Picture for Liang Lin

Liang Lin

DAGSM: Disentangled Avatar Generation with GS-enhanced Mesh

Add code
Nov 20, 2024
Figure 1 for DAGSM: Disentangled Avatar Generation with GS-enhanced Mesh
Figure 2 for DAGSM: Disentangled Avatar Generation with GS-enhanced Mesh
Figure 3 for DAGSM: Disentangled Avatar Generation with GS-enhanced Mesh
Figure 4 for DAGSM: Disentangled Avatar Generation with GS-enhanced Mesh
Viaarxiv icon

Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review

Add code
Nov 15, 2024
Figure 1 for Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review
Figure 2 for Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review
Figure 3 for Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review
Figure 4 for Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review
Viaarxiv icon

Integration of Communication and Computational Imaging

Add code
Oct 29, 2024
Figure 1 for Integration of Communication and Computational Imaging
Figure 2 for Integration of Communication and Computational Imaging
Figure 3 for Integration of Communication and Computational Imaging
Figure 4 for Integration of Communication and Computational Imaging
Viaarxiv icon

All Robots in One: A New Standard and Unified Dataset for Versatile, General-Purpose Embodied Agents

Add code
Aug 20, 2024
Figure 1 for All Robots in One: A New Standard and Unified Dataset for Versatile, General-Purpose Embodied Agents
Figure 2 for All Robots in One: A New Standard and Unified Dataset for Versatile, General-Purpose Embodied Agents
Figure 3 for All Robots in One: A New Standard and Unified Dataset for Versatile, General-Purpose Embodied Agents
Figure 4 for All Robots in One: A New Standard and Unified Dataset for Versatile, General-Purpose Embodied Agents
Viaarxiv icon

Style-Preserving Lip Sync via Audio-Aware Style Reference

Add code
Aug 10, 2024
Viaarxiv icon

High-fidelity and Lip-synced Talking Face Synthesis via Landmark-based Diffusion Model

Add code
Aug 10, 2024
Figure 1 for High-fidelity and Lip-synced Talking Face Synthesis via Landmark-based Diffusion Model
Figure 2 for High-fidelity and Lip-synced Talking Face Synthesis via Landmark-based Diffusion Model
Figure 3 for High-fidelity and Lip-synced Talking Face Synthesis via Landmark-based Diffusion Model
Figure 4 for High-fidelity and Lip-synced Talking Face Synthesis via Landmark-based Diffusion Model
Viaarxiv icon

Improving Network Interpretability via Explanation Consistency Evaluation

Add code
Aug 08, 2024
Figure 1 for Improving Network Interpretability via Explanation Consistency Evaluation
Figure 2 for Improving Network Interpretability via Explanation Consistency Evaluation
Figure 3 for Improving Network Interpretability via Explanation Consistency Evaluation
Figure 4 for Improving Network Interpretability via Explanation Consistency Evaluation
Viaarxiv icon

VideoQA in the Era of LLMs: An Empirical Study

Add code
Aug 08, 2024
Figure 1 for VideoQA in the Era of LLMs: An Empirical Study
Figure 2 for VideoQA in the Era of LLMs: An Empirical Study
Figure 3 for VideoQA in the Era of LLMs: An Empirical Study
Figure 4 for VideoQA in the Era of LLMs: An Empirical Study
Viaarxiv icon

MarvelOVD: Marrying Object Recognition and Vision-Language Models for Robust Open-Vocabulary Object Detection

Add code
Jul 31, 2024
Viaarxiv icon

Cool-Fusion: Fuse Large Language Models without Training

Add code
Jul 29, 2024
Figure 1 for Cool-Fusion: Fuse Large Language Models without Training
Figure 2 for Cool-Fusion: Fuse Large Language Models without Training
Figure 3 for Cool-Fusion: Fuse Large Language Models without Training
Figure 4 for Cool-Fusion: Fuse Large Language Models without Training
Viaarxiv icon