Picture for De-An Huang

De-An Huang

X-VILA: Cross-Modality Alignment for Large Language Model

Add code
May 29, 2024
Viaarxiv icon

What is Point Supervision Worth in Video Instance Segmentation?

Apr 01, 2024
Viaarxiv icon

LITA: Language Instructed Temporal-Localization Assistant

Add code
Mar 27, 2024
Figure 1 for LITA: Language Instructed Temporal-Localization Assistant
Figure 2 for LITA: Language Instructed Temporal-Localization Assistant
Figure 3 for LITA: Language Instructed Temporal-Localization Assistant
Figure 4 for LITA: Language Instructed Temporal-Localization Assistant
Viaarxiv icon

Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition

Add code
Mar 21, 2024
Figure 1 for Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
Figure 2 for Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
Figure 3 for Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
Figure 4 for Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
Viaarxiv icon

T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching

Add code
Feb 21, 2024
Viaarxiv icon

Deep Multimodal Fusion for Surgical Feedback Classification

Dec 06, 2023
Viaarxiv icon

Eureka: Human-Level Reward Design via Coding Large Language Models

Add code
Oct 19, 2023
Viaarxiv icon

Differentially Private Video Activity Recognition

Jun 27, 2023
Figure 1 for Differentially Private Video Activity Recognition
Figure 2 for Differentially Private Video Activity Recognition
Figure 3 for Differentially Private Video Activity Recognition
Figure 4 for Differentially Private Video Activity Recognition
Viaarxiv icon

PerAda: Parameter-Efficient and Generalizable Federated Learning Personalization with Guarantees

Feb 13, 2023
Figure 1 for PerAda: Parameter-Efficient and Generalizable Federated Learning Personalization with Guarantees
Figure 2 for PerAda: Parameter-Efficient and Generalizable Federated Learning Personalization with Guarantees
Figure 3 for PerAda: Parameter-Efficient and Generalizable Federated Learning Personalization with Guarantees
Figure 4 for PerAda: Parameter-Efficient and Generalizable Federated Learning Personalization with Guarantees
Viaarxiv icon

I$^2$SB: Image-to-Image Schrödinger Bridge

Add code
Feb 12, 2023
Figure 1 for I$^2$SB: Image-to-Image Schrödinger Bridge
Figure 2 for I$^2$SB: Image-to-Image Schrödinger Bridge
Figure 3 for I$^2$SB: Image-to-Image Schrödinger Bridge
Figure 4 for I$^2$SB: Image-to-Image Schrödinger Bridge
Viaarxiv icon