AIConfPaper
← Search

Tasnim Mohiuddin

4 accepted papers

2026

TimeSpot: Benchmarking Geo-Temporal Understanding in Vision–Language Models in Real-World Settings

Azmine Toushik Wasi, Shahriyar Zaman Ridoy, Koushik Tonmoy, Kinga Tshering, S. Hasan, Wahid Faisal +2
ICML 2026poster

Geo-temporal understanding, the ability to infer location, time, and contextual properties from visual input alone, is a core aspect of human intelligence and underpins applications such as disaster management, traffic planning, embodied navigation, world modeling, and geography education. Although …

Cited by 0Source ↗Scholar ↗
2025

DM-Codec: Distilling Multimodal Representations for Speech Tokenization

Md Mubtasim Ahasan, Md Fahim, Tasnim Mohiuddin, Akmmahbubur Rahman, Aman Chadha, Tariq Iqbal +3
EMNLP 2025

Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional attributes of speech into discrete tokens remains challenging. This process demands acoustic, semantic, and contextual

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2022

Data Selection Curriculum for Neural Machine Translation

Tasnim Mohiuddin, Philipp Koehn, Vishrav Chaudhary, James Cross, Shruti Bhosale, Shafiq Joty
EMNLP 2022finding

Neural Machine Translation (NMT) models are typically trained on heterogeneous data that are concatenated and randomly shuffled. However, not all of the training data are equally useful to the model. Curriculum training aims to present the data to the NMT models in a meaningful order. In this work,…

Cited by 20Source ↗PDF ↗code ↗Scholar ↗
2021

UXLA: A Robust Unsupervised Data Augmentation Framework for Zero-Resource Cross-Lingual NLP

M Saiful Bari, Tasnim Mohiuddin, Shafiq Joty
ACL 2021long

Transfer learning has yielded state-of-the-art (SoTA) results in many supervised NLP tasks. However, annotated data for every target task in every target language is rare, especially for low-resource languages. We propose UXLA, a novel unsupervised data augmentation framework for zero-resource trans…

Cited by 25Source ↗PDF ↗Scholar ↗