Picture for Weijie Liu

Weijie Liu

DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Dataset

Oct 20, 2023
Viaarxiv icon

Towards Optimal Randomized Strategies in Adversarial Example Game

Add code
Jun 29, 2023
Figure 1 for Towards Optimal Randomized Strategies in Adversarial Example Game
Figure 2 for Towards Optimal Randomized Strategies in Adversarial Example Game
Figure 3 for Towards Optimal Randomized Strategies in Adversarial Example Game
Viaarxiv icon

Recouple Event Field via Probabilistic Bias for Event Extraction

Add code
May 19, 2023
Figure 1 for Recouple Event Field via Probabilistic Bias for Event Extraction
Figure 2 for Recouple Event Field via Probabilistic Bias for Event Extraction
Figure 3 for Recouple Event Field via Probabilistic Bias for Event Extraction
Figure 4 for Recouple Event Field via Probabilistic Bias for Event Extraction
Viaarxiv icon

TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities

Add code
Dec 13, 2022
Figure 1 for TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities
Figure 2 for TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities
Figure 3 for TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities
Figure 4 for TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities
Viaarxiv icon

Modeling Fine-grained Information via Knowledge-aware Hierarchical Graph for Zero-shot Entity Retrieval

Add code
Nov 20, 2022
Figure 1 for Modeling Fine-grained Information via Knowledge-aware Hierarchical Graph for Zero-shot Entity Retrieval
Figure 2 for Modeling Fine-grained Information via Knowledge-aware Hierarchical Graph for Zero-shot Entity Retrieval
Figure 3 for Modeling Fine-grained Information via Knowledge-aware Hierarchical Graph for Zero-shot Entity Retrieval
Figure 4 for Modeling Fine-grained Information via Knowledge-aware Hierarchical Graph for Zero-shot Entity Retrieval
Viaarxiv icon

A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning

Add code
Oct 18, 2022
Figure 1 for A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning
Figure 2 for A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning
Figure 3 for A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning
Figure 4 for A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning
Viaarxiv icon

SAMP: A Toolkit for Model Inference with Self-Adaptive Mixed-Precision

Add code
Sep 19, 2022
Figure 1 for SAMP: A Toolkit for Model Inference with Self-Adaptive Mixed-Precision
Figure 2 for SAMP: A Toolkit for Model Inference with Self-Adaptive Mixed-Precision
Figure 3 for SAMP: A Toolkit for Model Inference with Self-Adaptive Mixed-Precision
Figure 4 for SAMP: A Toolkit for Model Inference with Self-Adaptive Mixed-Precision
Viaarxiv icon

Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching

Add code
Sep 13, 2022
Figure 1 for Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching
Figure 2 for Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching
Figure 3 for Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching
Figure 4 for Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching
Viaarxiv icon

CSL: A Large-scale Chinese Scientific Literature Dataset

Add code
Sep 12, 2022
Figure 1 for CSL: A Large-scale Chinese Scientific Literature Dataset
Figure 2 for CSL: A Large-scale Chinese Scientific Literature Dataset
Figure 3 for CSL: A Large-scale Chinese Scientific Literature Dataset
Figure 4 for CSL: A Large-scale Chinese Scientific Literature Dataset
Viaarxiv icon

Merak: An Efficient Distributed DNN Training Framework with Automated 3D Parallelism for Giant Foundation Models

Add code
Jun 21, 2022
Figure 1 for Merak: An Efficient Distributed DNN Training Framework with Automated 3D Parallelism for Giant Foundation Models
Figure 2 for Merak: An Efficient Distributed DNN Training Framework with Automated 3D Parallelism for Giant Foundation Models
Figure 3 for Merak: An Efficient Distributed DNN Training Framework with Automated 3D Parallelism for Giant Foundation Models
Figure 4 for Merak: An Efficient Distributed DNN Training Framework with Automated 3D Parallelism for Giant Foundation Models
Viaarxiv icon