2 citations · 4 across the 14 of their papers we have counts for
14 papers
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression
Nazia Tasnim, Shrimai Prabhumoye, Bryan A. Plummer
Parameter Recombination (PR) methods aim to efficiently compose the weights of a neural network for applications like Parameter-Efficient FineTuning (PEFT) and Model Compression (M…
Seeing Isn't Orienting: A Cognitively Grounded Benchmark Reveals Systematic Orientation Failures in MLLMs Supplementary
Nazia Tasnim, Keanu Nichols, Yuting Yang +4
Humans learn object orientation progressively, from recognizing which way an object faces, to mentally rotating it, to reasoning about orientations between objects. Current vision-…
Representation-Aware Unlearning via Activation Signatures: From Suppression to Entity-Signature Erasure
Syed Naveed Mahmood, Md. Rezaur Rahman Bhuiyan, Tasfia Zaman +5
Entity-level unlearning is usually evaluated by what a model says: whether it stops naming the target, refuses a query, or shifts a Truth Ratio distribution. These output-level tes…
Are ASR foundation models generalized enough to capture features of regional dialects for low-resource languages?
Tawsif Tashwar Dipto, Azmol Hossain, Rubayet Sabbir Faruque +12
Conventional research on speech recognition modeling relies on the canonical form for most low-resource languages while automatic speech recognition (ASR) for regional dialects is…
RegSpeech12: A Regional Corpus of Bengali Spontaneous Speech Across Dialects
Md. Rezuwan Hassan, Azmol Hossain, Kanij Fatema +13
The Bengali language, spoken extensively across South Asia and among diasporic communities, exhibits considerable dialectal diversity shaped by geography, culture, and history. Pho…
From Facts to Folklore: Evaluating Large Language Models on Bengali Cultural Knowledge
Nafis Chowdhury, Moinul Haque, Anika Ahmed +4
Recent progress in NLP research has demonstrated remarkable capabilities of large language models (LLMs) across a wide range of tasks. While recent multilingual benchmarks have adv…
Seeing Isn't Orienting: A Cognitively Informed Hierarchical Benchmark for Object Orientation in MLLMs
Nazia Tasnim, Keanu Nichols, Yuting Yan +4
Humans develop object orientation understanding progressively, from recognizing which way an object faces to reasoning about orientations across multiple objects. Yet existing visi…
RECAST: Reparameterized, Compact weight Adaptation for Sequential Tasks
Nazia Tasnim, Bryan A. Plummer
Incremental learning aims to adapt to new sets of categories over time with minimal computational overhead. Prior work often addresses this task by training efficient task-specific…
Mapping Violence: Developing an Extensive Framework to Build a Bangla Sectarian Expression Dataset from Social Media Interactions
Nazia Tasnim, Sujan Sen Gupta, Md. Istiak Hossain Shihab +10
Communal violence in online forums has become extremely prevalent in South Asia, where many communities of different cultures coexist and share resources. These societies exhibit a…
Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks
Maan Qraitem, Nazia Tasnim, Piotr Teterwak +2
Typographic attacks, adding misleading text to images, can deceive vision-language models (LVLMs). The susceptibility of recent large LVLMs like GPT4-V to such attacks is understud…
OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking
Fazle Rabbi Rakib, Souhardya Saha Dip, Samiul Alam +11
We present OOD-Speech, the first out-of-distribution (OOD) benchmarking dataset for Bengali automatic speech recognition (ASR). Being one of the most spoken languages globally, Ben…
VISTA: Vision Transformer enhanced by U-Net and Image Colorfulness Frame Filtration for Automatic Retail Checkout
Md. Istiak Hossain Shihab, Nazia Tasnim, Hasib Zunair +2
Multi-class product counting and recognition identifies product items from images or videos for automated retail checkout. The task is challenging due to the real-world scenario of…
TEAM-Atreides at SemEval-2022 Task 11: On leveraging data augmentation and ensemble to recognize complex Named Entities in Bangla
Nazia Tasnim, Md. Istiak Hossain Shihab, Asif Shahriyar Sushmit +2
Many areas, such as the biological and healthcare domain, artistic works, and organization names, have nested, overlapping, discontinuous entity mentions that may even be syntactic…
Exploring the Scope and Potential of Local Newspaper-based Dengue Surveillance in Bangladesh
Nazia Tasnim, Md. Istiak Hossain Shihab, Moqsadur Rahman +2
Dengue fever has been considered to be one of the global public health problems of the twenty-first century, especially in tropical and subtropical countries of the global south. T…