Picture for Xin Ding

Xin Ding

StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition

Add code
Mar 08, 2025
Viaarxiv icon

Q&C: When Quantization Meets Cache in Efficient Image Generation

Add code
Mar 04, 2025
Viaarxiv icon

Hyper Adversarial Tuning for Boosting Adversarial Robustness of Pretrained Large Vision Models

Add code
Oct 08, 2024
Figure 1 for Hyper Adversarial Tuning for Boosting Adversarial Robustness of Pretrained Large Vision Models
Figure 2 for Hyper Adversarial Tuning for Boosting Adversarial Robustness of Pretrained Large Vision Models
Figure 3 for Hyper Adversarial Tuning for Boosting Adversarial Robustness of Pretrained Large Vision Models
Figure 4 for Hyper Adversarial Tuning for Boosting Adversarial Robustness of Pretrained Large Vision Models
Viaarxiv icon

HyperDet: Generalizable Detection of Synthesized Images by Generating and Merging A Mixture of Hyper LoRAs

Add code
Oct 08, 2024
Figure 1 for HyperDet: Generalizable Detection of Synthesized Images by Generating and Merging A Mixture of Hyper LoRAs
Figure 2 for HyperDet: Generalizable Detection of Synthesized Images by Generating and Merging A Mixture of Hyper LoRAs
Figure 3 for HyperDet: Generalizable Detection of Synthesized Images by Generating and Merging A Mixture of Hyper LoRAs
Figure 4 for HyperDet: Generalizable Detection of Synthesized Images by Generating and Merging A Mixture of Hyper LoRAs
Viaarxiv icon

CCDM: Continuous Conditional Diffusion Models for Image Generation

Add code
May 06, 2024
Figure 1 for CCDM: Continuous Conditional Diffusion Models for Image Generation
Figure 2 for CCDM: Continuous Conditional Diffusion Models for Image Generation
Figure 3 for CCDM: Continuous Conditional Diffusion Models for Image Generation
Figure 4 for CCDM: Continuous Conditional Diffusion Models for Image Generation
Viaarxiv icon

Driving Style Alignment for LLM-powered Driver Agent

Add code
Mar 17, 2024
Viaarxiv icon

CBQ: Cross-Block Quantization for Large Language Models

Add code
Dec 13, 2023
Figure 1 for CBQ: Cross-Block Quantization for Large Language Models
Figure 2 for CBQ: Cross-Block Quantization for Large Language Models
Figure 3 for CBQ: Cross-Block Quantization for Large Language Models
Figure 4 for CBQ: Cross-Block Quantization for Large Language Models
Viaarxiv icon

Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networks

Add code
Aug 20, 2023
Viaarxiv icon

Regression-Oriented Knowledge Distillation for Lightweight Ship Orientation Angle Prediction with Optical Remote Sensing Images

Add code
Jul 13, 2023
Figure 1 for Regression-Oriented Knowledge Distillation for Lightweight Ship Orientation Angle Prediction with Optical Remote Sensing Images
Figure 2 for Regression-Oriented Knowledge Distillation for Lightweight Ship Orientation Angle Prediction with Optical Remote Sensing Images
Figure 3 for Regression-Oriented Knowledge Distillation for Lightweight Ship Orientation Angle Prediction with Optical Remote Sensing Images
Figure 4 for Regression-Oriented Knowledge Distillation for Lightweight Ship Orientation Angle Prediction with Optical Remote Sensing Images
Viaarxiv icon

A Scale-Arbitrary Image Super-Resolution Network Using Frequency-domain Information

Add code
Dec 08, 2022
Viaarxiv icon