Picture for Liang Wan

Liang Wan

NUC-Net: Non-uniform Cylindrical Partition Network for Efficient LiDAR Semantic Segmentation

Add code
May 30, 2025
Viaarxiv icon

On Path to Multimodal Historical Reasoning: HistBench and HistAgent

Add code
May 26, 2025
Viaarxiv icon

Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation

Add code
Mar 28, 2025
Figure 1 for Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation
Figure 2 for Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation
Figure 3 for Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation
Figure 4 for Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation
Viaarxiv icon

Casual Inference via Style Bias Deconfounding for Domain Generalization

Add code
Mar 21, 2025
Figure 1 for Casual Inference via Style Bias Deconfounding for Domain Generalization
Figure 2 for Casual Inference via Style Bias Deconfounding for Domain Generalization
Figure 3 for Casual Inference via Style Bias Deconfounding for Domain Generalization
Figure 4 for Casual Inference via Style Bias Deconfounding for Domain Generalization
Viaarxiv icon

iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models

Add code
Dec 09, 2024
Figure 1 for iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models
Figure 2 for iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models
Figure 3 for iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models
Figure 4 for iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models
Viaarxiv icon

Deep Correlated Prompting for Visual Recognition with Missing Modalities

Add code
Oct 10, 2024
Figure 1 for Deep Correlated Prompting for Visual Recognition with Missing Modalities
Figure 2 for Deep Correlated Prompting for Visual Recognition with Missing Modalities
Figure 3 for Deep Correlated Prompting for Visual Recognition with Missing Modalities
Figure 4 for Deep Correlated Prompting for Visual Recognition with Missing Modalities
Viaarxiv icon

Completed Feature Disentanglement Learning for Multimodal MRIs Analysis

Add code
Jul 06, 2024
Figure 1 for Completed Feature Disentanglement Learning for Multimodal MRIs Analysis
Figure 2 for Completed Feature Disentanglement Learning for Multimodal MRIs Analysis
Figure 3 for Completed Feature Disentanglement Learning for Multimodal MRIs Analysis
Figure 4 for Completed Feature Disentanglement Learning for Multimodal MRIs Analysis
Viaarxiv icon

Topicwise Separable Sentence Retrieval for Medical Report Generation

Add code
May 07, 2024
Figure 1 for Topicwise Separable Sentence Retrieval for Medical Report Generation
Figure 2 for Topicwise Separable Sentence Retrieval for Medical Report Generation
Figure 3 for Topicwise Separable Sentence Retrieval for Medical Report Generation
Figure 4 for Topicwise Separable Sentence Retrieval for Medical Report Generation
Viaarxiv icon

CorrNet+: Sign Language Recognition and Translation via Spatial-Temporal Correlation

Add code
Apr 17, 2024
Figure 1 for CorrNet+: Sign Language Recognition and Translation via Spatial-Temporal Correlation
Figure 2 for CorrNet+: Sign Language Recognition and Translation via Spatial-Temporal Correlation
Figure 3 for CorrNet+: Sign Language Recognition and Translation via Spatial-Temporal Correlation
Figure 4 for CorrNet+: Sign Language Recognition and Translation via Spatial-Temporal Correlation
Viaarxiv icon

Elastic Multi-Gradient Descent for Parallel Continual Learning

Add code
Jan 02, 2024
Viaarxiv icon