🔥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

Can deep learning finally compete with boosted trees on tabular data? 🌲 In our NeurIPS 2024 paper, we introduce RealMLP, a NN with improvements in all areas and meta-learned default parameters. Some insights about RealMLP and other models on large benchmarks (>200 datasets): 🧵

I *finally* got back home, and have some time to try out TabPFN (thanks everyone who worked so hard on ruining my vacation BTW :P ) 1. First impressions of the library are actually pretty good. I could not get it working on my Mac, but managed to install it on my Ubuntu machine.

The first independent evaluation of our RealMLP is here! On a recent 300-dataset benchmark with many baselines, RealMLP takes a shared first place overall. 🔥 Importantly, RealMLP is also relatively CPU-friendly, unlike other SOTA DL models (including TabPFNv2 and TabM). 🧵 1/

DeepSeek-R1 is a cheap, non-US, open-source foundation model challenging US market leaders … and so is TabPFN v2! Happy to report that TabPFN-TS just took #1 in the popular time series benchmark GIFT-Eval, outperforming Amazon's leading time series foundation model Chronos!🧵1/5

I‘m excited to announce that we raised €9m in a pre-seed round for Prior Labs, the world’s first company focussed on building tabular foundation models! The round was led by Balderton Capital, with participation from XTX Markets, Hector Foundation, Atlantic Labs, and Galion.exe. We’re

We’re actively hiring ML Engineers & Applied AI Scientists at Prior Labs to build the future of foundation models for structured data! We’re pushing the boundaries of AI with foundation models that understand structured data—an untapped AI frontier powering science, finance,

Want strong SSL, but not the complexity of DINOv2? CAPI: Cluster and Predict Latents Patches for Improved Masked Image Modeling.

Tabular data often has messy text features —preprocessing them is tedious and time-consuming. Our new #TabPFN 2+ removes that hassle: just feed in your data, and get fast, accurate predictions. No feature engineering required. We’d love your feedback! API + example notebook👇1/5

Practitioners are often sceptical of academic tabular benchmarks, so I am elated to see that our RealMLP model outperformed boosted trees in two 2nd place Kaggle solutions, for a $10,000 forecasting challenge and a research competition on survival analysis.

So proud of this one: today we're releasing Command A, our new 111B flagship model tailored for business use cases. Gpt4o/Deepseek-level in evals, better than Sonnet on LMsys, has 256k context length. Also, weights are available now on hf! huggingface.co/CohereForAI/c4…

Today we release our vision for tackling AI's critical blind spot: structured data. We believe the future requires AI that truly understands the language of spreadsheets & databases. We’re building this future with Multimodal Tabular Foundation Models (TFMs). Thread below 🧵

⚡ Something new is coming. We’ve been quietly building a model that reasons — not just over data, but also over real-world context. Soft-launching soon in our Discord. Early access 👉 discord.com/invite/VJRuU3b… #AI #TabPFN #Reasoning #Multimodal #ML #PriorLabs