🚀 Exciting projects from my Mobile Computing Lab in SS'24! Students are innovating with sensors, ML, and on-device computing. Highlights: Master Wang Game 🎮 Magic: The Gathering Scanner 🃏 TopOut App 🧗‍♂️ Citizen Weather Forecast 🌦️ sites.google.com/view/olgasaukh… #MobileComputing #AI

Exciting opportunity! 🚀 Join the Edge-Device LLM Challenge at #NeurIPS2024 to innovate and optimize LLMs for edge devices. Check out the details below👇! #AI #EdgeComputing

We strongly encourage #CoLLAs2024 participants to register before July 15th - which is only a few days away. Sign up today and start packing for Pisa! 👇

I am proud member of Stable Diffusion 3, and we won best paper award at #ICML2024

#CoLLas2024 Today oral session starting with "Subspace-Configurable Networks" presented by Dong Wang 🐨

Can't wait for next Monday's EfficientML reading group! 🚀

🚀 Excited to announce the launch of our Twitter page! 🚀 We’re the Embedded Learning and Sensing Systems (ELSS) group at TU Graz, pushing the limits of embedded and efficient #AI. Follow us for updates on our latest #research! 🌍💡 iti.tugraz.at/elss

🔥 We’re hiring! Join the Embedded Learning and Sensing Systems group @TUGraz as a PhD researcher in Embedded Machine Learning! 🌍🔍 📅 Deadline: Oct 20, 2024 🔗 More info: tugraz.at/en/institutes/… #PhDPosition #EmbeddedAI #MachineLearning #ELSS

Doing good science is 90% finding a science buddy to constantly talk to about the project.

🚀 Excited for the next #EfficientML reading group! 📅 21 Oct, 5pm CEST 👤 Francesco Tosoni (University of Pisa) on greener matrix ops via lossless compressed formats. Don’t miss out! 🌍⚡️ Details & paper: arxiv.org/pdf/2409.18620

📚 Next #EfficientML Reading Group! 🗓 Oct 28 @ 5pm CEST 🎤 Mathador-LM: A Dynamic Benchmark for Mathematical Reasoning on LLMs with Eldar Kurtić (NeuralMagic & ISTA) 🔗 arxiv.org/pdf/2406.12572

🚀 The next EfficientML talk ⬇️ 🧑‍🔬 The Uncanny Valley: Exploring Adversarial Robustness from a Flatness Perspective by Nils Philipp Walter & Linara Adilova 📅 11 Nov 2024 🕔 5pm CET Discover a curious twist in adversarial attacks! 🔗 arxiv.org/abs/2405.16918

Workshop alert 🚨 We'll host in ICLR 2025 a workshop on modularity, encompassing collaborative + decentralized + continual learning. Those topics are on the critical path to building better AIs. Interested? submit a paper and join us in Singapore! sites.google.com/corp/view/mcdc…

CVPR2025: Are you passionate about Large Vision models? How about efficiency? - We are looking for reviewers for eLVM workshop - Also eager to read your submissions! workshop page: sites.google.com/view/elvm/home reviewer enrolment: bit.ly/3Flhjcb #CVPR2025

1/ 🚨 New paper alert! 🚨 We explore a key question in deep learning: Can independently trained Transformers be linearly connected in weight space — without a loss barrier? Yes — if you uncover their rich symmetries. 📄 arXiv: arxiv.org/abs/2506.22712