Picture for Jun Huang

Jun Huang

An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services

Add code
Nov 05, 2024
Figure 1 for An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services
Figure 2 for An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services
Figure 3 for An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services
Figure 4 for An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services
Viaarxiv icon

Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective

Add code
Oct 14, 2024
Figure 1 for Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective
Figure 2 for Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective
Figure 3 for Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective
Figure 4 for Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective
Viaarxiv icon

VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models

Add code
Oct 01, 2024
Viaarxiv icon

DocLayLLM: An Efficient and Effective Multi-modal Extension of Large Language Models for Text-rich Document Understanding

Add code
Aug 27, 2024
Viaarxiv icon

Rotation center identification based on geometric relationships for rotary motion deblurring

Add code
Aug 08, 2024
Viaarxiv icon

Spatio-Temporal Encoding and Decoding-Based Method for Future Human Activity Skeleton Synthesis

Add code
Jul 08, 2024
Figure 1 for Spatio-Temporal Encoding and Decoding-Based Method for Future Human Activity Skeleton Synthesis
Figure 2 for Spatio-Temporal Encoding and Decoding-Based Method for Future Human Activity Skeleton Synthesis
Figure 3 for Spatio-Temporal Encoding and Decoding-Based Method for Future Human Activity Skeleton Synthesis
Figure 4 for Spatio-Temporal Encoding and Decoding-Based Method for Future Human Activity Skeleton Synthesis
Viaarxiv icon

On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Models

Add code
Jun 24, 2024
Figure 1 for On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Models
Figure 2 for On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Models
Figure 3 for On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Models
Figure 4 for On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Models
Viaarxiv icon

DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models

Add code
May 31, 2024
Figure 1 for DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models
Figure 2 for DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models
Figure 3 for DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models
Figure 4 for DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models
Viaarxiv icon

EasyAnimate: A High-Performance Long Video Generation Method based on Transformer Architecture

Add code
May 29, 2024
Viaarxiv icon

Distilling Instruction-following Abilities of Large Language Models with Task-aware Curriculum Planning

Add code
May 22, 2024
Viaarxiv icon