Picture for Yingbin Liang

Yingbin Liang

Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining

Add code
Feb 10, 2025
Figure 1 for Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining
Figure 2 for Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining
Figure 3 for Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining
Figure 4 for Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining
Viaarxiv icon

Object Detection for Medical Image Analysis: Insights from the RT-DETR Model

Add code
Jan 27, 2025
Figure 1 for Object Detection for Medical Image Analysis: Insights from the RT-DETR Model
Figure 2 for Object Detection for Medical Image Analysis: Insights from the RT-DETR Model
Figure 3 for Object Detection for Medical Image Analysis: Insights from the RT-DETR Model
Figure 4 for Object Detection for Medical Image Analysis: Insights from the RT-DETR Model
Viaarxiv icon

Integrative Analysis of Financial Market Sentiment Using CNN and GRU for Risk Prediction and Alert Systems

Add code
Dec 13, 2024
Viaarxiv icon

Leveraging Semi-Supervised Learning to Enhance Data Mining for Image Classification under Limited Labeled Data

Add code
Nov 27, 2024
Figure 1 for Leveraging Semi-Supervised Learning to Enhance Data Mining for Image Classification under Limited Labeled Data
Figure 2 for Leveraging Semi-Supervised Learning to Enhance Data Mining for Image Classification under Limited Labeled Data
Figure 3 for Leveraging Semi-Supervised Learning to Enhance Data Mining for Image Classification under Limited Labeled Data
Figure 4 for Leveraging Semi-Supervised Learning to Enhance Data Mining for Image Classification under Limited Labeled Data
Viaarxiv icon

Enhancing Few-Shot Learning with Integrated Data and GAN Model Approaches

Add code
Nov 25, 2024
Viaarxiv icon

Robust Offline Reinforcement Learning for Non-Markovian Decision Processes

Add code
Nov 12, 2024
Viaarxiv icon

Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers

Add code
Oct 17, 2024
Figure 1 for Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers
Figure 2 for Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers
Viaarxiv icon

Optimizing YOLOv5s Object Detection through Knowledge Distillation algorithm

Add code
Oct 16, 2024
Figure 1 for Optimizing YOLOv5s Object Detection through Knowledge Distillation algorithm
Figure 2 for Optimizing YOLOv5s Object Detection through Knowledge Distillation algorithm
Figure 3 for Optimizing YOLOv5s Object Detection through Knowledge Distillation algorithm
Figure 4 for Optimizing YOLOv5s Object Detection through Knowledge Distillation algorithm
Viaarxiv icon

Model Developmental Safety: A Safety-Centric Method and Applications in Vision-Language Models

Add code
Oct 13, 2024
Figure 1 for Model Developmental Safety: A Safety-Centric Method and Applications in Vision-Language Models
Figure 2 for Model Developmental Safety: A Safety-Centric Method and Applications in Vision-Language Models
Figure 3 for Model Developmental Safety: A Safety-Centric Method and Applications in Vision-Language Models
Figure 4 for Model Developmental Safety: A Safety-Centric Method and Applications in Vision-Language Models
Viaarxiv icon

Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis

Add code
Oct 12, 2024
Figure 1 for Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis
Viaarxiv icon