First YueCrewer off to NeurIPS Conference 🥳 Meet all of the ones going: Jennifer J. Sun - On the job market! 👩‍🏫 Sabera Talukder - brains 🧠 YihengLin - 🧮 Chris Yeh - climate 🌏 Cameron Voloshin - 🧮 Francesca-Zhoufan Li - cells 🧫 Yisong Yue - the boss 💪🏽

Go see our first 🤩 poster NeurIPS Conference tomorrow from Cameron Voloshin Hoang M. Le Swarat Chaudhuri Yisong Yue!! 👇👇👇👇👇👇

We're presenting at Learning from Time Series for Health tomorrow at #NeurIPS! 11:30am - 12:30pm CST, Room 392 Organized by Marzyeh A.Goldenberg Satya Narayan Shukla G.Ratsch Tom Hartvigsen Sana Tonekaboni Jennifer J. Sun Bing Wen Brunton Yisong Yue and I would ♥️ if you dropped by 🤗

Yue Crew #Neurips Dinner Underway 🤗 So many embarrassing Yisong Yue stories coming to light 😂🤫

Go see Francesca-Zhoufan Li @ ICLR'25's poster tomorrow at #NeurIPS!!

NeurIPS officially ended yesterday 😭 and it was 🔥 both in person and virtually! I enjoyed seeing old faces and meeting so many new ones ♥️ I put together some topics + papers that piqued my interest and maybe they'll pique yours too🤗 saberatalukder.com/neurips_2022.h…

GUYS the CosyneMeeting workshop program just dropped 🥳 AND Eric Trautmann's + my workshop "Taming Complexity: Discovering Interpretable Latent Spaces in Human Brains & Behaviors" will be on your Mont Tremblant menu🧑‍🍳 Too early to say #Cosyne2023? 🙊🤫 cosyne.org/workshops-prog…

Post #ICML2023 submission feast! 😋🍜

Conformal Generative Modeling on Triangulated Surfaces A general framework that can reliably train probability distributions on a wide range of complicated manifolds. 1st Author: Victor Dorobantu Project: vdorbs.github.io/conformal-gene…

We are thrilled to announce "automatic gradient descent"---a neural network optimiser without hyperparameters. AGD trains out-of-the-box and at ImageNet scale. paper: arxiv.org/abs/2304.05187 PyTorch: github.com/jxbz/agd 1/5

phd time Berkeley AI Research Jennifer Listgarten Sergey Levine !! also time to start using twitter…? super excited for the next several years and genuinely so much appreciation to Yisong Yue Ryan Adams Yue Lab Caltech Deniz Oktay Katie Bouman Adam Blank + many others who have built me up :))

Really exciting work by Jeremy Bernstein, Chris Mingard & others on designing hyperparameter-free optimizers for deep neural networks!

All animals behave in 3D - we discover 3D poses directly from multi-view videos without requiring annotations. Essentially videos -> 3D keypoints + connections We will be #CVPR2025 on June 21! BKinD-3D Paper: arxiv.org/abs/2212.07401 Co-first-authors Lili Karashchuk & Amil Dravid

Excited for this!! 🤓

Today's lab meeting reminder 😂 Coming to you live from Pasadena, it's Friday Night Live with your hosts Sabera Talukder & Victor Dorobantu. In tonight's top story Chris Yeh returns from Rwanda with the latest ICLR tidbits 👀 What ML news hides in plain sight? Tune in to find out!

Our favorite photo from ICLR 2023! It's going to be a YueCrew kind of ICLR 2024 😍🧑‍💻🇦🇹 📸 PC Chris Yeh

Congratulations Lu Gan!!!

Congrats to our postdoc Lu Gan 🥳🥳🥳

Excited to share our work on symbolic music generation: arxiv.org/abs/2402.14285! We introduce a symbolic music generator with non-differentiable rule guided diffusion models, enabling musicians to effectively use it as a compositional tool. Website: scg-rule-guided-music.github.io. 🧵👇

Tokenization (aka the root of suffering, iykyk) has gotten a terrible rap this past week😅 but in nascent fields this rap is wack🌶️ I am ecstatic to share➡️TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis TOTEM learns discrete time tokens (not patches!!)