3 papers
eess.SP2024
Hybrid Data-Driven SSM for Interpretable and Label-Free mmWave Channel Prediction
Yiyong Sun, Jiajun He, Zhidi Lin +3
Accurate prediction of mmWave time-varying channels is essential for mitigating the issue of channel aging in complex scenarios owing to high user mobility. Existing channel predic…
cs.LG2024
Efficient and Unbiased Sampling of Boltzmann Distributions via Consistency Models
Fengzhe Zhang, Jiajun He, Laurence I. Midgley +2
Diffusion models have shown promising potential for advancing Boltzmann Generators. However, two critical challenges persist: (1) inherent errors in samples due to model imperfecti…
cs.AI2023
ed-cec: improving rare word recognition using asr postprocessing based on error detection and context-aware error correction
Jiajun He, Zekun Yang, Tomoki Toda
Automatic speech recognition (ASR) systems often encounter difficulties in accurately recognizing rare words, leading to errors that can have a negative impact on downstream tasks…