·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
What Transfers from Training-Only Priors? Separating Knowledge, Ordinal Targets, and Optimization56m◆SpectrumQuant: Spectrum Alignment for LLM Quantization56m◆A Mixture-Gated Theory of Anisotropic Representation Dynamics in Transformers56m◆Privacy Accounting for Empirical Denoisers56m◆Foundations of the Scaling Law56m◆Lean Finder V2: Semantic Search for Mathlib That Disambiguates User Queries56m◆The Value of System 1 Models in Medicine56m◆Harmful Responses Are Jailbreak Templates: Transferring Autoregressive Jailbreaks to Diffusion Language Models56m◆Stochastic Inverse Problem: stability, regularization and Wasserstein gradient flow56m◆Quantum-aware Transformer model for state classification56m◆Deep Learning Warm Starts for Trajectory Optimization on the International Space Station56m◆BrainRotViT: Transformer-ResNet Hybrid for Explainable Modeling of Brain Aging from 3D sMRI56m◆MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data56m◆Isotropic Activation Functions Enable Deindividuated Neurons and Adaptive Topologies56m◆Half-Truths Break Similarity-Based Retrieval56m◆How do standard time series forecasting benchmarks translate to finance? A broad study of risk adjusted performance56m◆Temporal Fair Division in Multi-Agent Systems: From Precise Alternation Metrics to Scalable Coordination Proxies56m◆Causal Representation Learning for Generalisable Recommendation56m◆Instance-dependent Stochastic Lipschitz bandit56m◆Driving Video Retrieval for Complex Queries with Structured Grounding56m◆What Transfers from Training-Only Priors? Separating Knowledge, Ordinal Targets, and Optimization56m◆SpectrumQuant: Spectrum Alignment for LLM Quantization56m◆A Mixture-Gated Theory of Anisotropic Representation Dynamics in Transformers56m◆Privacy Accounting for Empirical Denoisers56m◆Foundations of the Scaling Law56m◆Lean Finder V2: Semantic Search for Mathlib That Disambiguates User Queries56m◆The Value of System 1 Models in Medicine56m◆Harmful Responses Are Jailbreak Templates: Transferring Autoregressive Jailbreaks to Diffusion Language Models56m◆Stochastic Inverse Problem: stability, regularization and Wasserstein gradient flow56m◆Quantum-aware Transformer model for state classification56m◆Deep Learning Warm Starts for Trajectory Optimization on the International Space Station56m◆BrainRotViT: Transformer-ResNet Hybrid for Explainable Modeling of Brain Aging from 3D sMRI56m◆MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data56m◆Isotropic Activation Functions Enable Deindividuated Neurons and Adaptive Topologies56m◆Half-Truths Break Similarity-Based Retrieval56m◆How do standard time series forecasting benchmarks translate to finance? A broad study of risk adjusted performance56m◆Temporal Fair Division in Multi-Agent Systems: From Precise Alternation Metrics to Scalable Coordination Proxies56m◆Causal Representation Learning for Generalisable Recommendation56m◆Instance-dependent Stochastic Lipschitz bandit56m◆Driving Video Retrieval for Complex Queries with Structured Grounding56m◆
News/Riazi-8B: An Urdu Large Language Model for Mathematical Reasoning
arxiv
PublishedJune 25, 2026 at 4:00 AM
▲bullish

Riazi-8B: An Urdu Large Language Model for Mathematical Reasoning

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

arXiv:2606.25568v1 Announce Type: new Abstract: Recent LLMs demonstrate strong mathematical reasoning capabilities, but existing gains rely heavily on English-centric training resources and benchmarks. As a result, reasoning performance degrades substantially in low-resource languages such as Urdu,

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
01
  • 01
    Riazi-8B
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#low-resource-languages#mathematical-reasoning#language-adaptation#fine-tuning

No replies yet. Be first.

Mentioned models
01
  • 01
    Riazi-8B
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#low-resource-languages#mathematical-reasoning#language-adaptation#fine-tuning

Related coverage

More from ARXIV
arxivWhat Transfers from Training-Only Priors? Separating Knowledge, Ordinal Targets, and Optimization56marxivSpectrumQuant: Spectrum Alignment for LLM Quantization56marxivA Mixture-Gated Theory of Anisotropic Representation Dynamics in Transformers56marxivPrivacy Accounting for Empirical Denoisers56m
The Bubble Brief
MON · WED · FRI

Read low-resource-languages 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