Conference on Parsimony and Learning (CPAL)
@CPALconf
Followers
944
Following
443
Media
53
Statuses
264
CPAL is a new annual research conference focused on the parsimonious, low dimensional structures that prevail in ML, signal processing, optimization, and beyond
Joined May 2023
Calling all parsimony and learning researchers 🚨🚨 The 3rd annual CPAL will be held in Tübingen Germany March 23–26, 2026! Check out this year's website for all the details https://t.co/Ra08OCHmA9
0
7
17
17 days to go! Don’t miss the deadline!
📣 Call for Papers: Conference on Parsimony and Learning, 2026 Join @ELLISInst_Tue & @MPI_IS to explore and share your work on parsimony in ML, signal processing, optimisation & beyond. 🗓 March 23-26, 2026 📍 Tübingen 🇩🇪 🔗 Details & submission: https://t.co/9eYbNi3lIM
0
3
8
Hey there 🎵 you’re a rock star 🎶submit to CPAL Rising Star Don’t miss out on your chance to be a CPAL Rising Star! Submit by December 15th https://t.co/GVExJzlaf4
0
1
5
Deadline for CPAL coming up on Dec 5! Submit your best work on Parsimony and Learning and come join us in Tübingen in March!
Calling all parsimony and learning researchers 🚨🚨 The 3rd annual CPAL will be held in Tübingen Germany March 23–26, 2026! Check out this year's website for all the details https://t.co/Ra08OCHmA9
0
2
3
Tired of receiving AI-generated reviews? Try CPAL! CPAL keeps things small — so every paper is reviewed by real experts, not algorithms.
Getting AI-written reviews for your AI paper? 😅 Try CPAL 2026 — a focused conference where humans actually read your work! Every paper gets careful attention from area chairs 🧑, not bots 🤖. Join us in Tübingen → https://t.co/cXKbuiJdsL #CPAL2026 #AI
0
1
5
Love seeing @OpenAI highlight sparse circuits — sparsity is finally getting the attention it deserves. In our earlier work, we showed how sparse training can unlock robustness, efficiency, and better scaling: ICML’21 • NeurIPS’21 • ICLR'22 • ICML'24 • ICLR'23. Many great
Excited to share our latest work on untangling language models by training them with extremely sparse weights! We can isolate tiny circuits inside the model responsible for various simple behaviors and understand them unprecedentedly well.
3
13
80
Tired of receiving AI-generated reviews? Try CPAL! CPAL keeps things small — so every paper is reviewed by real experts, not algorithms.
Getting AI-written reviews for your AI paper? 😅 Try CPAL 2026 — a focused conference where humans actually read your work! Every paper gets careful attention from area chairs 🧑, not bots 🤖. Join us in Tübingen → https://t.co/cXKbuiJdsL #CPAL2026 #AI
0
3
8
Getting AI-written reviews for your AI paper? 😅 Try CPAL 2026 — a focused conference where humans actually read your work! Every paper gets careful attention from area chairs 🧑, not bots 🤖. Join us in Tübingen → https://t.co/cXKbuiJdsL #CPAL2026 #AI
0
2
11
CPAL 2026 has an INCREDIBLE list of confirmed keynote speakers: @BachFrancis
@bschoelkopf
@FannyYangETH
@arkrause
@MatthiasBethge
@StefanieJegelka Niao He Taiji Suzuki Jared Tanner Ulrike von Luxburg
0
1
4
Calling all junior researchers! Apply now for CPAL's Rising Star Award💫 A great opportunity to get recognized by the community and network with senior researchers! Apply now through December 15th: https://t.co/GVExJzkCpw
0
1
5
Super excited to have CPAL 2026 at Tübingen. At least two reasons to submit to CPAL: (1) professional reviewers in your fields, (2) come to see how this beautiful old city is being reborn in the age of AI.
Calling all parsimony and learning researchers 🚨🚨 The 3rd annual CPAL will be held in Tübingen Germany March 23–26, 2026! Check out this year's website for all the details https://t.co/Ra08OCHmA9
0
2
9
Take a break from hunting demons and submit to CPAL! Now accepting submissions on OpenReview https://t.co/EkHOmmmgH5
0
1
5
Frustrated by a rejection from NeurIPS 😠? Consider submitting your work on sparsity/optimization/learning to CPAL, a conference and community that *appreciates* high quality work ☺️! Deadline December 5th: https://t.co/Ra08OCHmA9
0
2
6
I am very excited to announce that the third CPAL conference: https://t.co/xVwrpSEvoM is to be held at Tübingen, Germany in March 2026 (after Hong Kong and Stanford). Complementary to the arguably too many mega conferences on machine intelligence, CPAL aims to be focused and
cpal.cc
Conference on Parsimony and Learning (CPAL) - Addressing the low-dimensional structures in high-dimensional data that prevail in machine learning, signal processing, optimization, and beyond.
0
12
30
The course/book is to be about AI and by AI.
[1/3]🤨Many grad school courses teach you to train a LM but what if we train one to teach? Here is our practice! We build & deploy a cute 7B LM that can answer questions regarding the book. As it's only 7B, it will not relieve students from mathy homework.🤡
2
4
23
Please RT - Open PhD position in my group at the Donders Center for Neuroscience, Radboud University. We're looking for a PhD candidate interested in developing theories of learning in neural networks. Applications are open until October 20th. Info:
ru.nl
Thank you for your interest in working at Radboud University. We are no longer taking applications for this job.
0
11
14
I came to realize that, for studying intelligence, the only "inductive bias" that one is allowed to assume is that the data worth sensing and learning has extremely low intrinsic dimension. This can be precisely verified and quantified by the data's volume, entropy, or coding
15
25
260
There are only two types of generic linear/matrix operations that truly scale: one is low-rank and the other is sparse.
#CPAL2025 invited speaker @tydsh shows that attention map first goes *sparser* than gets *denser* as we train a nonlinear attention mechanism using gradient flow — and the phenomena show up in the experiments too.
4
5
66