Search

Mingkui Tan

Enhancing Perception Capabilities of Multimodal LLMs with Training-Free Fusion
Efficient test-time adaptation for super-resolution with second-order degradation and reconstruction
Single-path bit sharing for automatic loss-aware model compression
Aqd: Towards accurate quantized object detection
Discrimination-aware network pruning for deep model compression
Effective training of convolutional neural networks with low-bitwidth weights and activations
Structured binary neural networks for accurate image classification and semantic segmentation

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.