Google presents Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? Long-context LM: - Often rivals SotA retrieval and RAG systems - But still struggles with areas like compositional reasoning repo: github.com/google-deepmin… abs: arxiv.org/abs/2406.13121

I'll be presenting our TACL paper "Improving Probability-based Prompt Selection Through Unified Evaluation and Analysis" at #ACL2024! 📍 Oral: Mon 12:00 (Machine Learning for NLP I, World Ballroom B) 📍 Poster: Tue 16:00 (Conv. Center A1) Please drop by if you are interested!

Our paper "Do Large Language Models Latently Perform Multi-Hop Reasoning?" will be presented at #ACL2024 today. 📍 Mon 14:00-15:30 Poster Session 2 (Conv. Center A1) Please visit our poster if you are interested, and catch me to chat about the latent reasoning ability of LLMs!

The popular science series 10 Things You Should Know by SevenDials Orion Publishing has a new member: Artificial Intelligence! Out September 26th. You can pre-order it at geni.us/ArtificialInte…

Super proud to have been able to work with you Patrick Lewis! Does this improve my Bacon number?

🚨NEW BENCHMARK🚨 Are LLMs good at linguistic reasoning if we minimize the chance of prior language memorization? We introduce Linguini🍝, a benchmark for linguistic reasoning in which SOTA models perform below 25%. w/ Belen Alastruey, Mikel Artetxe, Marta R. Costa-jussa et al. 🧵(1/n)

We are launching Design Your Own Avatar (DYOA)! With our latest innovations in multimodal generation at Creatify AI , you can now create ultra realistic AI avatars from text description and bring it to life! This unblocks a whole new level of possibilities. Check it out:

Amazing progress Yuxiang (Jimmy) Wu and Zhengyao Jiang, and great to see the impact of "agent scaffolding" given a base model.

I am looking for a Research Scientist intern for 2025. If you have already published work that involves understanding behaviours of AI models looking at their parameters and activations, I would like to hear from you. metacareers.com/jobs/556063310…

I am hiring for a research engineering role in NYC, focused on Gemini post training. If you are interested, please apply here. Deadline is just in two weeks. boards.greenhouse.io/deepmind/jobs/…

Excited to share our prompt tuning playbook! (Not an official product. Just authors tips & tricks for better prompting). I'm most excited about first half on mental models for post-training & prompting. Feedback/forks welcome! #LLM #PromptEngineering github.com/varungodbole/p…

The team @jhamrick and I co-lead is hiring a research engineer. If you are interested in improving the capabilities of LLMs in the planning and reasoning space, and building generally capable agents, please apply! boards.greenhouse.io/deepmind/jobs/…

🚨 New Paper 🚨 Can LLMs perform latent multi-hop reasoning without exploiting shortcuts? We find the answer is yes – they can recall and compose facts not seen together in training or guessing the answer, but success greatly depends on the type of the bridge entity (80%+ for

Frontier models can do this stuff, but also not! Opinions differ on how much we even want this (CC Geoffrey Irving), but understanding the patterns will be critical regardless. Been a pleasure to work with Latent Reasoning Dream Team Sohee Yang Mor Geva Nora Kassner!

It's paper review day (every day) - since I discovered that DeepMind already knows everything let's look at their latest Paper arxiv.org/pdf/2411.16679

Sohee (Sohee Yang) in the house! 🚀🚀🚀🚀

I am hiring for RS/RE positions! If you are interested in language-flavored multimodal learning, evaluation, or post-training apply here 🦎 boards.greenhouse.io/deepmind/jobs/… I will also be #NeurIPS2024 so come say hi! (Please email me to find time to chat)

The Gemini 2.0 era begins with 2.0 Flash Experimental release ⚡️ 📈2.0 Flash beats 1.5 Pro across factuality, reasoning, coding, math. 📳 More modalities - image and audio out (in EAP) 🔧 Native tool use for Google Search, code execution and 3P functions 🆕 a new multimodal,

Want to build on the new Google Multimodal Live API with Gemini 2.0? My teammates Kyle Phillips + Tina Tarighian + Trudy Painter made open-source starter demos! 🧵 Here's a React.js boilerplate console you can start with. Code here: github.com/google-gemini/…

🚨 New Paper 🧵 How effectively do reasoning models reevaluate their thought? We find that: - Models excel at identifying unhelpful thoughts but struggle to recover from them - Smaller models can be more robust - Self-reevaluation ability is far from true meta-cognitive awareness