AI & lifelong machine learning. We’ve got lots of exciting ideas in store 🤗 0119
Reposted by Chengkun LiFrederic Jacobs @fredericjacobs.com · 05/12/2024Samy Bengio, Senior Director of AI and ML Research at Apple is appointed professor at EPFL and will be "active in teaching while also expanding the opportunities for academic collaboration between EPFL and Apple" actu.epfl.ch/news/appoint...actu.epfl.chAppointment of EPFL professorsThe Board of the Swiss Federal Institutes of Technology has announced the appointment of professors at EPFL. 062
Reposted by Chengkun LiAndreas Steiner @andreaspsteiner.bsky.social · 05/12/2024🚀🚀PaliGemma 2 is our updated and improved PaliGemma release using the Gemma 2 models and providing new pre-trained checkpoints for the full cross product of {224px,448px,896px} resolutions and {3B,10B,28B} model sizes. 1/7 16921
Chengkun Li @ckli.bsky.social · 04/12/2024any plans for opening offices in lausanne or the french-speaking region? 😜 the weather is warmer and the views are a bit nicer imo (debatable in my old internship team tho) 100
Chengkun Li @ckli.bsky.social · 04/12/2024Congrats! Looking forward to reading your future work at OpenAI Zurich! 020
Reposted by Chengkun LiCarmen Sandi @carmensandi10.bsky.social · 03/12/2024We are hiring! Postdoc position in Data Science in Neuroscience in our lab @EPFL Cutting-edge research analyzing rich datasets (VR, physiol, behav, metabolism, neuroimaging) to understand human stress, anxiety & motivation Apply!: epfl.ch/labs/lgc/ind... #Postdoc #DataScience #Neuroscienceepfl.chOpen positionsPhD positions Postdoc positions 15548
Chengkun Li @ckli.bsky.social · 02/12/2024Looks so cool! Can’t wait to read the follow-up work on GIVT! 000
Chengkun Li @ckli.bsky.social · 29/11/2024Thanks! Just added you :) feel free to repost and help spread the word🚀 010
Reposted by Chengkun LiFrancesco Mondada @francescomondada.bsky.social · 29/11/2024La #newsletter_robotique est à nouveau là, avec des belles offres pour associer créativité, curiosité et technologie, tout en restant attentifs à l'environnement. Profitez sans modération et faites passer le message! actu.epfl.ch/newsletter/n... 063
Chengkun Li @ckli.bsky.social · 27/11/2024Such a nice blog post! Reminds me of the good old distill.pub days 030
Reposted by Chengkun LiGautam Kamath @gautamkamath.com · 26/11/2024TMLR will go on winter break starting December 2. A chance for authors, reviewers, and AEs to all get some much deserved peace and quiet. 3544
Reposted by Chengkun LiFrançois Fleuret @francois.fleuret.org · 26/11/2024My deep learning course at the University of Geneva is available on-line. 1000+ slides, ~20h of screen-casts. Full of examples in PyTorch. fleuret.org/dlc/ And my "Little Book of Deep Learning" is available as a phone-formatted pdf (nearing 700k downloads!) fleuret.org/lbdl/ 461253247
Chengkun Li @ckli.bsky.social · 25/11/2024agree, public double-blind review + public discussions (e.g., OpenReview, AlphaXiv) could help mitigate the issue to some extent 000
Chengkun Li @ckli.bsky.social · 23/11/2024please repost to help spread the word! 🙌 feel free to comment or ping me if you’d like to be added to the starter pack 000
Reposted by Chengkun LiJeff Boudier 🤗 @jeffboudier.hf.co · 22/11/2024Hey Skeeters, you can add your Sky handle to your @huggingface.bsky.social profile - here's how 1317