11 papers
Adapting Feature Attenuation to NLP
Tianshuo Yang, Ryan Rabinowitz, Terrance E. Boult +1
Transformer classifiers such as BERT deliver impressive closed-set accuracy, yet they remain brittle when confronted with inputs from unseen categories--a common scenario for deplo…
Solving Math Word Problems Using Estimation Verification and Equation Generation
Mitchell Piehl, Dillon Wilson, Ananya Kalita +1
Large Language Models (LLMs) excel at various tasks, including problem-solving and question-answering. However, LLMs often find Math Word Problems (MWPs) challenging because solvin…
Linear Relational Decoding of Morphology in Language Models
Eric Xia, Jugal Kalita
A two-part affine approximation has been found to be a good approximation for transformer computations over certain subject object relations. Adapting the Bigger Analogy Test Set,…
A Novel Active Learning Approach to Label One Million Unknown Malware Variants
Ahmed Bensaoud, Jugal Kalita
Active learning for classification seeks to reduce the cost of labeling samples by finding unlabeled examples about which the current model is least certain and sending them to an…
SGNetPose+: Stepwise Goal-Driven Networks with Pose Information for Trajectory Prediction in Autonomous Driving
Akshat Ghiya, Ali K. AlShami, Jugal Kalita
Predicting pedestrian trajectories is essential for autonomous driving systems, as it significantly enhances safety and supports informed decision-making. Accurate predictions enab…
Optimized detection of cyber-attacks on IoT networks via hybrid deep learning models
Ahmed Bensaoud, Jugal Kalita
The rapid expansion of Internet of Things (IoT) devices has increased the risk of cyber-attacks, making effective detection essential for securing IoT networks. This work introduce…