Thông tin nhà nghiên cứu KH&CN

Single Concatenated Input is Better than Indenpendent Multiple-input for CNNs to Predict Chemical-induced Disease Relation from Literature

Memory-Based Method using Prototype Augmentation for Continual Relation Extraction

Bert Adapter and Contrastive Learning for Continual Classification of Aspect Sentiment Task Sequences Tác giả

Mitigating Catastrophic Forgetting in Neural Machine Translation Through Teacher-Student Distillation with Attention Mechanism

Document-level chemical-induced disease semantic relation extraction using bidirectional long short-term memory on dependency graph

Dynamic Prompt Selection for Resource-Efficient Continual Learning in Panoptic Segmentation Tác giả

Deep Continual Image Classification Based on Memory Prototype and Energy-Based Feature Synchronizing Tác giả

Contrastive Learning for Boosting Knowledge Transfer in Task-Incremental Continual Learning of Aspect Sentiment Classification Tasks

Enhancing Continual Abdominal Multi-Organ and Tumor Segmentation through Best Model Knowledge Distillation and Encoder-Decoder Training

Towards Robust Continual Learning: A Multi-head Approach with Online Prototype Equilibrium and Adaptive Prototypical Feedback

Continual Extraction of Semantic Relations using Augmented Prototypes with Energy-based Model Alignment

Integrating Graph and Transformer-Based Models for Enhanced Chemical-Disease Relation Extraction in Document-Level Contexts

TMMP: Efficient Continual Learning via Mixture of LoRA Experts and Top Maximum Magnitude Parameter Fusion

Enhancing Continual Abdominal Multi-Organ and Tumor Segmentation through Best Model Knowledge Distillation and Encoder-Decoder Training

Bert Adapter and Contrastive Learning for Continual Classification of Aspect Sentiment Task Sequences Tác giả

Continual Extraction of Semantic Relations using Augmented Prototypes with Energy-based Model Alignment

Contrastive Learning for Boosting Knowledge Transfer in Task-Incremental Continual Learning of Aspect Sentiment Classification Tasks

Deep Continual Image Classification Based on Memory Prototype and Energy-Based Feature Synchronizing Tác giả

Document-level chemical-induced disease semantic relation extraction using bidirectional long short-term memory on dependency graph

Dynamic Prompt Se-lection for Resource-Efficient Continual Learning in Panoptic Segmentation Tác giả

Integrating Graph and Transformer-Based Models for Enhanced Chemical-Disease Relation Extraction in Document-Level Contexts

Memory-Based Method using Prototype Augmentation for Continual Relation Extraction

Mitigating Catastrophic Forgetting in Neural Machine Translation Through Teacher-Student Distillation with Attention Mechanism

Single Con-catenated Input is Better than Indenpendent Multiple-input for CNNs to Predict Chemical-induced Disease Relation f-rom Literature

TMMP: Efficient Continual Learning via Mixture of LoRA Experts and Top Maximum Magnitude Parameter Fusion

Towards Robust Continual Learning: A Multi-head Approach with Online Prototype Equilibrium and Adaptive Prototypical Feedback

Học liên tục dựa trên mô hình ngôn ngữ đào tạo trước kết hợp với học máy tương phản cho bài toán trích xuất quan hệ ngữ nghĩa

Học liên tục dựa trên mô hình ngôn ngữ đào tạo trước kết hợp với học máy tương phản cho bài toán trích xuất quan hệ ngữ nghĩa