• bitcoinBitcoin(BTC)$60,146.002.14%
  • ethereumEthereum(ETH)$1,681.703.71%
  • tetherTether(USDT)$1.000.03%
  • binancecoinBNB(BNB)$547.401.49%
  • usd-coinUSDC(USDC)$1.000.01%
  • rippleXRP(XRP)$0.932.33%
  • solanaSolana(SOL)$70.271.76%
  • tronTRON(TRX)$0.3049581.10%
  • Figure HelocFigure Heloc(FIGR_HELOC)$1.052.41%
  • HyperliquidHyperliquid(HYPE)$61.230.45%
  • zcashZcash(ZEC)$780.842.31%
  • moneroMonero(XMR)$490.956.79%
  • dogecoinDogecoin(DOGE)$0.0551921.37%
  • leo-tokenLEO Token(LEO)$9.13-0.22%
  • whitebitWhiteBIT Coin(WBT)$57.712.32%
  • chainlinkChainlink(LINK)$8.590.18%
  • USDSUSDS(USDS)$1.000.01%
  • cardanoCardano(ADA)$0.1443370.71%
  • Ethena USDeEthena USDe(USDE)$1.00-0.02%
  • stellarStellar(XLM)$0.1290571.02%
  • daiDai(DAI)$1.000.00%
  • bitcoin-cashBitcoin Cash(BCH)$199.432.30%
  • nearNEAR Protocol(NEAR)$2.901.24%
  • litecoinLitecoin(LTC)$39.76-2.18%
  • CantonCanton(CC)$0.0761841.67%
  • avalanche-2Avalanche(AVAX)$6.570.53%
  • Ripple USDRipple USD(RLUSD)$1.000.01%
  • tether-goldTether Gold(XAUT)$3,544.910.43%
  • uniswapUniswap(UNI)$4.724.97%
  • USD1USD1(USD1)$1.000.05%
  • the-open-networkGram (prev. Toncoin)(GRAM)$0.95-2.94%
  • suiSui(SUI)$0.65-0.73%
  • RainRain(RAIN)$0.0037331.81%
  • Global DollarGlobal Dollar(USDG)$1.000.01%
  • Ondo US Dollar YieldOndo US Dollar Yield(USDY)$1.150.08%
  • paypal-usdPayPal USD(PYUSD)$1.000.01%
  • hedera-hashgraphHedera(HBAR)$0.051414-0.57%
  • BittensorBittensor(TAO)$186.182.42%
  • crypto-com-chainCronos(CRO)$0.0412403.27%
  • shiba-inuShiba Inu(SHIB)$0.0000040.87%
  • quant-networkQuant(QNT)$143.802.67%
  • Spiko Amundi Overnight Swap Fund (EUR)Spiko Amundi Overnight Swap Fund (EUR)(EURSAFO)$1.12-0.04%
  • Circle USYCCircle USYC(USYC)$1.140.00%
  • MemeCoreMemeCore(M)$0.76-11.22%
  • Falcon USDFalcon USD(USDF)$1.000.03%
  • okbOKB(OKB)$79.530.64%
  • United StablesUnited Stables(U)$1.000.13%
  • pax-goldPAX Gold(PAXG)$3,548.190.48%
  • BlackRock USD Institutional Digital Liquidity FundBlackRock USD Institutional Digital Liquidity Fund(BUIDL)$1.000.00%
  • aaveAave(AAVE)$97.69-0.60%
TradePoint.io
  • Main
  • AI & Technology
  • Stock Charts
  • Market & News
  • Business
  • Finance Tips
  • Trade Tube
  • Blog
  • Shop
No Result
View All Result
TradePoint.io
No Result
View All Result

NVIDIA Releases Kumo Tabular: Open Tabular Foundation Models That Predict New Rows in a Single Forward Pass

October 1, 2026
in AI & Technology
Reading Time: 15 mins read
A A
NVIDIA Releases Kumo Tabular: Open Tabular Foundation Models That Predict New Rows in a Single Forward Pass
ShareShareShareShareShare

NVIDIA has released Kumo Tabular, a new family of tabular foundation models (TFMs) for classification and regression. If you have followed TabPFN or TabICL, the setup will look familiar. The model takes labeled rows as context and predicts new rows in one forward pass. There is no training, no hyperparameter tuning, and no feature engineering.

Kumo Tabular comes in Small, Medium, and Large versions, spanning about 28M to 215M parameters. It runs through NVIDIA’s open-source structured-data-models (SDM) library.

