·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Adversarial Trust Poisoning in Vehicular Collaborative Perception6h◆VibeJam: A User Study Platform for Web Development with Agents6h◆How Order-Sensitive Are LLMs? OrderProbe for Deterministic Structural Reconstruction6h◆CoReflect: A Reflective Co-Evolution Framework for Improving Conversational Evaluation6h◆EMemBench: Interactive Benchmarking of Episodic Memory for VLM Agents6h◆Propensity Straight-Through Gradients for Discrete Stochastic Systems6h◆GFlowNets and variational inference6h◆PRACTICE: From Experience to Expertise in Self-Evolving Embodied Agents6h◆Compact and Infinite-Order Error Analysis for Null-Space SVD Estimation6h◆Learning to Look Again: Loss-Gap Supervision for Free-form Crop Routing in Vision-Language Models6h◆Controlling Refusal Behavior of LLMs via Stiefel-Constrained Rotation Steering6h◆When Can We Work in Embedding Space? What Text Embeddings Preserve6h◆Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting6h◆Conservative Hybrid Graph Networks for Process Systems with Learned Routing6h◆Can We Change the Stroke Size for Easier Diffusion?6h◆Prefix-Adaptive Block Diffusion for Efficient Document Recognition6h◆MultiHashFormer: Hash-based Generative Language Models6h◆Learning to Trace Seiberg Dualities6h◆Vectors from Larger Language Models Predict Human Reading Time and fMRI Data More Poorly when Dimensionality Expansion is Controlled6h◆DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulation6h◆Adversarial Trust Poisoning in Vehicular Collaborative Perception6h◆VibeJam: A User Study Platform for Web Development with Agents6h◆How Order-Sensitive Are LLMs? OrderProbe for Deterministic Structural Reconstruction6h◆CoReflect: A Reflective Co-Evolution Framework for Improving Conversational Evaluation6h◆EMemBench: Interactive Benchmarking of Episodic Memory for VLM Agents6h◆Propensity Straight-Through Gradients for Discrete Stochastic Systems6h◆GFlowNets and variational inference6h◆PRACTICE: From Experience to Expertise in Self-Evolving Embodied Agents6h◆Compact and Infinite-Order Error Analysis for Null-Space SVD Estimation6h◆Learning to Look Again: Loss-Gap Supervision for Free-form Crop Routing in Vision-Language Models6h◆Controlling Refusal Behavior of LLMs via Stiefel-Constrained Rotation Steering6h◆When Can We Work in Embedding Space? What Text Embeddings Preserve6h◆Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting6h◆Conservative Hybrid Graph Networks for Process Systems with Learned Routing6h◆Can We Change the Stroke Size for Easier Diffusion?6h◆Prefix-Adaptive Block Diffusion for Efficient Document Recognition6h◆MultiHashFormer: Hash-based Generative Language Models6h◆Learning to Trace Seiberg Dualities6h◆Vectors from Larger Language Models Predict Human Reading Time and fMRI Data More Poorly when Dimensionality Expansion is Controlled6h◆DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulation6h◆
News/Benchmarking Linguistic Adaptation in Comparable-Sized LLMs: A Study of Llama-3.1-8B, Mistral-7B-v0.1, and Qwen3-8B on Romanized Nepali
arxiv
PublishedApril 17, 2026 at 4:00 AM
—neutral

Benchmarking Linguistic Adaptation in Comparable-Sized LLMs: A Study of Llama-3.1-8B, Mistral-7B-v0.1, and Qwen3-8B on Romanized Nepali

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

arXiv:2604.14171v1 Announce Type: new Abstract: Romanized Nepali, the Nepali language written in the Latin alphabet, is the dominant medium for informal digital communication in Nepal, yet it remains critically underresourced in the landscape of Large Language Models (LLMs). This study presents a sy

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
arxivAdversarial Trust Poisoning in Vehicular Collaborative Perception6harxivVibeJam: A User Study Platform for Web Development with Agents6harxivHow Order-Sensitive Are LLMs? OrderProbe for Deterministic Structural Reconstruction6harxivCoReflect: A Reflective Co-Evolution Framework for Improving Conversational Evaluation6h
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