4 papers · 1 filter
DRIVE: Dual-Robustness via Information Variability and Entropic Consistency in Source-Free Unsupervised Domain Adaptation
Ruiqiang Xiao, Songning Lai, Yijun Yang +3
Adapting machine learning models to new domains without labeled data, especially when source data is inaccessible, is a critical challenge in applications like medical imaging, aut…
Beyond Task Vectors: Selective Task Arithmetic Based on Importance Metrics
Tian Bowen, Lai Songning, Wu Jiemin +3
Pretrained models have revolutionized deep learning by enabling significant performance improvements across a wide range of tasks, leveraging large-scale, pre-learned knowledge rep…
Maintaining Informative Coherence: Migrating Hallucinations in Large Language Models via Absorbing Markov Chains
Jiemin Wu, Songning Lai, Ruiqiang Xiao +3
Large Language Models (LLMs) are powerful tools for text generation, translation, and summarization, but they often suffer from hallucinations-instances where they fail to maintain…
DRIVE: Dependable Robust Interpretable Visionary Ensemble Framework in Autonomous Driving
Songning Lai, Tianlang Xue, Hongru Xiao +7
Recent advancements in autonomous driving have seen a paradigm shift towards end-to-end learning paradigms, which map sensory inputs directly to driving actions, thereby enhancing…