Picture for Liang Lin

Liang Lin

Mirror Gradient: Towards Robust Multimodal Recommender Systems via Exploring Flat Local Minima

Add code
Feb 17, 2024
Viaarxiv icon

Multimodal Embodied Interactive Agent for Cafe Scene

Add code
Feb 01, 2024
Viaarxiv icon

TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts

Add code
Jan 26, 2024
Figure 1 for TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts
Figure 2 for TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts
Figure 3 for TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts
Figure 4 for TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts
Viaarxiv icon

Adaptive Global-Local Representation Learning and Selection for Cross-Domain Facial Expression Recognition

Add code
Jan 20, 2024
Viaarxiv icon

Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition

Add code
Jan 13, 2024
Figure 1 for Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition
Figure 2 for Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition
Figure 3 for Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition
Figure 4 for Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition
Viaarxiv icon

MirrorDiffusion: Stabilizing Diffusion Process in Zero-shot Image Translation by Prompts Redescription and Beyond

Add code
Jan 06, 2024
Viaarxiv icon

Credible Teacher for Semi-Supervised Object Detection in Open Scene

Add code
Jan 03, 2024
Figure 1 for Credible Teacher for Semi-Supervised Object Detection in Open Scene
Figure 2 for Credible Teacher for Semi-Supervised Object Detection in Open Scene
Figure 3 for Credible Teacher for Semi-Supervised Object Detection in Open Scene
Viaarxiv icon

Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach

Add code
Dec 15, 2023
Figure 1 for Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach
Figure 2 for Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach
Figure 3 for Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach
Figure 4 for Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach
Viaarxiv icon

Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation

Add code
Dec 06, 2023
Figure 1 for Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation
Figure 2 for Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation
Figure 3 for Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation
Figure 4 for Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation
Viaarxiv icon

SQLNet: Scale-Modulated Query and Localization Network for Few-Shot Class-Agnostic Counting

Add code
Nov 16, 2023
Viaarxiv icon