YOU MAY ALSO LIKE

Lean and Mathlib Communities Certify Claude-Assisted Riemann Proof – Unite.AI

Anthropic Employee Claims To Have Proven The Most Famous Math Problem Using Claude

Is it deployable? Yes. Weights ship under the OpenMDW-1.1 license, which permits commercial use. The SDM code is Apache-2.0, and it needs Python 3.11+ and PyTorch 2.7+, with examples targeting a CUDA GPU.

What the SDM Library Adds

SDM is a GPU-native library for structured-data foundation models and preprocessing. Besides Kumo Tabular, it ships TabICLv2, Google’s TabFM, and KumoRelational for multi-table data. All models share one in-context learning interface built on a TableTensor container. The library also handles preprocessing, ensembling, and many-class prediction.

How Kumo Tabular Works

Kumo Tabular is a Transformer built around the structure of a table. It uses column, row, and in-context attention, as introduced in TabICL and TabPFN. The pipeline has 3 stages:

  • Cell embedding: Numerical and categorical values pass through learned Fourier features, with separate weights per type. Missing values need no imputation.
  • Row embedding: Column attention uses induced self-attention, so cost grows linearly with rows. Row attention, with rotary positions, learns feature interactions. 4 learnable [CLS] tokens compress each row.
  • In-context learning: A final Transformer runs over row embeddings. Context rows attend to each other, while query rows attend only to context rows.

Because the context never sees the queries, its keys and values are computed once and reused. The head outputs class probabilities, or 999 quantiles for regression. That gives a point prediction plus an uncertainty estimate.

One more detail matters at scale. Softmax attention spreads thin as the number of keys grows. Kumo Tabular scales each query by a temperature that grows with the log of the key count. The coefficient is learned per attention head, so attention stays sharp on larger tables.

Credit: Source link

ShareTweetSendSharePin

Related Posts

Lean and Mathlib Communities Certify Claude-Assisted Riemann Proof – Unite.AI
AI & Technology

Lean and Mathlib Communities Certify Claude-Assisted Riemann Proof – Unite.AI

November 21, 2026
Anthropic Employee Claims To Have Proven The Most Famous Math Problem Using Claude
AI & Technology

Anthropic Employee Claims To Have Proven The Most Famous Math Problem Using Claude

November 21, 2026
Thinking Machines wows with Inkling 2 Mini looped transformer model that runs locally on laptops
AI & Technology

Thinking Machines wows with Inkling 2 Mini looped transformer model that runs locally on laptops

November 21, 2026
Why Your Ping Is Terrible (Even Though You Have Fast Internet)
AI & Technology

Why Your Ping Is Terrible (Even Though You Have Fast Internet)

November 21, 2026
Next Post
California’s New Law Bans Companies From Relying On AI To Fire Workers

California's New Law Bans Companies From Relying On AI To Fire Workers

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Search

No Result
View All Result
Market volatility: Opportunity or warning sign? Nvidia or Microsoft? Amazon or Alphabet?

Market volatility: Opportunity or warning sign? Nvidia or Microsoft? Amazon or Alphabet?

November 16, 2026
IIT Kharagpur Secures M From Google to Expand Campus AI Work – Unite.AI

IIT Kharagpur Secures $5M From Google to Expand Campus AI Work – Unite.AI

November 21, 2026
Germany Seems To Be Serious About A TikTok Europe Takeover

Germany Seems To Be Serious About A TikTok Europe Takeover

November 20, 2026

About

Learn more

Our Services

Legal

Privacy Policy

Terms of Use

Bloggers

Learn more

Article Links

Contact

Advertise

Ask us anything

©2020- TradePoint.io - All rights reserved!

Tradepoint.io, being just a publishing and technology platform, is not a registered broker-dealer or investment adviser. So we do not provide investment advice. Rather, brokerage services are provided to clients of Tradepoint.io by independent SEC-registered broker-dealers and members of FINRA/SIPC. Every form of investing carries some risk and past performance is not a guarantee of future results. “Tradepoint.io“, “Instant Investing” and “My Trading Tools” are registered trademarks of Apperbuild, LLC.

This website is operated by Apperbuild, LLC. We have no link to any brokerage firm and we do not provide investment advice. Every information and resource we provide is solely for the education of our readers. © 2020 Apperbuild, LLC. All rights reserved.

No Result
View All Result
  • Main
  • AI & Technology
  • Stock Charts
  • Market & News
  • Business
  • Finance Tips
  • Trade Tube
  • Blog
  • Shop

© 2023 - TradePoint.io - All Rights Reserved!