3 papers
cs.LG2025
Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation
Hoigi Seo, Wongi Jeong, Jae-sun Seo +1
Large-scale text encoders in text-to-image (T2I) diffusion models have demonstrated exceptional performance in generating high-quality images from textual prompts. Unlike denoising…
cs.LG2025
RaZeR: Pushing the Limits of NVFP4 Quantization with Redundant Zero Remapping
Yuzong Chen, Xilai Dai, Jake Hyun +6
The recently introduced NVFP4 format demonstrates remarkable performance and memory benefits for quantized large language model (LLM) inference. However, we observe two types of re…
cs.CV2024
Neural Architecture Search of Hybrid Models for NPU-CIM Heterogeneous AR/VR Devices
Yiwei Zhao, Ziyun Li, Win-San Khwa +10
Low-Latency and Low-Power Edge AI is essential for Virtual Reality and Augmented Reality applications. Recent advances show that hybrid models, combining convolution layers (CNN) a…