·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Claude Duet app is Anthropic’s bet on agents1h◆Nirva raises $33M for a pendant that only listens to you1h◆DeepSeek reportedly raises $15B days after US restrictions1h◆1Password lets AI agents use your passwords without seeing them2h◆AI agents are ready to shop. Some retailers are wary.2h◆Claude did not invent scorpion antivenom2h◆Eiliko maker says it’s hiring an ‘independent security firm’ after Verge report on its insecure robots4h◆Making the case for context-aware AI5h◆AI’s hidden storage bill: What inference leaves behind6h◆Ensemble forecasting with IBM Granite time-series models7h◆What FDE means at OpenAI9h◆Retrieval Augmented Generation Compositionality11h◆Evolving with Open Worlds: Towards Recursive Self-Improvement for Future Forecasting11h◆Towards English - Mizo Legal Machine Translation: Corpus Creation, Analysis, and Benchmarks11h◆VeriEvolve: Evaluator-First Evolution for Tool-Using Agents11h◆Beyond Model Weights: Sampling-Dependent Fairness in Diffusion Language Models11h◆Asymmetry Tunneling Beyond Adaptive Equivariance Relaxation11h◆Asymmetric Likelihood-Free Hypothesis Testing11h◆Bilateral Sharpness-Aware Minimization for Flatter Minima11h◆Backtracking Direct, Indirect and Total Effects11h◆Claude Duet app is Anthropic’s bet on agents1h◆Nirva raises $33M for a pendant that only listens to you1h◆DeepSeek reportedly raises $15B days after US restrictions1h◆1Password lets AI agents use your passwords without seeing them2h◆AI agents are ready to shop. Some retailers are wary.2h◆Claude did not invent scorpion antivenom2h◆Eiliko maker says it’s hiring an ‘independent security firm’ after Verge report on its insecure robots4h◆Making the case for context-aware AI5h◆AI’s hidden storage bill: What inference leaves behind6h◆Ensemble forecasting with IBM Granite time-series models7h◆What FDE means at OpenAI9h◆Retrieval Augmented Generation Compositionality11h◆Evolving with Open Worlds: Towards Recursive Self-Improvement for Future Forecasting11h◆Towards English - Mizo Legal Machine Translation: Corpus Creation, Analysis, and Benchmarks11h◆VeriEvolve: Evaluator-First Evolution for Tool-Using Agents11h◆Beyond Model Weights: Sampling-Dependent Fairness in Diffusion Language Models11h◆Asymmetry Tunneling Beyond Adaptive Equivariance Relaxation11h◆Asymmetric Likelihood-Free Hypothesis Testing11h◆Bilateral Sharpness-Aware Minimization for Flatter Minima11h◆Backtracking Direct, Indirect and Total Effects11h◆
News/Exploring the Potential of Probabilistic Transformer for Time Series Modeling: A Report on the ST-PT Framework
arxiv
PublishedApril 30, 2026 at 4:00 AM
▲bullish

Exploring the Potential of Probabilistic Transformer for Time Series Modeling: A Report on the ST-PT Framework

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

arXiv:2604.26762v1 Announce Type: cross Abstract: The Probabilistic Transformer (PT) establishes that the Transformer's self-attention plus its feed-forward block is mathematically equivalent to Mean-Field Variational Inference (MFVI) on a Conditional Random Field (CRF). Under this equivalence the T

Stay posted· Newsletter

Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.

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

Your email is used only to send The Bubble Brief. Privacy policy

Discussion
Mentioned models
02
  • 01
    Probabilistic Transformer
  • 02
    Spatial-Temporal Probabilistic Transformer
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#time-series#probabilistic-models#transformers#machine-learning

No replies yet. Be first.

Mentioned models
02
  • 01
    Probabilistic Transformer
  • 02
    Spatial-Temporal Probabilistic Transformer
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#time-series#probabilistic-models#transformers#machine-learning

Related coverage

More from ARXIV
arxivRetrieval Augmented Generation Compositionality11harxivEvolving with Open Worlds: Towards Recursive Self-Improvement for Future Forecasting11harxivTowards English - Mizo Legal Machine Translation: Corpus Creation, Analysis, and Benchmarks11harxivVeriEvolve: Evaluator-First Evolution for Tool-Using Agents11h
The Bubble Brief
MON · WED · FRI

Read time-series insights every Monday, Wednesday and Friday — top movers, new models, story of the week.

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

Your email is used only to send The Bubble Brief. Privacy policy

Originally published on arxiv ↗
PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews