Picture for Hong Zhou

Hong Zhou

ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification

May 23, 2024
Viaarxiv icon

Multimodal Sense-Informed Prediction of 3D Human Motions

May 05, 2024
Viaarxiv icon

The intelligent prediction and assessment of financial information risk in the cloud computing model

Apr 14, 2024
Viaarxiv icon

Towards Accurate Post-training Quantization for Reparameterized Models

Add code
Feb 25, 2024
Viaarxiv icon

EL-VIT: Probing Vision Transformer with Interactive Visualization

Jan 23, 2024
Viaarxiv icon

DSText V2: A Comprehensive Video Text Spotting Dataset for Dense and Small Text

Add code
Nov 29, 2023
Viaarxiv icon

Continual Learning for Image Segmentation with Dynamic Query

Add code
Nov 29, 2023
Viaarxiv icon

Improving Vision-and-Language Reasoning via Spatial Relations Modeling

Nov 09, 2023
Viaarxiv icon

EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models

Add code
Oct 12, 2023
Figure 1 for EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models
Figure 2 for EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models
Figure 3 for EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models
Figure 4 for EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models
Viaarxiv icon

Dual Grained Quantization: Efficient Fine-Grained Quantization for LLM

Oct 07, 2023
Figure 1 for Dual Grained Quantization: Efficient Fine-Grained Quantization for LLM
Figure 2 for Dual Grained Quantization: Efficient Fine-Grained Quantization for LLM
Figure 3 for Dual Grained Quantization: Efficient Fine-Grained Quantization for LLM
Figure 4 for Dual Grained Quantization: Efficient Fine-Grained Quantization for LLM
Viaarxiv icon