Improving Region Representation Learning from Urban Imagery with Noisy Long-Caption Supervision
arxiv.org·51m
🤖AI technology
Flag this post
Animating Realism: Transferring Motion Styles with AI
dev.to·1d·
Discuss: DEV
🖼AI Picture
Flag this post
Show HN: Spine AI – Visual workspace to think across multiple AI models
app.getspine.ai·1d·
Discuss: Hacker News
🤖AI technology
Flag this post
Garbage In, Garbage Out: The Case for Better Robot Data Understanding
huggingface.co·21h·
Discuss: Hacker News
🤖AI
Flag this post
ConsistEdit: Highly Consistent and Precise Training-free Visual Editing
paperium.net·18h·
Discuss: DEV
🖼AI Picture
Flag this post
Seeing Shapes: Unveiling Neural Network Vision with Fourier Geometry by Arvind Sundararajan
dev.to·22h·
Discuss: DEV
🤖AI
Flag this post
A Second-Order Attention Mechanism For Prostate Cancer Segmentation and Detection in Bi-Parametric MRI
arxiv.org·51m
🤖AI
Flag this post
Deep Learning for Molecules and Materials
dmol.pub·20h·
Discuss: Hacker News
🤖AI
Flag this post
DiffusionUavLoc: Visually Prompted Diffusion for Cross-View UAV Localization
arxiv.org·51m
🤖AI
Flag this post
TiS-TSL: Image-Label Supervised Surgical Video Stereo Matching via Time-Switchable Teacher-Student Learning
arxiv.org·51m
🤖AI
Flag this post
BitNetMCU with CNN: >99.5% MNIST accuracy on a low-end Microcontroller
cpldcpu.com·1d
🤖AI technology
Flag this post
Time-Warping Control: Taming Complex Systems with AI
dev.to·2h·
Discuss: DEV
🤖AI technology
Flag this post
DeepEyesV2: Toward Agentic Multimodal Model
arxiv.org·1d
🤖AI
Flag this post
Lesson 3 - Scene graph and transform
infinitecanvas.cc·14h
🖼AI Picture
Flag this post
ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction with Fewer Primitives
arxiv.org·51m
🖼AI Picture
Flag this post
A Mandibular Defect Dataset for Autonomous Reconstruction Planning in Oral and Maxillofacial Surgery
nature.com·16h
🤖AI technology
Flag this post
Convolutional Fully-Connected Capsule Network (CFC-CapsNet): A Novel and Fast Capsule Network
arxiv.org·51m
🖼AI Picture
Flag this post
FoCLIP: A Feature-Space Misalignment Framework for CLIP-Based Image Manipulation and Detection
arxiv.org·51m
🖼AI Picture
Flag this post