·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Another swarm of OpenAI agents reached the open internet without the frontier lab’s knowledge59m◆Apple’s Ternus era begins as Nvidia bets on the whole AI stack1h◆Google’s Gemini Spark can now manage your Google Photos library2h◆Less than 24 hours to apply for your TechCrunch Disrupt 2026 Side Event3h◆Rogue OpenAI agents appear to have organized another attack using a German wiki3h◆Instagram’s AI detection is a mess (again)5h◆Why AI food looks like that6h◆Microsoft’s Project Zenith is a ‘distraction-free Windows experience’ for developers6h◆Sam Altman apologizes for ‘messy’ GPT-6 Astra rollout that’s locked out paying users6h◆This NAS company wants to run your local smart home7h◆Data from drones in Ukraine is fueling a new Wild West marketplace7h◆The sameness problem behind those unappetizing AI-generated menus13h◆CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning13h◆Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation13h◆X-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System13h◆A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors13h◆Influence of Extruded Filament Shape on Buildability in 3D Concrete Printing: A Geometry-Informed Deep Learning-FEM Approach13h◆Subspace Inference Enables Efficient Active Reward Learning from Preferences13h◆Identifying AI Web Scrapers Using Canary Tokens13h◆PalmClaw: A Native On-Device Agent Framework for Mobile Phones13h◆Another swarm of OpenAI agents reached the open internet without the frontier lab’s knowledge59m◆Apple’s Ternus era begins as Nvidia bets on the whole AI stack1h◆Google’s Gemini Spark can now manage your Google Photos library2h◆Less than 24 hours to apply for your TechCrunch Disrupt 2026 Side Event3h◆Rogue OpenAI agents appear to have organized another attack using a German wiki3h◆Instagram’s AI detection is a mess (again)5h◆Why AI food looks like that6h◆Microsoft’s Project Zenith is a ‘distraction-free Windows experience’ for developers6h◆Sam Altman apologizes for ‘messy’ GPT-6 Astra rollout that’s locked out paying users6h◆This NAS company wants to run your local smart home7h◆Data from drones in Ukraine is fueling a new Wild West marketplace7h◆The sameness problem behind those unappetizing AI-generated menus13h◆CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning13h◆Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation13h◆X-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System13h◆A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors13h◆Influence of Extruded Filament Shape on Buildability in 3D Concrete Printing: A Geometry-Informed Deep Learning-FEM Approach13h◆Subspace Inference Enables Efficient Active Reward Learning from Preferences13h◆Identifying AI Web Scrapers Using Canary Tokens13h◆PalmClaw: A Native On-Device Agent Framework for Mobile Phones13h◆
News/Pocket Foundation Models: Distilling TFMs into CPU-Ready Gradient-Boosted Trees
arxiv
PublishedMay 19, 2026 at 4:00 AM

Pocket Foundation Models: Distilling TFMs into CPU-Ready Gradient-Boosted Trees

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2605.18654v1 Announce Type: cross Abstract: A fraud scorer needs to answer in under 2 ms. The best tabular foundation models (TFMs) take 151-1,275 ms on GPU. We close this gap by distilling the TFM offline into an XGBoost or CatBoost student that runs natively on CPU. The central obstacle is s

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivCulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning13harxivProactive Service Agents: A Unified Decision Framework, Methods, and Evaluation13harxivX-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System13harxivA Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors13h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews