Twitter Beğeni Hilesi

Happy to see our paper on adversarial arithmetic released! (arxiv.org/abs/2311.07587)

Excited to share that our paper on "Frontier Language Models are not Robust to Adversarial Arithmetic, or 'What do I need to say so you agree 2+2=5?'" are now posted arxiv.org/abs/2311.07587

Welcome Gemini 1.0 🎉

Excited to announce our new work on using synthetic data for improving mathematical problem solving and code generation in LLMs! arxiv: arxiv.org/abs/2312.06585 A small amount of fine-tuning can lead to large gains (>6% on Hendrycks MATH with Palm-2)

Can Transformers be used to learn object-centric representations? Yes! If we "invert" the attention operation by taking the softmax over the queries instead of the keys. paper: openreview.net/pdf?id=m9s6rnY…

The Gemini report is now up on Arxiv. arxiv.org/abs/2312.11805

Very excited for the release of Gemini 1.5 Pro, a highly capable multimodal model with Huge context length. Big congratulations to the team.

Introducing Gemma - a family of lightweight, state-of-the-art open models for their class, built from the same research & technology used to create the Gemini models. Blog post: blog.google/technology/dev… Tech report: goo.gle/GemmaReport This thread explores some of the

Introducing SIMA: the first generalist AI agent to follow natural-language instructions in a broad range of 3D virtual environments and video games. 🕹️ It can complete tasks similar to a human, and outperforms an agent trained in just one setting. 🧵 dpmd.ai/3TiYV7d

We are rolling out Gemini 1.5 Pro API so that you can keep building amazing stuff on top of the model like we've seen in the past few weeks. Also, if you just want to play with Gemini 1.5, we removed the waitlist: aistudio.google.com Last, but not least, we pushed the model

nanoChinchilla. Reproducing Chinchilla-Optimal Scaling Phenomenon: Colab, 1 Hour, 100 Lines, + Beautiful Theory tinyurl.com/2saj6bkj

Happy to announce that NanoDO is now open-sourced. NanoDO is highly readable and easily adaptable implementation of a Transformer decoder-only language model in Jax.

Really nice work from Lechao Xiao highlighting important topics about training and scaling large language models!

Congratulations Geoffrey Hinton . Very well deserved.

One more nobel prize for AI. What a great team! I am really proud I have been part of Google Brain and Google DeepMind. Congratulations Demis Hassabis and John.