Conference on Parsimony and Learning (CPAL)

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 cpal.cc

Winners: @GhoshAvrajit @angcharlesli @bhavya_vasudeva @LingjingKong @Real_HDong @yuko_kuroki_cs @Charlesyooo1 @ChenLingjiao @luu_yinn @RickTDing @KyriectionZhang Bowen Song Can Yaras Yuqing Wang Zhen Tan

You don't need the University Tübingen @tubingen telescope to see Rising Stars! CPAL is proud to announce of the 2026 recipients of the Rising Star Award cpal.cc/rising_stars_a…. Come hear them talk at CPAL the next 3 days

Arriving Tübingen for CPAL 2026! We'll be presenting 2 papers there: 🚀 FOSL: A Foldable Sparse-and-Low-Rank Method for Efficient LLM Pre-training 🚀 GRAIL: Post-hoc Compensation by Linear Reconstruction for Compressed Networks If you’re here, ping me to grab a ☕️ and chat.

Attending CPAL in Tubingen, Germany this week.

We got best paper award at CPAL. I am sure Ali will do a great job at presenting this work. There are some quite interesting insights in it.

Two Red Hat AI research papers accepted to major 2026 conferences. 1️⃣ Panza: Design and Analysis of a Fully-Local Personalized Text Writing Assistant (Accepted to @CPALconf 2026) • A fully local, personalized writing assistant that learns your style and runs entirely on-device. • LoRA-style fine-tuning + quantization • Built for sensitive data • Includes a Gmail plugin • Paper: arxiv.org/abs/2407.10994 • Code: github.com/IST-DASLab/Pan… Congrats to Red Hat AI teams @_EldarKurtic, @il_markov, @nir_shavit, and @DAlistarh. 2️⃣ Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization (Accepted to @iclr_conf 2026) • New FP4 approach for MXFP and NVFP • Optimized for latest AMD and NVIDIA GPUs, including DGX B200 • Introduces Micro-Rotated-GPTQ with block-wise Hadamard transforms • Paired with QuTLASS kernels for fast inference with negligible overhead • Paper: arxiv.org/abs/2509.23202 Congrats to Red Hat AI teams @RobertoL_Castro, @_EldarKurtic, Shubhra Pandit, Alexandre Marques, @markurtz_, and @DAlistarh. Fully local AI. Cutting-edge quantization. Real performance work shipping upstream.

🚨CPAL registration is open! cpal2026.vokdams-ticketservice.de/payment/master

@YTraonmilin Congrats!

Good week ! Our paper with A. Joundi and J.-F. Aujol "From sparse recovery to plug-and-play priors, understanding trade-offs for stable recovery with generalized projected gradient descent" hal.science/hal-05401157v1 has been accepted to conf. on Parsimony and Learning @CPALconf

@nityanandmathur Congrats!

Where does pronunciation live in a large language model (LLM)–based text-to-speech (TTS) system, and how can we surgically modify it for specific texts while preserving all other model behavior? We’ve been trying to answer this question for a while, and after a lot of failed ideas, debugging, and rethinking assumptions, we finally hit a breakthrough, and I am excited to share that our work has been accepted to @CPALconf 2026. @A_a_yush @harshan2002 @AkshatMandloi10 @kamath_sutra

@feliwang177207 Thank you for reaching out - we are still finalizing everything. The registration button should be up in the next few weeks!

@CPALconf Hello! I found that there is no registration button on the CPAL website. Will it be open in the next few weeks?

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 cpal.cc

REMINDER: Just 3 days left to apply for CPAL's Rising Star Award! cpal.cc/rising_stars_g…

🚨 The deadline for CPAL has been extended by a week: it is now December 12th, 2025 (AOE) 🚨 If you've been frustrated by your experience submitting to ICLR or other big conferences, you still have TIME to submit to CPAL

Submitting to CPAL: - You get high quality reviewers in your field - You get non-overwhelmed Area Chairs carefully evaluating the reviews - You get to be part of a small, interdisciplinary community that cares about your work

17 days to go! Don’t miss the deadline!

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 cpal.cc/rising_stars_g…

Deadline for CPAL coming up on Dec 5! Submit your best work on Parsimony and Learning and come join us in Tübingen in March!

Tired of receiving AI-generated reviews? Try CPAL! CPAL keeps things small — so every paper is reviewed by real experts, not algorithms.

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 papers fly from @VITAGroupUT 🔗in-time over-parameterization: proceedings.neurips.cc/paper/2021/fil… 🔗 Granet: proceedings.mlr.press/v139/liu21y/li… 🔗 Random sparse training: openreview.net/forum?id=VBZJ_… 🔗 Outlier-weighed LLM pruning: arxiv.org/abs/2310.05175 🔗 Sparsity May Cry: arxiv.org/abs/2303.02141 The future is sparse. #Sparsity #DeepLearning