Skip to content

Author

Yik-Chung Wu

We have 5 of 351 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

CrossRAFT: Cross-Domain Complex-Valued Feature Extraction for Ultrasound Motion Estimation

These findings demonstrate that leveraging phase information via complex-valued neural networks provides a powerful framework for ultrasound motion estimation, showing potential for clinical elastography and functional imaging.

Yang Leng, Yu-Chen Tang, Kai-Hang Yiu et al. · 0 citations
Aug 2026

Low-Complexity Sparse Bayesian Learning for Joint Channel Estimation and Target Detection in ISAC

In massive multiple-input multiple-output (MIMO) Integrated Sensing and Communications (ISAC) systems, the joint task of high-dimensional channel estimation and multi-target detection suffers from a severe computational bottleneck, which limits practical deployment and system scalability. To address this problem, this...

Wan-Jun Qing, Xiao-Xu Zhang, C. Masouros et al. · 0 citations
#machine learning Preprint Sep 2026

Automatic Rank Allocation for Low-Rank Adaptation in Large Language Models via lp Regularization

This work regularizes the energy of each rank-one LoRA component, encouraging redundant components to vanish while preserving important ones, and proposes a principled rank-allocation method based on classical sparsity-inducing technique in signal processing and statistics.

Ze-Bang Xie, Chuan-Yang Zheng, Yik-Chung Wu et al. · 0 citations

Memory-Native Non-Terrestrial Networks for Embodied Intelligence

This paper proposes the memory-native NTN (Mem-NTN) paradigm that leverages long-horizon contexts for memory-augmented system optimization and establishes a dual-memory architecture that distinguishes between physical memory representing the state of the world and digital memory encoding historical network experience.

Chengyang Li, Yi-Kun Wang, Jia-Hui He et al. · 0 citations
Preprint Aug 2026

FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy

FluxBin is proposed, an algorithm-kernel co-design that synergizes post-training quantization with a highly optimized CUDA kernel and introduces Decoupled Row-Column Binary Decomposition to enhance representational capacity while maintaining hardware efficiency.

Qingyao Yang, Run-Ming Yang, He Xiao et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.