Picture for Ziyue Yang

Ziyue Yang

Uncertainty Aware Human-machine Collaboration in Camouflaged Object Detection

Add code
Feb 12, 2025
Viaarxiv icon

Optimizing Large Language Model Training Using FP4 Quantization

Add code
Jan 28, 2025
Figure 1 for Optimizing Large Language Model Training Using FP4 Quantization
Figure 2 for Optimizing Large Language Model Training Using FP4 Quantization
Figure 3 for Optimizing Large Language Model Training Using FP4 Quantization
Figure 4 for Optimizing Large Language Model Training Using FP4 Quantization
Viaarxiv icon

Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models

Add code
Jan 23, 2025
Figure 1 for Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models
Figure 2 for Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models
Figure 3 for Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models
Figure 4 for Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models
Viaarxiv icon

SPFresh: Incremental In-Place Update for Billion-Scale Vector Search

Add code
Oct 18, 2024
Figure 1 for SPFresh: Incremental In-Place Update for Billion-Scale Vector Search
Figure 2 for SPFresh: Incremental In-Place Update for Billion-Scale Vector Search
Figure 3 for SPFresh: Incremental In-Place Update for Billion-Scale Vector Search
Figure 4 for SPFresh: Incremental In-Place Update for Billion-Scale Vector Search
Viaarxiv icon

ForestColl: Efficient Collective Communications on Heterogeneous Network Fabrics

Add code
Feb 09, 2024
Viaarxiv icon

FP8-LM: Training FP8 Large Language Models

Add code
Oct 27, 2023
Figure 1 for FP8-LM: Training FP8 Large Language Models
Figure 2 for FP8-LM: Training FP8 Large Language Models
Figure 3 for FP8-LM: Training FP8 Large Language Models
Figure 4 for FP8-LM: Training FP8 Large Language Models
Viaarxiv icon

Copyright Protection and Accountability of Generative AI:Attack, Watermarking and Attribution

Add code
Mar 15, 2023
Viaarxiv icon

Tutel: Adaptive Mixture-of-Experts at Scale

Add code
Jun 07, 2022
Figure 1 for Tutel: Adaptive Mixture-of-Experts at Scale
Figure 2 for Tutel: Adaptive Mixture-of-Experts at Scale
Figure 3 for Tutel: Adaptive Mixture-of-Experts at Scale
Figure 4 for Tutel: Adaptive Mixture-of-Experts at Scale
Viaarxiv icon

ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection

Add code
Jun 11, 2021
Figure 1 for ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection
Figure 2 for ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection
Figure 3 for ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection
Figure 4 for ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection
Viaarxiv icon