IEEE

Optimized Identification of Sentence-Level Multiclass Events on Urdu-Language-Text Using Machine Learning Techniques

Abstract: In today’s digital world, social media platforms generate a plethora of unstructured information. However, for low-resource languages like Urdu, there is a scarcity of well-structured data ...
IEEE

Derivative-Free Optimization for Low-Rank Adaptation in Large Language Models

Abstract: Parameter-efficient tuning methods such as LoRA could achieve comparable performance to model tuning by tuning a small portion of the parameters. However, substantial computational resources ...
Microsoft

AdaptCache: KV Cache Native Storage Hierarchy for Low-Delay and High-Quality Language Model Serving

Large language model (LLM) applications often reuse previously processed context, such as chat history and documents, which in troduces significant redundant computation. Existing LLM serving systems ...
Microsoft

Crowdsourcing Speech Data for Low-Resource Languages from Low-Income Workers

Voice-based technologies are essential to cater to the hundreds of millions of new smartphone users. However, most of the languages spoken by these new users have little to no labelled speech data.
GitHub

STELLAR: Scene Text Editor for Low-resource LAnguage and Real-world data

This repository is the official implementation of the oral paper accepted to the AIBSD workshop at AAAI 2026: Official Workshop Page The synthetic data used for Stage 1 training can be generated in ...