Picture for Yu Yuan

Yu Yuan

Cognitive Memory in Large Language Models

Add code
Apr 03, 2025
Viaarxiv icon

Learning Phase Distortion with Selective State Space Models for Video Turbulence Mitigation

Add code
Apr 03, 2025
Viaarxiv icon

S3R-GS: Streamlining the Pipeline for Large-Scale Street Scene Reconstruction

Add code
Mar 11, 2025
Viaarxiv icon

CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing

Add code
Feb 06, 2025
Figure 1 for CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing
Figure 2 for CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing
Figure 3 for CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing
Figure 4 for CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing
Viaarxiv icon

Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models

Add code
Jan 31, 2025
Figure 1 for Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models
Figure 2 for Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models
Figure 3 for Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models
Figure 4 for Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models
Viaarxiv icon

Personalized Generative Low-light Image Denoising and Enhancement

Add code
Dec 18, 2024
Viaarxiv icon

Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis

Add code
Dec 03, 2024
Figure 1 for Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis
Figure 2 for Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis
Figure 3 for Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis
Figure 4 for Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis
Viaarxiv icon

Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models

Add code
Oct 17, 2024
Figure 1 for Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models
Figure 2 for Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models
Figure 3 for Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models
Figure 4 for Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models
Viaarxiv icon

Beyond the Metaverse: XV (eXtended meta/uni/Verse)

Add code
Dec 15, 2022
Figure 1 for Beyond the Metaverse: XV (eXtended meta/uni/Verse)
Figure 2 for Beyond the Metaverse: XV (eXtended meta/uni/Verse)
Figure 3 for Beyond the Metaverse: XV (eXtended meta/uni/Verse)
Figure 4 for Beyond the Metaverse: XV (eXtended meta/uni/Verse)
Viaarxiv icon

Ghost-free High Dynamic Range Imaging via Hybrid CNN-Transformer and Structure Tensor

Add code
Dec 01, 2022
Viaarxiv icon