Training Transformer Models by Wavelet Losses Improves Quantitative and Visual Performance in Single Image Super-Resolution
Paper • 2404.11273 • Published • 1
Dan Jacobellis PRO
danjacobellis
AI & ML interests
Signal processing, information theory, data compression
Recent Activity
upvoted a paper 1 day ago
ViT-5: Vision Transformers for The Mid-2020s upvoted a paper 1 day ago
Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and
ResolutionOrganizations
upvoted 5
papers 1 day ago
ViT-5: Vision Transformers for The Mid-2020s
Paper • 2602.08071 • Published • 2
Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
Paper • 2307.06304 • Published • 36
FlexiViT: One Model for All Patch Sizes
Paper • 2212.08013 • Published • 2
High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator
Paper • 2510.10693 • Published • 1
updated a
model 7 days ago
published a
model 7 days ago
upvoted 2
papers 12 days ago
upvoted 2
papers 15 days ago
upvoted a paper 16 days ago
upvoted 5
papers 18 days ago
One View Is Enough! Monocular Training for In-the-Wild Novel View Generation
Paper • 2603.23488 • Published • 5
Terminal Agents Suffice for Enterprise Automation
Paper • 2604.00073 • Published • 96
Hyperagents
Paper • 2603.19461 • Published • 50
ADD for Multi-Bit Image Watermarking
Paper • 2604.11491 • Published • 3
Domain-Specific Latent Representations Improve the Fidelity of Diffusion-Based Medical Image Super-Resolution
Paper • 2604.12152 • Published • 3
upvoted 3
papers 20 days ago