Picture for Jingyu Liu

Jingyu Liu

VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding

Add code
May 22, 2024
Viaarxiv icon

How Far Are We From AGI

Add code
May 16, 2024
Viaarxiv icon

Unmasking Efficiency: Learning Salient Sparse Models in Non-IID Federated Learning

May 15, 2024
Viaarxiv icon

A Survey of Neural Network Robustness Assessment in Image Recognition

Apr 15, 2024
Viaarxiv icon

Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning

Mar 22, 2024
Figure 1 for Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning
Figure 2 for Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning
Figure 3 for Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning
Figure 4 for Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning
Viaarxiv icon

Brain Networks and Intelligence: A Graph Neural Network Based Approach to Resting State fMRI Data

Add code
Nov 06, 2023
Viaarxiv icon

Do We Really Need Contrastive Learning for Graph Representation?

Oct 23, 2023
Viaarxiv icon

Perfect Alignment May be Poisonous to Graph Contrastive Learning

Oct 06, 2023
Viaarxiv icon

Effective Long-Context Scaling of Foundation Models

Sep 27, 2023
Figure 1 for Effective Long-Context Scaling of Foundation Models
Figure 2 for Effective Long-Context Scaling of Foundation Models
Figure 3 for Effective Long-Context Scaling of Foundation Models
Figure 4 for Effective Long-Context Scaling of Foundation Models
Viaarxiv icon

Code Llama: Open Foundation Models for Code

Add code
Aug 25, 2023
Figure 1 for Code Llama: Open Foundation Models for Code
Figure 2 for Code Llama: Open Foundation Models for Code
Figure 3 for Code Llama: Open Foundation Models for Code
Figure 4 for Code Llama: Open Foundation Models for Code
Viaarxiv icon