Yves Raimond

We’re testing something that I’m very excited about - giving users literal control of the algorithm, using just the English language. You can write, iterate, tune and schedule your own unique playlist algorithm by writing a prompt, using any world information as well as all your own play history and data, like for example: ”Give me all the tracks that are trending in TV-shows right now, tell me which show and specific episode they are from, filter them by my taste and show only tracks that I’ve never listened to before. ” and then schedule it to update daily or weekly. It’s a lot of fun!

This is my team. I’m super excited to work on this stuff. If you are too, let’s talk: we’re hiring. newsroom.spotify.com/2025-10-16/art…

Seconded!

Google quietly released a powerful recommender systems library optimized for JAX and TPUs, based on Keras. It's called RecML. It has native support for SparseCore (latest hardware for handling large distributed embeddings)

Happy to announce that our team has just launched Gemini Personalization! This is a massive update to Gemini, which for the first time we bring your Google Searches to @GeminiApp. Just try it out, it is good to talk with an AI that truly knows us :) gemini.google/overview/perso…

I’m very excited to share our work on Gemini today! Gemini is a family of multimodal models that demonstrate really strong capabilities across the image, audio, video, and text domains. Our most-capable model, Gemini Ultra, advances the state of the art in 30 of 32 benchmarks, including 10 of 12 popular text and reasoning benchmarks, 9 of 9 image understanding benchmarks, 6 of 6 video understanding benchmarks, and 5 of 5 speech recognition and speech translation benchmarks. Gemini Ultra is the first model to achieve human-expert performance on MMLU across 57 subjects with a score above 90%. It also achieves a new state-of-the-art score of 62.4% on the new MMMU multimodal reasoning benchmark, outperforming the previous best model by more than 5 percentage points. Gemini was built by an awesome team of people from @GoogleDeepMind, @GoogleResearch, and elsewhere at @Google, and is one of the largest science and engineering efforts we’ve ever undertaken. As one of the two overall technical leads of the Gemini effort, along with my colleague @OriolVinyalsML, I am incredibly proud of the whole team, and we’re so excited to be sharing our work with you today! There’s quite a lot of different material about Gemini available, starting with: Main blog post: blog.google/technology/ai/… 60-page technical report authored by th Gemini Team: deepmind.google/gemini/gemini_… In this thread, I’ll walk you through some of the highlights.

5-6 years ago I was working on music generation at DeepMind, but let me tell you, this is... something else. Incredibly excited to be able to finally share what our team has been working on!

The full recording of our #RecSys2023 workshop can now be found online. Tell your friends! @ACMRecSys youtu.be/WRRnsZfcQ9g

We're launching Keras Core, a new library that brings the Keras API to JAX and PyTorch in addition to TensorFlow. It enables you to write cross-framework deep learning components and to benefit from the best that each framework has to offer. Read more: keras.io/keras_core/ann…

As Bard and LaMDA Research Platform lead, I am excited for people to try Bard. It's experimental and early stages, but the user feedback will be very useful and help develop this new technology.

REVEAL is over, we continue tomorrow as CONSEQUENCES!🗼🌄 Don't miss our tutorial and keynotes given by: - @usait0en recently listed in Forbes - JAPAN 30 under 30 - @LihongLi20 Senior Principal Scientist at Amazon - Guido Imbens - co-awarded the Nobel Prize in Economics in 2021

The full program and schedule for both the REVEAL and CONSEQUENCES workshop days can now be found on our website: sites.google.com/view/consequen… #RecSys2022

We will have a whopping 21 contributions presented at our #RecSys2022 workshop, just over 2 weeks away. The titles and authors are now listed on our webpage: have a look, and see you soon @ACMRecSys! sites.google.com/view/consequen…

Quick professional update: after 8 amazing years at @NetflixResearch (time flies!), I started last week at Google, where I'll be focusing on ML for user modeling & personalization -- excited about taking on a new challenge!

@usait0en Many congratulations Yuta!!

One week left until CONSEQUENCES and REVEAL @ACMRecSys workshop deadline (8/5) sites.google.com/view/consequen…

Want to learn about RecSysOps: Best Practices for Operating a Large-Scale Recommender System? See our Ehsan Saberian's presentation at NVidia's virtual Recommender Systems Summit on July 28th: events.nvidia.com/recommender-sy…

🚨 2 weeks left to submit your contributions! 🚨 Be sure to start writing in time, and we look forward to seeing all of you in person (or virtually) in Seattle at #RecSys2022!

Consider submitting your contributions to our 2-day #RecSys2022 workshop on counterfactuals, causality, sequential decision-making and reinforcement learning for recommender systems. Deadline August 5th, submissions open now: cmt3.research.microsoft.com/CONSEQUENCES20… Spread the word!

CfP for the CONSEQUENCES and REVEAL workshops on counterfactual and reinforcement-learned recommender systems here: sites.google.com/view/consequen… -- Deadline August 5th! Should be an awesome two days at #recsys2022 :)