ELSS Team

Excited to present our paper "Sensor-Guided Adaptive ML on Resource-Constrained Devices" at #IoT2024! 🎉 We show how sensor data (e.g., IMUs) can boost ML model accuracy by 7.57% with 75% fewer parameters, enabling efficient & robust #EdgeAI. Full paper: t.ly/n7rMR

@nilspwalter @LinaraAdylova

🚀 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

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

🚀 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

🔥 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

🚀 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