20 citations · 25 across the 16 of their papers we have counts for
16 papers
CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgery
Mahir Shahriar Tamim, Sharjil Khan, Md. Samiul Alim +3
End-to-end training of multimodal neural networks often exhibits unstable neural dynamics characterized by three coupled failure modes that degrade learning: (i) modality imbalance…
Beyond Real Weights: Hypercomplex Representations for Stable Quantization
Jawad Ibn Ahad, Maisha Rahman, Amrijit Biswas +5
Multimodal language models (MLLMs) require large parameter capacity to align high-dimensional visual features with linguistic representations, making them computationally heavy and…
LAET: A Layer-wise Adaptive Ensemble Tuning Framework for Pretrained Language Models
Jawad Ibn Ahad, Muhammad Rafsan Kabir, Robin Krambroeckers +3
Natural Language Processing (NLP) has transformed the financial industry, enabling advancements in areas such as textual analysis, risk management, and forecasting. Large language…
Teacher-Guided One-Shot Pruning via Context-Aware Knowledge Distillation
Md. Samiul Alim, Sharjil Khan, Amrijit Biswas +3
Unstructured pruning remains a powerful strategy for compressing deep neural networks, yet it often demands iterative train-prune-retrain cycles, resulting in significant computati…
Label Semantics for Robust Hyperspectral Image Classification
Rafin Hassan, Zarin Tasnim Roshni, Rafiqul Bari +4
Hyperspectral imaging (HSI) classification is a critical tool with widespread applications across diverse fields such as agriculture, environmental monitoring, medicine, and materi…
Z-Pruner: Post-Training Pruning of Large Language Models for Efficiency without Retraining
Samiul Basir Bhuiyan, Md. Sazzad Hossain Adib, Mohammed Aman Bhuiyan +4
Large language models (LLMs) have rapidly advanced in recent years, achieving remarkable performance across a wide range of natural language processing tasks. However, this progres…
Temporal Window Smoothing of Exogenous Variables for Improved Time Series Prediction
Mustafa Kamal, Niyaz Bin Hashem, Robin Krambroeckers +2
Although most transformer-based time series forecasting models primarily depend on endogenous inputs, recent state-of-the-art approaches have significantly improved performance by…
VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval
Dhiman Paul, Md Rizwan Parvez, Nabeel Mohammed +1
Prevailing joint prediction transformers for Video Highlight Detection and Moment Retrieval (HD/MR) exhibit deficiencies in handling cross-task dynamics, achieving robust video-tex…
3D Point Cloud Network Pruning: When Some Weights Do not Matter
Amrijit Biswas, Md. Ismail Hossain, M M Lutfe Elahi +4
A point cloud is a crucial geometric data structure utilized in numerous applications. The adoption of deep neural networks referred to as Point Cloud Neural Networks (PC- NNs), fo…
Beyond Labels: Aligning Large Language Models with Human-like Reasoning
Muhammad Rafsan Kabir, Rafeed Mohammad Sultan, Ihsanul Haque Asif +5
Aligning large language models (LLMs) with a human reasoning approach ensures that LLMs produce morally correct and human-like decisions. Ethical concerns are raised because curren…
ChatGPT-guided Semantics for Zero-shot Learning
Fahimul Hoque Shubho, Townim Faisal Chowdhury, Ali Cheraghian +3
Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen classes…
LumiNet: Perception-Driven Knowledge Distillation via Statistical Logit Calibration
Md. Ismail Hossain, M M Lutfe Elahi, Sameera Ramasinghe +4
In the knowledge distillation literature, feature-based methods have dominated due to their ability to effectively tap into extensive teacher models. In contrast, logit-based appro…
SentiGOLD: A Large Bangla Gold Standard Multi-Domain Sentiment Analysis Dataset and its Evaluation
Md. Ekramul Islam, Labib Chowdhury, Faisal Ahamed Khan +5
This study introduces SentiGOLD, a Bangla multi-domain sentiment analysis dataset. Comprising 70,000 samples, it was created from diverse sources and annotated by a gender-balanced…
BenCoref: A Multi-Domain Dataset of Nominal Phrases and Pronominal Reference Annotations
Shadman Rohan, Mojammel Hossain, Mohammad Mamun Or Rashid +1
Coreference Resolution is a well studied problem in NLP. While widely studied for English and other resource-rich languages, research on coreference resolution in Bengali largely r…
COLT: Cyclic Overlapping Lottery Tickets for Faster Pruning of Convolutional Neural Networks
Md. Ismail Hossain, Mohammed Rakib, M. M. Lutfe Elahi +2
Pruning refers to the elimination of trivial weights from neural networks. The sub-networks within an overparameterized model produced after pruning are often called Lottery ticket…
Less is More: Facial Landmarks can Recognize a Spontaneous Smile
Md. Tahrim Faroque, Yan Yang, Md Zakir Hossain +3
Smile veracity classification is a task of interpreting social interactions. Broadly, it distinguishes between spontaneous and posed smiles. Previous approaches used hand-engineere…