Picture for Guangxiang Zhao

Guangxiang Zhao

TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation

Add code
Mar 06, 2025
Viaarxiv icon

Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision

Add code
Feb 28, 2025
Viaarxiv icon

LongAttn: Selecting Long-context Training Data via Token-level Attention

Add code
Feb 24, 2025
Viaarxiv icon

Stress Testing Generalization: How Minor Modifications Undermine Large Language Model Performance

Add code
Feb 18, 2025
Viaarxiv icon

When to Trust Aggregated Gradients: Addressing Negative Client Sampling in Federated Learning

Add code
Jan 25, 2023
Viaarxiv icon

From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models

Add code
Oct 11, 2022
Figure 1 for From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models
Figure 2 for From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models
Figure 3 for From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models
Figure 4 for From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models
Viaarxiv icon

Rethinking the Openness of CLIP

Add code
Jun 04, 2022
Viaarxiv icon

Model Uncertainty-Aware Knowledge Amalgamation for Pre-Trained Language Models

Add code
Dec 14, 2021
Figure 1 for Model Uncertainty-Aware Knowledge Amalgamation for Pre-Trained Language Models
Figure 2 for Model Uncertainty-Aware Knowledge Amalgamation for Pre-Trained Language Models
Figure 3 for Model Uncertainty-Aware Knowledge Amalgamation for Pre-Trained Language Models
Figure 4 for Model Uncertainty-Aware Knowledge Amalgamation for Pre-Trained Language Models
Viaarxiv icon

Well-classified Examples are Underestimated in Classification with Deep Neural Networks

Add code
Oct 15, 2021
Figure 1 for Well-classified Examples are Underestimated in Classification with Deep Neural Networks
Figure 2 for Well-classified Examples are Underestimated in Classification with Deep Neural Networks
Figure 3 for Well-classified Examples are Underestimated in Classification with Deep Neural Networks
Figure 4 for Well-classified Examples are Underestimated in Classification with Deep Neural Networks
Viaarxiv icon

Topology-Imbalance Learning for Semi-Supervised Node Classification

Add code
Oct 08, 2021
Figure 1 for Topology-Imbalance Learning for Semi-Supervised Node Classification
Figure 2 for Topology-Imbalance Learning for Semi-Supervised Node Classification
Figure 3 for Topology-Imbalance Learning for Semi-Supervised Node Classification
Figure 4 for Topology-Imbalance Learning for Semi-Supervised Node Classification
Viaarxiv icon