activity
20242026
most citedPEFT A2Z: Parameter-Efficient Fine-Tuning Survey for Large Language and Vision Models

1 citations · 1 across the 3 of their papers we have counts for

collaborators

7 papers

cs.LG2026

Monkey Jump : MoE-Style PEFT for Efficient Multi-Task Learning

Nusrat Jahan Prottasha, Md Kowsher, Chun-Nam Yu +2

Mixture-of-experts variants of parameter-efficient fine-tuning enable per-token specialization, but they introduce additional trainable routers and expert parameters, increasing me…

cs.CL2025

FlowNIB: An Information Bottleneck Analysis of Bidirectional vs. Unidirectional Language Models

Md Kowsher, Nusrat Jahan Prottasha, Shiyun Xu +4

Bidirectional language models have better context understanding and perform better than unidirectional models on natural language understanding tasks, yet the theoretical reasons b…

cs.CL20251 cited

PEFT A2Z: Parameter-Efficient Fine-Tuning Survey for Large Language and Vision Models

Nusrat Jahan Prottasha, Upama Roy Chowdhury, Shetu Mohanto +7

Large models such as Large Language Models (LLMs) and Vision Language Models (VLMs) have transformed artificial intelligence, powering applications in natural language processing,…

cs.CL2025

User Profile with Large Language Models: Construction, Updating, and Benchmarking

Nusrat Jahan Prottasha, Md Kowsher, Hafijur Raman +4

User profile modeling plays a key role in personalized systems, as it requires building accurate profiles and updating them with new information. In this paper, we present two high…

cs.CL2025

BnTTS: Few-Shot Speaker Adaptation in Low-Resource Setting

Mohammad Jahid Ibna Basher, Md Kowsher, Md Saiful Islam +8

This paper introduces BnTTS (Bangla Text-To-Speech), the first framework for Bangla speaker adaptation-based TTS, designed to bridge the gap in Bangla speech synthesis using minima…

cs.CL2025

Predicting Through Generation: Why Generation Is Better for Prediction

Md Kowsher, Nusrat Jahan Prottasha, Prakash Bhat +6

This paper argues that generating output tokens is more effective than using pooled representations for prediction tasks because token-level generation retains more mutual informat…