8 papers
A Metamorphic Testing Perspective on Knowledge Distillation for Language Models of Code: Does the Student Deeply Mimic the Teacher?
Md. Abdul Awal, Mrigank Rochan, Chanchal K. Roy
Transformer-based language models of code have achieved state-of-the-art performance across a wide range of software analytics tasks, but their practical deployment remains limited…
Model Compression vs. Adversarial Robustness: An Empirical Study on Language Models for Code
Md. Abdul Awal, Mrigank Rochan, Chanchal K. Roy
Transformer-based language models for code have shown remarkable performance in various software analytics tasks, but their adoption is hindered by high computational costs, slow i…
Learnable Motion-Focused Tokenization for Effective and Efficient Video Unsupervised Domain Adaptation
Tzu Ling Liu, Ian Stavness, Mrigank Rochan
Video Unsupervised Domain Adaptation (VUDA) poses a significant challenge in action recognition, requiring the adaptation of a model from a labeled source domain to an unlabeled ta…
MoEKD: Mixture-of-Experts Knowledge Distillation for Robust and High-Performing Compressed Code Models
Md. Abdul Awal, Mrigank Rochan, Chanchal K. Roy
Large language models for code have achieved strong performance across diverse software analytics tasks, yet their real-world adoption remains limited by high computational demands…
Test-Time Adaptation for Video Highlight Detection Using Meta-Auxiliary Learning and Cross-Modality Hallucinations
Zahidul Islam, Sujoy Paul, Mrigank Rochan
Existing video highlight detection methods, although advanced, struggle to generalize well to all test videos. These methods typically employ a generic highlight detection model fo…
Investigating Adversarial Attacks in Software Analytics via Machine Learning Explainability
MD Abdul Awal, Mrigank Rochan, Chanchal K. Roy
With the recent advancements in machine learning (ML), numerous ML-based approaches have been extensively applied in software analytics tasks to streamline software development and…