ImHorPhen

“On a log-log plot, my grandmother fits on a straight line.” -Physicist Fritz Houtermans There's a lot of truth to this. log-log plots are often abused and can be very misleading 1/5

Congratulations to Pierre Bouillon for his new position @Cornell after the successful defense of his PhD @IRHS_Angers in collaboration between @UnivAngers and I.F.O International Fruit Obtention via @AnrtPage Video accessible on our @imhorphen channel youtu.be/iLmVWbh41hg

Students don't need a perfect teacher. Students need a happy teacher, who's gonna make them excited to come to school and grow a love for learning.

Heureux de sortir du laboratoire @imhorphen @UnivAngers pour une rencontre Ciné-débat sur l'IA au quotidien à la Pommeraye organisé en partenariat avec la MSA et le cinéma Grand écran mauges-sur-loire.fr/evenements/cin…

At the opening of ⁦@OpenAI⁩´s office in Paris, ⁦Head of Developer Experience ⁦@romainhuet⁩ shows the use of #o1 to program a drone to fly and broadcast live video from scratch. All instantly and without any specific technical knowledge. ✨

Open-source alternative to OpenAI's voice. Extends text-based LLM to have native "listening" ability. Think of it as an open data, open weight, on device Siri. What it offers: 📌 Implements native "listening" abilities in LLMs, similar to Siri but runs locally on-device 📌 Latest v0.4 achieves 64.63 MMLU score with enhanced context handling and noise management 📌 Provides complete training pipeline combining speech noise and multi-turn conversation data 📌 Includes ready-to-use demos via WebUI, Gradio interface, and Colab notebooks

Nice collection of LLM papers, blogs, and projects, focussing on OpenAI o1 and reasoning techniques. What it offers: 📌 Curates papers, blogs, talks, and Twitter discussions about OpenAI's o1 and LLM reasoning 📌 Tracks frontier developments in LLM reasoning capabilities and techniques

📅 On 26.11.2024 at 4:40 p.m., we invite you to the inaugural lecture "From Pixels to Patterns: #MachineLearning for Bioimage Analysis" of Prof. Martin Weigert. He is professor for Machine Learning for Spatial Understanding at @tudresden_de & @Sca_DS. 👉 scads.ai/calendar/inaug…

🎧 Create your own web audio experiences! Our new course on the Web Audio API is here—learn how to build interactive sound projects. #WebAudioAPI #SoundDesign #LearnCoding Sign up now: ircam.fr/agenda/design-…

The @RoyalMicroSoc Journal of Microscopy special issue for Data Analysis In Microscopy (DAIM) is now out and includes the paper on MIA! onlinelibrary.wiley.com/toc/13652818/2…

Extremely happy to share this review #FLIM at @MethodsPrimers in collaboration between #LFD @michelledigman @torrado_belen and @advanced_unit #BrunoPannunzio. Special thanks to editor #NatalieBarnes, who help us to shape this review. Take a look 👉 rdcu.be/dZqtr

THE BEST visual explainer of how information propagates through a transformer. If you want to have more than intuition about how the Transformer architecture is ruling the LLM world → open-source project explains everything about LLM Transformer Models! → A great resource for anyone looking to gain a deeper understanding of how Transformer-based AI models like GPT work, including: → Self-attention mechanisms → Encoder-decoder architecture → Positional encoding → Multi-head attention

My slides about "Developing a Training Strategy" presented at #GloBIAS2024 are available #openaccess 🖥️🧑‍🏫🔓 zenodo.org/records/140537…

The Phd Defense of Abderazzaq Moufidi is on our youtube channel. Congratulation Doctor Abder @UnivAngers @groupeesaip @Angers youtube.com/channel/UCsd9D…

We built a GPT-4o-powered cleaning robot. - $250 for the robot arms - 4 days to build Open source is truly democratizing the field of robotics. @KasparJanssen

Two great books available online that I recommend on information theory: * "Information theory, inference and learning algorithms" by Sir MacKay * "Information Theory: From Coding to Learning" by Y. Polyanskiy and Y. Wu

I just uploaded my slides for the webinar about #BioImageAnalysis Code Generation at #I2K2024 - #openaccess. See you in an hour! 🔬🖥️🤖🔓 zenodo.org/records/140010…

😍⚠️And it’s out in @J_Cell_Sci!! Our review on the opportunities and challenges of using Machine Learning in Microscopy research 🤖🔬! From using ML to curate data to using ML to give us more KNOWLEDGE about our data (i.e. Interpretation 😉) DOI: doi.org/10.1242/jcs.26… (1/n) ⬇️

If you liked UNIC, check out Theia: a simple approach for distilling pretrained models, e.g.,CLIP, DINOv2, SAM, DepthAnything into a unified model with improved performance on policy learning theia.theaiinstitute.com

Today presenting the prototype of napari-phasors! A fruitful collaboration with @MalacridaLab, @schutyb and Bruno Pannunzio to port features of the recent @phasorpy library release into @napari_imaging ! If you are in #I2K, come to poster 54