6 papers
Online Domain-aware LLM Decoding for Continual Domain Evolution
Mohammad Abu-Shaira, Weishi Shi
LLMs are typically fine-tuned offline on domain-specific data, assuming a static domain. In practice, domain knowledge evolves continuously through new regulations, products, servi…
OLC-WA: Drift Aware Tuning-Free Online Classification with Weighted Average
Mohammad Abu Shaira, Yunhe Feng, Heng Fan +1
Real-world data sets often exhibit temporal dynamics characterized by evolving data distributions. Disregarding this phenomenon, commonly referred to as concept drift, can signific…
OLR-WAA: Adaptive and Drift-Resilient Online Regression with Dynamic Weighted Averaging
Mohammad Abu-Shaira, Weishi Shi
Real-world datasets frequently exhibit evolving data distributions, reflecting temporal variations and underlying shifts. Overlooking this phenomenon, known as concept drift, can s…
DAO-GP Drift Aware Online Non-Linear Regression Gaussian-Process
Mohammad Abu-Shaira, Ajita Rattani, Weishi Shi
Real-world datasets often exhibit temporal dynamics characterized by evolving data distributions. Disregarding this phenomenon, commonly referred to as concept drift, can significa…
Diagnosing Shortcut-Induced Rigidity in Continual Learning: The Einstellung Rigidity Index (ERI)
Kai Gu, Weishi Shi
Deep neural networks frequently exploit shortcut features, defined as incidental correlations between inputs and labels without causal meaning. Shortcut features undermine robustne…
Wearable Sensor-Based Few-Shot Continual Learning on Hand Gestures for Motor-Impaired Individuals via Latent Embedding Exploitation
Riyad Bin Rafiq, Weishi Shi, Mark V. Albert
Hand gestures can provide a natural means of human-computer interaction and enable people who cannot speak to communicate efficiently. Existing hand gesture recognition methods hea…