paper-with-me

Papers

Tiny Aya: Bridging Scale and Multilingual Depth

2026-03-12 · Alejandro R. Salamanca, Diana Abagyan, Daniel D'souza, Ammar Khairi, David Mora, Saurabh Dash, Viraat Aryabumi, Sara Rajaee, Mehrnaz Mofakhami, Ananya Sahu, Thomas Euyang, Brittawnya Prince, Madeline Smith, Hangyu Lin, Acyr Locatelli, Sara Hooker, Tom Kocmi, Aidan Gomez, Ivan Zhang, Phil Blunsom, Nick Frosst, Joelle Pineau, Beyza Ermis, Ahmet Üstün, Julia Kreutzer, Marzieh Fadaee arxiv

Tiny Aya redefines what a small multilingual language model can achieve. Trained on 70 languages and refined through region-aware posttraining, it delivers state-of-the-art in translation quality, strong multilingual understanding, and high-quality target-language generation, all with just 3.35B parameters. The release includes a pretrained foundation model, a globally balanced instruction-tuned variant, and three region-specialized models targeting languages from Africa, South Asia, Europe, Asia-Pacific, and West Asia. This report details the training strategy, data composition, and comprehensive evaluation framework behind Tiny Aya, and presents an alternative scaling path for multilingual AI: one centered on efficiency, balanced performance across languages, and practical deployment.

📄 PDF Abstract BibTeX arXiv:2603.11510

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Bridging the Scale Gap: Balanced Tiny and General Object Detection in Remote Sensing Imagery

2025-12-01 · Zhicheng Zhao, Yin Huang, Lingma Sun, Chenglong Li 외 arxiv

Tiny object detection in remote sensing imagery has attracted significant research interest in recent years. Despite recent progress, achieving balanced detection performance across diverse object scales remains a formid…

Object Detection

Multilingual TinyStories: A Synthetic Combinatorial Corpus of Indic Children's Stories for Training Small Language Models

2026-03-15 · Deepon Halder, Angira Mukherjee arxiv

The development of robust language models for low-resource languages is frequently bottlenecked by the scarcity of high-quality, coherent, and domain-appropriate training corpora. In this paper, we introduce the Multilin…

Prompt EngineeringTransfer Learning

Using Cross-Domain Detection Loss to Infer Multi-Scale Information for Improved Tiny Head Tracking

2025-05-14 · Jisu Kim, Alex Mattingly, Eung-Joo Lee, Benjamin S. Riggan

Head detection and tracking are essential for downstream tasks, but current methods often require large computational budgets, which increase latencies and ties up resources (e.g., processors, memory, and bandwidth). To …

Head DetectionMultiple Object TrackingObject Tracking

N-QGN: Navigation Map from a Monocular Camera using Quadtree Generating Networks

2022-02-24 · Daniel Braun, Olivier Morel, Pascal Vasseur, Cédric Demonceaux

Monocular depth estimation has been a popular area of research for several years, especially since self-supervised networks have shown increasingly good results in bridging the gap with supervised and stereo methods. How…

3D ReconstructionAutonomous NavigationDepth EstimationMonocular Depth Estimation

Tiny QA Benchmark++: Ultra-Lightweight, Synthetic Multilingual Dataset Generation & Smoke-Tests for Continuous LLM Evaluation

2025-05-17 · Vincent Koc

Tiny QA Benchmark++ (TQB++) presents an ultra-lightweight, multilingual smoke-test suite designed to give large-language-model (LLM) pipelines a unit-test style safety net dataset that runs in seconds with minimal cost. …

Dataset GenerationGPULarge Language ModelMMLU+2