Picture for Yingying Zhang

Yingying Zhang

When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning

Add code
Mar 10, 2025
Viaarxiv icon

RCRank: Multimodal Ranking of Root Causes of Slow Queries in Cloud Database Systems

Add code
Mar 06, 2025
Figure 1 for RCRank: Multimodal Ranking of Root Causes of Slow Queries in Cloud Database Systems
Figure 2 for RCRank: Multimodal Ranking of Root Causes of Slow Queries in Cloud Database Systems
Figure 3 for RCRank: Multimodal Ranking of Root Causes of Slow Queries in Cloud Database Systems
Figure 4 for RCRank: Multimodal Ranking of Root Causes of Slow Queries in Cloud Database Systems
Viaarxiv icon

Sliding Window Attention Training for Efficient Large Language Models

Add code
Feb 26, 2025
Viaarxiv icon

From System 1 to System 2: A Survey of Reasoning Large Language Models

Add code
Feb 25, 2025
Viaarxiv icon

Understanding Generalization in Transformers: Error Bounds and Training Dynamics Under Benign and Harmful Overfitting

Add code
Feb 18, 2025
Viaarxiv icon

RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?

Add code
Jan 20, 2025
Viaarxiv icon

Cross-View Geo-Localization with Street-View and VHR Satellite Imagery in Decentrality Settings

Add code
Dec 16, 2024
Viaarxiv icon

HomoMatcher: Dense Feature Matching Results with Semi-Dense Efficiency by Homography Estimation

Add code
Nov 11, 2024
Viaarxiv icon

Cluster-Wide Task Slowdown Detection in Cloud System

Add code
Aug 08, 2024
Figure 1 for Cluster-Wide Task Slowdown Detection in Cloud System
Figure 2 for Cluster-Wide Task Slowdown Detection in Cloud System
Figure 3 for Cluster-Wide Task Slowdown Detection in Cloud System
Figure 4 for Cluster-Wide Task Slowdown Detection in Cloud System
Viaarxiv icon

POA: Pre-training Once for Models of All Sizes

Add code
Aug 02, 2024
Figure 1 for POA: Pre-training Once for Models of All Sizes
Figure 2 for POA: Pre-training Once for Models of All Sizes
Figure 3 for POA: Pre-training Once for Models of All Sizes
Figure 4 for POA: Pre-training Once for Models of All Sizes
Viaarxiv icon