Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Sayeed, Khondker Salman"'
Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs
Autor:
Mahfuz, Tamzeed, Dey, Satak Kumar, Naswan, Ruwad, Adil, Hasnaen, Sayeed, Khondker Salman, Shahgir, Haz Sameen
Each new generation of English-oriented Large Language Models (LLMs) exhibits enhanced cross-lingual transfer capabilities and significantly outperforms older LLMs on low-resource languages. This prompts the question: Is there a need for LLMs dedicat
Externí odkaz:
http://arxiv.org/abs/2407.00416
Autor:
Shahgir, Haz Sameen, Sayeed, Khondker Salman, Bhattacharjee, Abhik, Ahmad, Wasi Uddin, Dong, Yue, Shahriyar, Rifat
The advent of Vision Language Models (VLM) has allowed researchers to investigate the visual understanding of a neural network using natural language. Beyond object classification and detection, VLMs are capable of visual comprehension and common-sen
Externí odkaz:
http://arxiv.org/abs/2403.15952
Autor:
Shahgir, Haz Sameen, Sayeed, Khondker Salman, Tahmid, Md Toki, Zaman, Tanjeem Azwad, Alam, Md. Zarif Ul
Recent advances in Deep Learning and Computer Vision have been successfully leveraged to serve marginalized communities in various contexts. One such area is Sign Language - a primary means of communication for the deaf community. However, so far, th
Externí odkaz:
http://arxiv.org/abs/2401.12210
Autor:
Shahgir, H. A. Z. Sameen, Sayeed, Khondker Salman, Zaman, Tanjeem Azwad, Haider, Md. Asif, Jony, Sheikh Saifur Rahman, Rahman, M. Sohel
This report outlines our approach in the IEEE SPS VIP Cup 2023: Ophthalmic Biomarker Detection competition. Our primary objective in this competition was to identify biomarkers from Optical Coherence Tomography (OCT) images obtained from a diverse ra
Externí odkaz:
http://arxiv.org/abs/2310.14005
This paper presents a method for detecting grammatical errors in Bangla using a Text-to-Text Transfer Transformer (T5) Language Model, using the small variant of BanglaT5, fine-tuned on a corpus of 9385 sentences where errors were bracketed by the de
Externí odkaz:
http://arxiv.org/abs/2303.10612
Speech is inherently continuous, where discrete words, phonemes and other units are not clearly segmented, and so speech recognition has been an active research problem for decades. In this work we have fine-tuned wav2vec 2.0 to recognize and transcr
Externí odkaz:
http://arxiv.org/abs/2209.06581