PulseAugur
EN
LIVE 06:48:31

New Arkios language model trained on English-Nepali text

By PulseAugur Editorial · [1 sources] ·

Researchers have introduced Arkios, a 1.04 billion parameter language model trained on 150 billion tokens of English and Nepali text. The model utilizes a custom training stack and a Devanagari-aware tokenizer. Evaluations show Arkios outperforms comparable open models on ARC-Easy and ARC-Challenge benchmarks, though this may be due to data overlap with the benchmarks rather than general capability. The study also highlights challenges in evaluating low-resource language models, as standard multiple-choice prompts can yield chance-level results for Nepali comprehension. AI

IMPACT Introduces a new bilingual model and highlights evaluation challenges for low-resource languages.

RANK_REASON The cluster describes a new research paper detailing the creation and evaluation of a novel language model. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New Arkios language model trained on English-Nepali text

How we ranked this

Signal score
27 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster describes a new research paper detailing the creation and evaluation of a novel language model. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Sajal Regmi, Siddhartha Pudasaini, Chetan Phakami Pun ·

    Arkios: An Open Bilingual English-Nepali Language Model Trained From Scratch, with a Devanagari-Aware Tokenizer

    arXiv:2608.30092v1 Announce Type: cross Abstract: We present Arkios, a 1.04B-parameter dense transformer pretrained from scratch on 150B tokens of bilingual English-Nepali text, using a custom single-file C/CUDA training stack and a Devanagari-aware byte-level BPE tokenizer built…

RELATED ENTITIES

RELATED TOPICS