Picture for Grace Luo

Grace Luo

Task Vectors are Cross-Modal

Add code
Oct 29, 2024
Viaarxiv icon

Readout Guidance: Learning Control from Diffusion Features

Add code
Dec 04, 2023
Viaarxiv icon

Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence

Add code
May 23, 2023
Figure 1 for Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence
Figure 2 for Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence
Figure 3 for Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence
Figure 4 for Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence
Viaarxiv icon

Shape-Guided Diffusion with Inside-Outside Attention

Add code
Dec 01, 2022
Viaarxiv icon

Focus! Relevant and Sufficient Context Selection for News Image Captioning

Add code
Dec 01, 2022
Viaarxiv icon

G^3: Geolocation via Guidebook Grounding

Add code
Nov 28, 2022
Viaarxiv icon

Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation

Add code
Dec 16, 2021
Figure 1 for Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation
Figure 2 for Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation
Figure 3 for Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation
Figure 4 for Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation
Viaarxiv icon

NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media

Add code
Apr 13, 2021
Figure 1 for NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media
Figure 2 for NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media
Figure 3 for NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media
Figure 4 for NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media
Viaarxiv icon