Picture for Peng Yan

Peng Yan

Truth in the Few: High-Value Data Selection for Efficient Multi-Modal Reasoning

Add code
Jun 05, 2025
Viaarxiv icon

Learning Actionable World Models for Industrial Process Control

Add code
Mar 03, 2025
Viaarxiv icon

AI Agents for Computer Use: A Review of Instruction-based Computer Control, GUI Automation, and Operator Assistants

Add code
Jan 27, 2025
Figure 1 for AI Agents for Computer Use: A Review of Instruction-based Computer Control, GUI Automation, and Operator Assistants
Figure 2 for AI Agents for Computer Use: A Review of Instruction-based Computer Control, GUI Automation, and Operator Assistants
Figure 3 for AI Agents for Computer Use: A Review of Instruction-based Computer Control, GUI Automation, and Operator Assistants
Figure 4 for AI Agents for Computer Use: A Review of Instruction-based Computer Control, GUI Automation, and Operator Assistants
Viaarxiv icon

Augmenting the Veracity and Explanations of Complex Fact Checking via Iterative Self-Revision with LLMs

Add code
Oct 19, 2024
Figure 1 for Augmenting the Veracity and Explanations of Complex Fact Checking via Iterative Self-Revision with LLMs
Figure 2 for Augmenting the Veracity and Explanations of Complex Fact Checking via Iterative Self-Revision with LLMs
Figure 3 for Augmenting the Veracity and Explanations of Complex Fact Checking via Iterative Self-Revision with LLMs
Figure 4 for Augmenting the Veracity and Explanations of Complex Fact Checking via Iterative Self-Revision with LLMs
Viaarxiv icon

Personalized Image Generation with Large Multimodal Models

Add code
Oct 18, 2024
Viaarxiv icon

Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization

Add code
Sep 17, 2024
Figure 1 for Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization
Figure 2 for Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization
Figure 3 for Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization
Figure 4 for Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization
Viaarxiv icon

Personalized Interpretation on Federated Learning: A Virtual Concepts approach

Add code
Jun 28, 2024
Figure 1 for Personalized Interpretation on Federated Learning: A Virtual Concepts approach
Figure 2 for Personalized Interpretation on Federated Learning: A Virtual Concepts approach
Figure 3 for Personalized Interpretation on Federated Learning: A Virtual Concepts approach
Figure 4 for Personalized Interpretation on Federated Learning: A Virtual Concepts approach
Viaarxiv icon

Improved Content Understanding With Effective Use of Multi-task Contrastive Learning

Add code
May 21, 2024
Figure 1 for Improved Content Understanding With Effective Use of Multi-task Contrastive Learning
Figure 2 for Improved Content Understanding With Effective Use of Multi-task Contrastive Learning
Figure 3 for Improved Content Understanding With Effective Use of Multi-task Contrastive Learning
Figure 4 for Improved Content Understanding With Effective Use of Multi-task Contrastive Learning
Viaarxiv icon

Large-Scale Multi-Domain Recommendation: an Automatic Domain Feature Extraction and Personalized Integration Framework

Add code
Apr 15, 2024
Figure 1 for Large-Scale Multi-Domain Recommendation: an Automatic Domain Feature Extraction and Personalized Integration Framework
Figure 2 for Large-Scale Multi-Domain Recommendation: an Automatic Domain Feature Extraction and Personalized Integration Framework
Figure 3 for Large-Scale Multi-Domain Recommendation: an Automatic Domain Feature Extraction and Personalized Integration Framework
Figure 4 for Large-Scale Multi-Domain Recommendation: an Automatic Domain Feature Extraction and Personalized Integration Framework
Viaarxiv icon

Calibrating the Confidence of Large Language Models by Eliciting Fidelity

Add code
Apr 03, 2024
Figure 1 for Calibrating the Confidence of Large Language Models by Eliciting Fidelity
Figure 2 for Calibrating the Confidence of Large Language Models by Eliciting Fidelity
Figure 3 for Calibrating the Confidence of Large Language Models by Eliciting Fidelity
Figure 4 for Calibrating the Confidence of Large Language Models by Eliciting Fidelity
Viaarxiv icon