🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Judea Pearl On top of heterogeneity issues, what if we don't have direct access to all the RCT information and need to process complex data structures, e.g., image or text, to retrieve the (factual) outcome for our downstream analysis?

Interested in Causality and its many applications? Don't forget to register for #CLeaR2025, the 4th Conference on Causal Learning and Reasoning, conference May 7-9 in Lausanne, Switzerland! ✅Register ASAP by Mar 31 to enjoy the early-bird discount: cclear.cc/2025/VenueandR…

🚀 Exciting news! Our paper "From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks" has been accepted at ICLR 2025! arxiv.org/abs/2409.14623 A thread on how relative weight initialization shapes learning dynamics in deep networks. 🧵 (1/9)

Excited to present our paper “Unifying Causal Representation Learning with the Invariance Principle” at #ICLR2025 in Singapore! Joint work with DarioRancati, Riccardo Cadei , MarcoFumero, and Francesco Locatello.

🎉 NeCo is accepted to ICLR 2026 #ICLR25 TL;DR: Self-supervised patch-level neighbor consistency boosts dense features of foundation models like DINOv2—in just 19 GPU hours. 📍 Tomorrow,10:00–12:30@Hall3+Hall2B#133 📄 Paper: openreview.net/forum?id=Qro97…

We are presenting JetFormer at ICLR this morning, poster #190. Stop by if you’re interested in unified multimodal architectures!

Come to our poster ‘From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks’ 📍10 am, Hall 3 + Hall 2B, #340.

📍Poster 465 Happening now 🏝️

🚀 Exciting news! #GCPR2025 – the DAGM German Conference on Pattern Recognition – is coming to Freiburg, Germany! 📍🗓️ Mark your calendars: September 23-26, 2025!

One more week to apply to this exciting position... and another position on #CausalRepresentationLearning and #ReinforcementLearning for learning provably correct #concepts from raw data opening up soon!

Happy to finally release the digital version of this series. Fun ML fact: all of these 2018 works used test-time compute across the search space of classifiers. Felt wonky at the time - so also glad inference time search is now back in style. 😉

⚠️ Attention: The site is currently down. Our engineering team is investigating. We will update as soon as possible. You can track progress here: status.overleaf.com Sorry for any inconvenience.

And that's how, from 27K+ submissions, we go back to good old 5K

🌟📚 DAGM Young Researcher’s Forum: Submission deadline - June 04, 2025! Showcase your thesis, meet experts, and compete for the Best Master’s Thesis Award! 🚀 #YoungResearchers #MasterThesis 👉 dagm-gcpr.de/year/2025/subm…

📣Call for Reviewers: We're looking for reviewers with a PhD (or in progress) & research experience in vision, ML, or pattern recognition. Prior reviewing experience is a plus. Be part of the community—review & engage! 📝Deadline: 04.06.2025 👉forms.gle/WmN38bbZaPii9o…

We are thrilled to annouce our conference speaker - Francesco Locatello! Francesco Locatello is a tenure-track assistant professor at the Institute of Science and Technology Austria (ISTA) and an AI resident at the Chan Zuckerberg Initiative. Before, he was a senior applied

Continued....Announcing our Publicity Chairs and Local Organizer: Publicity Chairs: Shashank Agnihotri and Adeel Pervez Shashank Agnihotri Data and Web Science Group ISTAustria Local Organizer: Julia Willi Computer Vision Freiburg