Picture for Yonggang Wen

Yonggang Wen

TorchGT: A Holistic System for Large-scale Graph Transformer Training

Add code
Jul 19, 2024
Viaarxiv icon

Characterization of Large Language Model Development in the Datacenter

Add code
Mar 12, 2024
Figure 1 for Characterization of Large Language Model Development in the Datacenter
Figure 2 for Characterization of Large Language Model Development in the Datacenter
Figure 3 for Characterization of Large Language Model Development in the Datacenter
Figure 4 for Characterization of Large Language Model Development in the Datacenter
Viaarxiv icon

Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases

Add code
Feb 13, 2024
Figure 1 for Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases
Figure 2 for Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases
Figure 3 for Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases
Figure 4 for Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases
Viaarxiv icon

PartSeg: Few-shot Part Segmentation via Part-aware Prompt Learning

Add code
Aug 24, 2023
Figure 1 for PartSeg: Few-shot Part Segmentation via Part-aware Prompt Learning
Figure 2 for PartSeg: Few-shot Part Segmentation via Part-aware Prompt Learning
Figure 3 for PartSeg: Few-shot Part Segmentation via Part-aware Prompt Learning
Figure 4 for PartSeg: Few-shot Part Segmentation via Part-aware Prompt Learning
Viaarxiv icon

Rethinking the Localization in Weakly Supervised Object Localization

Add code
Aug 11, 2023
Figure 1 for Rethinking the Localization in Weakly Supervised Object Localization
Figure 2 for Rethinking the Localization in Weakly Supervised Object Localization
Figure 3 for Rethinking the Localization in Weakly Supervised Object Localization
Figure 4 for Rethinking the Localization in Weakly Supervised Object Localization
Viaarxiv icon

MAS: Towards Resource-Efficient Federated Multiple-Task Learning

Add code
Jul 21, 2023
Figure 1 for MAS: Towards Resource-Efficient Federated Multiple-Task Learning
Figure 2 for MAS: Towards Resource-Efficient Federated Multiple-Task Learning
Figure 3 for MAS: Towards Resource-Efficient Federated Multiple-Task Learning
Figure 4 for MAS: Towards Resource-Efficient Federated Multiple-Task Learning
Viaarxiv icon

FHA-Kitchens: A Novel Dataset for Fine-Grained Hand Action Recognition in Kitchen Scenes

Add code
Jun 19, 2023
Figure 1 for FHA-Kitchens: A Novel Dataset for Fine-Grained Hand Action Recognition in Kitchen Scenes
Figure 2 for FHA-Kitchens: A Novel Dataset for Fine-Grained Hand Action Recognition in Kitchen Scenes
Figure 3 for FHA-Kitchens: A Novel Dataset for Fine-Grained Hand Action Recognition in Kitchen Scenes
Figure 4 for FHA-Kitchens: A Novel Dataset for Fine-Grained Hand Action Recognition in Kitchen Scenes
Viaarxiv icon

Boosting Distributed Full-graph GNN Training with Asynchronous One-bit Communication

Add code
Mar 02, 2023
Figure 1 for Boosting Distributed Full-graph GNN Training with Asynchronous One-bit Communication
Figure 2 for Boosting Distributed Full-graph GNN Training with Asynchronous One-bit Communication
Figure 3 for Boosting Distributed Full-graph GNN Training with Asynchronous One-bit Communication
Figure 4 for Boosting Distributed Full-graph GNN Training with Asynchronous One-bit Communication
Viaarxiv icon

FedABC: Targeting Fair Competition in Personalized Federated Learning

Add code
Feb 15, 2023
Figure 1 for FedABC: Targeting Fair Competition in Personalized Federated Learning
Figure 2 for FedABC: Targeting Fair Competition in Personalized Federated Learning
Figure 3 for FedABC: Targeting Fair Competition in Personalized Federated Learning
Figure 4 for FedABC: Targeting Fair Competition in Personalized Federated Learning
Viaarxiv icon

Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE

Add code
Dec 04, 2022
Figure 1 for Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE
Figure 2 for Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE
Figure 3 for Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE
Figure 4 for Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE
Viaarxiv icon