🔥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

GTC After Party week! Join us at noon EST Thurs for an interactive "Connect with KGMON" session where all 9 KGMONs (JFPuget 🇺🇦🇨🇦🇬🇱 Chris Deotte Dieter Gilberto Titericz Jr Bojan Tunguz Jiwei Liu Ahmet Erdem onodera Bo ) meet audience in both group and 1:1 settings. gtc21.event.nvidia.com/media/Winning%…

Meet Kaggle grandmasters and learn how to approach and succeed in different types of Kaggle competitions including tabular, image, natural language processing, and physics in this session [CWES1112] at 9 a.m. PDT. #GTC21 nvda.ws/3emOXNt

COVID-19 Recovery: Subway Edition The below graph shows how subway ridership for MTA (NYC) & BART (Bay Area) has changed during the pandemic. MTA is currently ~1/3 of pre-Covid ridership, while BART is at a mere 15%. Spikes = weekends. Source code/data: github.com/youyanggu/subw…

We need a 12 year old Kaggle GM

This year's RecSys Challenge, organized with Twitter, has come to an end! Following 386 submissions and 578 participants, we have the following Top-3: 1st place 15k USD: NVIDIA RAPIDS.ai 2nd place 10k USD: Synerise 3rd place 5k USD: LAYER6_AI Congratulations!

Really excited to host a workshop on the optimization and deployment of deep learning based recommender systems. Come join us on the 29th for this free event featuring talks by Maciej Kula, Xiaodong Wang, Jade Nie, Chris Deotte, Benedikt Schifferer, Bo Liu, Gilberto Titericz Jr and myself.

NVIDIA won the ACM RecSys Challenge marking its 3rd recommender systems competition win in 5 months! Read the blog to learn about the team's most recent performance at the ACM RecSys, Booking.com and SIGIR 2025 challenges. #RecSys

We have released our solution paper and code at github.com/NVIDIA-Merlin/…

I really wanted to host more winning sol deep dives & panels 🍵 I had the honor of interviewing Bo, Benedikt, Chris Deotte & Even Oldridge exactly about that 🙏 -🏆ACM RecSys Win sol -👨‍🔬How are RecSys underrated -💪Secret behind the team's 3x wins youtube.com/watch?v=W3aWEX…

In ACM RecSys competition, there are 20 million unique users in our embedding table. We leveraged PyTorch Sparse Embedding to speed up training by 6x while reducing memory usage by 2.4x I wrote about how we did it in this Merlin blog: link.medium.com/t8O82YJxtib

Really excited to share our latest blog post from Kaggle grandmaster Bo on how to fit larger recommender models into your GPU using sparse embeddings in PyTorch. medium.com/nvidia-merlin/…

#RANZCRASM21 AI Session 4 will include RANZCR 2021 CLiP Kaggle Challenge with international speakers including Kaggle Challenge winners Bo Liu (Bo) and Hiroshi Yoshihara (Rabotni(kuma|熊)), Maggie Demkin (Maggie Demkin) from Kaggle and A/Prof George Shih from MD.ai

#RANZCRASM21 Tune in to AI Session 4 to hear Kaggle Grandmaster Bo Liu Bo talk about his incredible first-place winning approach to the inaugural RANZCR CLiP Challenge!

#NVIDIA's @Kaggle Grandmaster team provides an insight on what it involves being part of Kaggle competition and how to become Kaggle Grandmasters: nvda.ws/3CV2OWf

Here are the winners of the general leaderboard of the RecSys Challenge! The winners decided to donate their prize to the Women in RecSys Community 😍 #RecSys2021 Thank you Walter Anelli for being the host tonight of the RecSys Challenge Awards!

Have you ever wondered what happens to Kaggle winning solutions after the competitions? Join us at #GTC and find out how Kaggle Grandmasters of NVIDIA (KGMON) team reuses their competition-winning models and techniques for real-world problems:nvda.ws/3qaxmPA #GTC22

Thanks for hosting me on Chai Time Data Science Show Sanyam. I got so excited that I brought a two-liter Chai to the show!

Now on Hugging Face: Classify docs into 26 domains with our advanced text classification model. Accelerated using intelligent batching + RAPIDS for faster inference. Trained on 1M Common Crawl samples and 500k Wikipedia articles. Download ➡️ nvda.ws/3XIlUMQ ✨

👀 Just released - 4 new classifier models for curating high-quality data with NVIDIA NeMo Curator ✨ Read blog ➡️ nvda.ws/3ZQa2I3 Categorize your data into predefined groups or classes, annotate it with metadata, and optimize your #dataprocessing pipelines. #LLM