·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions39m◆MARIC: Multi-Agent Reasoning for Image Classification39m◆The Impossibility of Eliciting Latent Knowledge39m◆A Five-Plane Reference Architecture for Runtime Governance of Production AI Agents39m◆PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents39m◆Nonslop: A Gamified Experiment in Human-AI Collaborative Writing39m◆Geometric Metrics and LLMs: What They Measure and When They Work39m◆From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data39m◆From Consumption to Reflection: Designing Human-AI Relations for Stable Reasoning39m◆PoQ-Judge: A Multi-Architecture Evaluation Framework for Cost-Aware Proof-of-Quality in Decentralized LLM Inference39m◆MA-DLE: Speech-based Automatic Depression Level Estimation via Memory Augmentation39m◆The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content39m◆Noise-Guided Transport for Imitation Learning39m◆NightFeats @ MMU-RAGent NeurIPS 2025: A Context-Optimized Multi-Agent RAG System for the Text-to-Text Track39m◆To Intervene or Not: Guiding Inference-time Alignment with Probabilistic Model Blending39m◆Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention39m◆BioDivergence: A Benchmark and Evaluation Framework for Hidden Contextual Contradictions in Biomedical Abstracts39m◆When Researchers Say Mental Model/Theory of Mind of AI, What Are They Really Talking About?39m◆ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward39m◆T2MM: An LLM Supported Architecture For Inquiry-Based Modeling39m◆Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions39m◆MARIC: Multi-Agent Reasoning for Image Classification39m◆The Impossibility of Eliciting Latent Knowledge39m◆A Five-Plane Reference Architecture for Runtime Governance of Production AI Agents39m◆PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents39m◆Nonslop: A Gamified Experiment in Human-AI Collaborative Writing39m◆Geometric Metrics and LLMs: What They Measure and When They Work39m◆From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data39m◆From Consumption to Reflection: Designing Human-AI Relations for Stable Reasoning39m◆PoQ-Judge: A Multi-Architecture Evaluation Framework for Cost-Aware Proof-of-Quality in Decentralized LLM Inference39m◆MA-DLE: Speech-based Automatic Depression Level Estimation via Memory Augmentation39m◆The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content39m◆Noise-Guided Transport for Imitation Learning39m◆NightFeats @ MMU-RAGent NeurIPS 2025: A Context-Optimized Multi-Agent RAG System for the Text-to-Text Track39m◆To Intervene or Not: Guiding Inference-time Alignment with Probabilistic Model Blending39m◆Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention39m◆BioDivergence: A Benchmark and Evaluation Framework for Hidden Contextual Contradictions in Biomedical Abstracts39m◆When Researchers Say Mental Model/Theory of Mind of AI, What Are They Really Talking About?39m◆ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward39m◆T2MM: An LLM Supported Architecture For Inquiry-Based Modeling39m◆
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
arxivGeneralizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions39marxivMARIC: Multi-Agent Reasoning for Image Classification39marxivThe Impossibility of Eliciting Latent Knowledge39marxivA Five-Plane Reference Architecture for Runtime Governance of Production AI Agents39m
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