2 papers
cs.DC2025
Parallax: Runtime Parallelization for Operator Fallbacks in Heterogeneous Edge Systems
Chong Tang, Hao Dai, Jagmohan Chauhan
The growing demand for real-time DNN applications on edge devices necessitates faster inference of increasingly complex models. Although many devices include specialized accelerato…
cs.LG2025
ViRN: Variational Inference and Distribution Trilateration for Long-Tailed Continual Representation Learning
Hao Dai, Chong Tang, Jagmohan Chauhan
Continual learning (CL) with long-tailed data distributions remains a critical challenge for real-world AI systems, where models must sequentially adapt to new classes while retain…