8 citations · 27 across the 12 of their papers we have counts for
12 papers
Zebra-Llama: Towards Extremely Efficient Hybrid Models
Mingyu Yang, Mehdi Rezagholizadeh, Guihong Li +2
With the growing demand for deploying large language models (LLMs) across diverse applications, improving their inference efficiency is crucial for sustainable and democratized acc…
X-EcoMLA: Upcycling Pre-Trained Attention into MLA for Efficient and Extreme KV Compression
Guihong Li, Mehdi Rezagholizadeh, Mingyu Yang +2
Multi-head latent attention (MLA) is designed to optimize KV cache memory through low-rank key-value joint compression. Rather than caching keys and values separately, MLA stores t…
SAM-guided Pseudo Label Enhancement for Multi-modal 3D Semantic Segmentation
Mingyu Yang, Jitong Lu, Hun-Seok Kim
Multi-modal 3D semantic segmentation is vital for applications such as autonomous driving and virtual reality (VR). To effectively deploy these models in real-world scenarios, it i…
Diffusion-Aided Joint Source Channel Coding For High Realism Wireless Image Transmission
Mingyu Yang, Bowen Liu, Boyang Wang +1
Deep learning-based joint source-channel coding (deep JSCC) has been demonstrated to be an effective approach for wireless image transmission. Nevertheless, most existing work adop…
Siamese Learning-based Monarch Butterfly Localization
Sara Shoouri, Mingyu Yang, Gordy Carichner +7
A new GPS-less, daily localization method is proposed with deep learning sensor fusion that uses daylight intensity and temperature sensor data for Monarch butterfly tracking. Prio…
Efficient Computation Sharing for Multi-Task Visual Scene Understanding
Sara Shoouri, Mingyu Yang, Zichen Fan +1
Solving multiple visual tasks using individual models can be resource-intensive, while multi-task learning can conserve resources by sharing knowledge across different tasks. Despi…