Picture for Yannis Panagakis

Yannis Panagakis

Enabling Local Editing in Diffusion Models by Joint and Individual Component Analysis

Add code
Sep 02, 2024
Viaarxiv icon

Scale Equivariant Graph Metanetworks

Add code
Jun 15, 2024
Viaarxiv icon

Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses

Add code
May 28, 2024
Viaarxiv icon

Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization

Add code
Feb 19, 2024
Viaarxiv icon

Latent Alignment with Deep Set EEG Decoders

Add code
Nov 29, 2023
Viaarxiv icon

Locality-preserving Directions for Interpreting the Latent Space of Satellite Image GANs

Add code
Sep 26, 2023
Viaarxiv icon

Investigating Personalization Methods in Text to Music Generation

Add code
Sep 20, 2023
Viaarxiv icon

Audio-visual video-to-speech synthesis with synthesized input audio

Add code
Jul 31, 2023
Viaarxiv icon

Large-scale unsupervised audio pre-training for video-to-speech synthesis

Add code
Jun 27, 2023
Viaarxiv icon

Parts of Speech-Grounded Subspaces in Vision-Language Models

Add code
May 23, 2023
Figure 1 for Parts of Speech-Grounded Subspaces in Vision-Language Models
Figure 2 for Parts of Speech-Grounded Subspaces in Vision-Language Models
Figure 3 for Parts of Speech-Grounded Subspaces in Vision-Language Models
Figure 4 for Parts of Speech-Grounded Subspaces in Vision-Language Models
Viaarxiv icon