Both pictures were taken in Berlin. One of them, today.

Excited to announce that our paper has been accepted to NeurIPS D&B 2024! Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models Read the paper here: lnkd.in/dfHzA9eg Check out the project website: lnkd.in/dfQgKb24

🎉 We had a blast presenting #VisualRiddles at the D&B Track at #NeurIPS2024! 🙏 Thanks to everyone who stopped by—We hope this benchmark will push models with better visual reasoning and world knowledge. 🌐 Missed it? Learn more here: visual-riddles.github.io nitzan guetta

🚀🚀🚀 OpenAI O1, Gemini-2.0 and Gemini-2.0-thinking are on the #VisualRiddles leaderboard! Multiple Choice: Gemini-2.0-thinking hits 60% accuracy (84% with hints!) Open-Ended (Auto-Rating): O1 leads with 58% accuracy. Check it out: 🔗 visual-riddles.github.io Yonatan Bitton

🚀 A new way to control AI video generation - by concatenation of control signals and LoRAs trained on just a few samples We’re releasing 3 control LoRAs for LTX-Video: open-pose, depth, and canny edges. Plus: training code so you can build your own types of control. 🧵