Picture for Xiaoli Wang

Xiaoli Wang

Rethinking Multi-view Representation Learning via Distilled Disentangling

Add code
Mar 29, 2024
Figure 1 for Rethinking Multi-view Representation Learning via Distilled Disentangling
Figure 2 for Rethinking Multi-view Representation Learning via Distilled Disentangling
Figure 3 for Rethinking Multi-view Representation Learning via Distilled Disentangling
Figure 4 for Rethinking Multi-view Representation Learning via Distilled Disentangling
Viaarxiv icon

Fine-tuning Large Language Models for Domain-specific Machine Translation

Add code
Feb 23, 2024
Viaarxiv icon

BESTMVQA: A Benchmark Evaluation System for Medical Visual Question Answering

Add code
Dec 13, 2023
Viaarxiv icon

Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering

Add code
Sep 09, 2023
Figure 1 for Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering
Figure 2 for Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering
Figure 3 for Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering
Figure 4 for Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering
Viaarxiv icon

Disentangling Multi-view Representations Beyond Inductive Bias

Add code
Aug 04, 2023
Figure 1 for Disentangling Multi-view Representations Beyond Inductive Bias
Figure 2 for Disentangling Multi-view Representations Beyond Inductive Bias
Figure 3 for Disentangling Multi-view Representations Beyond Inductive Bias
Figure 4 for Disentangling Multi-view Representations Beyond Inductive Bias
Viaarxiv icon

ConKI: Contrastive Knowledge Injection for Multimodal Sentiment Analysis

Add code
Jun 27, 2023
Figure 1 for ConKI: Contrastive Knowledge Injection for Multimodal Sentiment Analysis
Figure 2 for ConKI: Contrastive Knowledge Injection for Multimodal Sentiment Analysis
Figure 3 for ConKI: Contrastive Knowledge Injection for Multimodal Sentiment Analysis
Figure 4 for ConKI: Contrastive Knowledge Injection for Multimodal Sentiment Analysis
Viaarxiv icon

A Sequence-to-Sequence&Set Model for Text-to-Table Generation

Add code
May 31, 2023
Figure 1 for A Sequence-to-Sequence&Set Model for Text-to-Table Generation
Figure 2 for A Sequence-to-Sequence&Set Model for Text-to-Table Generation
Figure 3 for A Sequence-to-Sequence&Set Model for Text-to-Table Generation
Figure 4 for A Sequence-to-Sequence&Set Model for Text-to-Table Generation
Viaarxiv icon

PRIMP: PRobabilistically-Informed Motion Primitives for Efficient Affordance Learning from Demonstration

Add code
May 25, 2023
Figure 1 for PRIMP: PRobabilistically-Informed Motion Primitives for Efficient Affordance Learning from Demonstration
Figure 2 for PRIMP: PRobabilistically-Informed Motion Primitives for Efficient Affordance Learning from Demonstration
Figure 3 for PRIMP: PRobabilistically-Informed Motion Primitives for Efficient Affordance Learning from Demonstration
Figure 4 for PRIMP: PRobabilistically-Informed Motion Primitives for Efficient Affordance Learning from Demonstration
Viaarxiv icon

LA3: Efficient Label-Aware AutoAugment

Add code
Apr 20, 2023
Viaarxiv icon

Search-Map-Search: A Frame Selection Paradigm for Action Recognition

Add code
Apr 20, 2023
Figure 1 for Search-Map-Search: A Frame Selection Paradigm for Action Recognition
Figure 2 for Search-Map-Search: A Frame Selection Paradigm for Action Recognition
Figure 3 for Search-Map-Search: A Frame Selection Paradigm for Action Recognition
Figure 4 for Search-Map-Search: A Frame Selection Paradigm for Action Recognition
Viaarxiv icon