TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking Paper • 2502.11187 • Published Feb 16, 2025 • 1
User Profile with Large Language Models: Construction, Updating, and Benchmarking Paper • 2502.10660 • Published Feb 15, 2025
SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks Paper • 2510.08513 • Published Oct 9, 2025
LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning Paper • 2604.02338 • Published Feb 1