RecSys Challenge 2025優勝！

Sharing our ICML’25 paper!. We studied how to design user-item allocation in two-sided systems (e.g., RecSys) when user and item populations change reactively to the utility they receive. “Policy Design for Two-sided Platforms with Participation Dynamics”.

🚀 Call for Papers: GenAI for E-commerce @ RecSys 2025.📍 Prague, Czech Republic | 📅 September 22, 2025.🌐 Website: Key dates: .📢 Submission Deadline: August 7, 2025. ✅ Acceptance Notification: August 25, 2025. 📝 Camera-Ready Due: September 4, 2025.

twitters got a good recsys reranker

Starting @ir_glasgow's #SIGIR2025 Day 2 talks with another illuminating recsys work of @asash with @craig_macdonald & @ntonellotto.

Congrats to @aiDotEngineer 2025 Best Speakers!. MCP: @zeeg.Tiny Teams: @alxai_.LLM Recsys: @devanshtandon_.GraphRAG: @danielchalef.Fortune 500 Day 1: @hwchase17.Architects Day 1: @denyslinkov.Infra: @dylan522p.Voice: @bnicholehopkins.Product Management: @bbalfour.Agent

RecSys Challenge優勝！！！.チェコ行き！！

Zhihu contributor 周国睿 has spent the past year exploring a big Q:.👉 Can we take recommender systems to the next level?. Based on hands-on work with OneRec, they found E2E recsys might be the future. Here are his key thoughts:.🔍How big should a rec model be? .⚙️How to scale

Just attended an insightful talk by @anindyadeeps at @lossfunk on “Are LLM-based Recommendation Systems a Model Problem or a UX Problem?”. He covered:. Evolution of RecSys: CF → Deep Learning → Transformers → Graph-based models. Cold-start issues, embeddings, retrieval

OneRec Technical Report. OneRec replaces multi-stage recsys pipelines with a single encoder-decoder model trained via next-token prediction over semantic item IDs. Core Design:.- Tokenizer: RQ-Kmeans with collaborative multimodal alignment → coarse-to-fine semantic IDs.-

Train a Simple Recommendation Engine using Azure #MachineLearning! #BigData #Analytics #DataScience #AI #MachineLearning #IoT #IIoT #Python #RStats #TensorFlow #Java #CloudComputing #Serverless #DataScientist #Linux #Programming #Coding #100DaysofCode .

The Keras team has released a new library for building recommender systems: KerasRS. Easy-to-use building blocks (layers, losses, metrics. ) to quickly assemble state-of-the-art RecSys pipelines. Compatible with JAX, PyTorch, TF, and optimized for TPUs. (Links in next tweet)

I’m at Netflix PRS. Come say hi! . Would love to talk about all things recsys, llm-based user experiences, evals, and everything it takes to put magical user-facing experiences into production!

one of the weirdest problems pytorch distributed has is that recsys is a very, very important internal user and my god is recsys fucked up.

📢 Great news, RecSysChallenge2025 participants! 📢. We heard you needed more time! We have extended the paper submission deadline for the Synerise ACM RecSys 2025 Challenge Workshop. The new deadline is July 16th. 👉 Find all the submission details here:.

I couldn’t be prouder — once again, the @Synerise 🇵🇱 team has raised the bar for what’s possible in global AI. 🚀. The Synerise ACM #RecSys Challenge 2025 has officially concluded — and it wasn’t just a competition. It was a statement. A bold vision. A global stage where the

I ranked #10 ⁦@icmlconf⁩ 👀 not that I’m proud of it 🤣 - but if you’ll be there let me know! #ICML2025. Would love to chat about GenAgents, Synthetic Data and RecSys applications

本日の勉強会では、ELYZAさんのPromptOpsの話、Uberの検索基盤の変遷、Claude CodeとBQを利用したデー��分析の話、LINEヤフーさんのクロスモーダルな音楽推薦の話、今年のRecSys Challengeのソリューションについて紹介されました.#Wantedly機械学習輪講.

An Introduction to #RecSys Engine! #BigData #Analytics #DataScience #AI #MachineLearning #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #GoLang #CloudComputing #Serverless #DataScientist #Linux #Programming #Coding #100DaysofCode