🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Google AI Blog:Project Euphonia’s Personalized Speech Recognition for Non-Standard Speech ai.googleblog.com/2019/08/projec… via @googleai

Understanding how neural networks reach decisions can be challenging, but is also valuable for uses from image analysis to scientific discovery. A new approach, called StylEx, discovers and visualizes how disentangled attributes affect a classifier → goo.gle/357gn9r

Happy to share that my work, Imagic, was accepted to #CVPR2023! A huge thank you to my collaborators @ZadaShiran oran lang omer tov Huiwen Chang Tali Dekel Inbar Mosseri and Michal Irani.

What You See is What You Read? Improving Text-Image Alignment Evaluation paper page: huggingface.co/papers/2305.10…

1/📄 Excited to introduce our paper "What You See is What You Read? Improving Text-Image Alignment Evaluation"! 🖼️📚🔗 arxiv.org/abs/2305.10400 wysiwyr-itm.github.io w. Michal Yarom, Soravit “Beer” Changpinyo, roeeaharoni, Jonathan Herzig, oran lang, Eran Ofek, Idan Szpektor 🧵

The Hidden Language of Diffusion Models paper page: huggingface.co/papers/2306.00… tackle the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a

Text-to-image models revolutionized computer vision, but what do they learn about the world?🤔 We present Conceptor 🧐 a method to inspect the inner representation of a concept by decomposing it into a set of interpretable tokens, which reveals surprising semantic structures🧵

Excited to share our latest research on aligning Large Language Models (LLMs) with human preferences! We're moving beyond single-turn interactions to improve multi-turn conversations. arxiv.org/abs/2405.14655 Joint work by Google Research Google DeepMind (1/8)

Check out our work covered in the latest Google AI blog!

Oran Lang innovates at Google, advancing medical explainability with Generative AI and now with Gemini. His project, StylEx, uses StyleGAN to visualize decision-making. This breakthrough aids understanding and detects biases, opening new research avenues. Explore Oran's impactful

What are the best datasets to measure progress in AI beyond standard ones like ImageNet?

Presenting Looking to Listen, research into a deep learning audio-visual model for isolating a single speech signal from a mixture of sounds. goo.gl/L2V9G2