🔥Telegram İfşa

1/N) Are current large multimodal models like #GPT4o really good at video understanding? 🚀 We are thrilled to introduce TemporalBench to examine temporal dynamics understanding for LMMs! Our TemporalBench reveals even the SOTA LMM #GPT4o achieves only 38.5, far from

NEW PREPRINT! Interested in Mendelian randomization and proteomics? We created a comprehensive multi-ancestry proteome-phenome-wide atlas of protein-disease associations in European, African, and East Asian ancestries! medrxiv.org/cgi/content/sh… Website: broad.io/protein_mr_atl…

Public service announcement: Multimodal LLMs are really bad at understanding images with *precision*. x.com/lukeprog/statu… A thread🧵: 1/13.

Excited to share that I will be at Adobe Research in San Jose, CA as a Research Scientist Intern under Valentin Deschaintre Michael Fischer Iliyan Georgiev and Krishna Kumar Singh ! Looking forward to my first California experience! I would love to connect and catch up with anyone in the area :)

🚨Our new paper: VisualToolAgent (VisTA) 🚨 Visual agents learn to use tools—no prompts or supervision! ✅RL via GRPO ✅Decoupled agent/reasoner (e.g. GPT-4o) ✅Strong OoD generalization 📊ChartQA, Geometry3K, BlindTest, MathVerse 🔗oodbag.github.io/vista_web/ 🧵👇

Super excited to present our new work on hybrid architecture models—getting the best of Transformers and SSMs like Mamba—at #COLM2025! Come chat with Nicholas Roberts at poster session 2 on Tuesday. Thread below! (1)

Love this. We also saw benefits of replacing position encodings with NoPE + Mamba in ICL tasks for Mamba-Attn hybrids in arxiv.org/abs/2402.04248