FunAI
11 posts
@FunAILab
Research lab led by @y_m_asano at @utn_nuremberg. We conduct fundamental AI research and develop core technology for future Foundation Models.
My slide deck is feature complete. Finally ready for my European speaking tour 🇪🇺 Plan to record this talk too, once back in my #Toronto home studio.
🚀 Two Big Announcements for ELLIS | ELIAS | ELLIOT Winter School on Foundation Models (FoMo) 2026, which is organised at the Tolhuistuin from 24-27 March 2026! 1️⃣ We’re excited to reveal the incredible speaker lineup for FoMo 2026... (1)
Today we introduce Bidirectional Instruction Tuning (Bitune). It's a new way of adapting LLMs for the instruction->answering stage. It allows the model to process the instruction/question with bidirectional attention, while the answer generation remains causal.
Can open-data models beat DINOv2? Today we release Franca, a fully open-sourced vision foundation model. Franca with ViT-G backbone matches (and often beats) proprietary models like SigLIPv2, CLIP, DINOv2 on various benchmarks setting a new standard for open-source research🧵
Ever wondered if better LLMs actually have a better understanding of the visual world? 🤔 As it turns out, they do! We find: An LLM's MMLU performance correlates positively with zero-shot performance in a CLIP-like case when using that LLM to encode the text. 🧵👇
