· ai
Improved Baselines with Momentum Contrastive Learning
Overview Teaching computers to recognize patterns without labeled data—known as unsupervised learning—has become more accessible thanks to simple tweaks to the...
-
- · ai
[Paper] Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing
Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level re...
- · ai
[Paper] Re-Depth Anything: Test-Time Depth Refinement via Self-Supervised Re-lighting
Monocular depth estimation remains challenging as recent foundation models, such as Depth Anything V2 (DA-V2), struggle with real-world images that are far from...
- · ai
[Paper] Dexterous World Models
Recent progress in 3D reconstruction has made it easy to create realistic digital twins from everyday environments. However, current digital twins remain largel...
- · ai
[Paper] Adversarial Robustness of Vision in Open Foundation Models
With the increase in deep learning, it becomes increasingly difficult to understand the model in which AI systems can identify objects. Thus, an adversary could...
- · ai
[Paper] Diffusion Forcing for Multi-Agent Interaction Sequence Modeling
Understanding and generating multi-person interactions is a fundamental challenge with broad implications for robotics and social computing. While humans natura...
- · ai
[Paper] RadarGen: Automotive Radar Point Cloud Generation from Cameras
We present RadarGen, a diffusion model for synthesizing realistic automotive radar point clouds from multi-view camera imagery. RadarGen adapts efficient image-...
- · ai
[Paper] Keypoint Counting Classifiers: Turning Vision Transformers into Self-Explainable Models Without Training
Current approaches for designing self-explainable models (SEMs) require complicated training procedures and specific architectures which makes them impractical....
- · ai
[Paper] Visually Prompted Benchmarks Are Surprisingly Fragile
A key challenge in evaluating VLMs is testing models' ability to analyze visual content independently from their textual priors. Recent benchmarks such as BLINK...
- · ai
[Paper] InSPECT: Invariant Spectral Features Preservation of Diffusion Models
Modern diffusion models (DMs) have achieved state-of-the-art image generation. However, the fundamental design choice of diffusing data all the way to white noi...
- · ai
[Paper] Interpretable Plant Leaf Disease Detection Using Attention-Enhanced CNN
Plant diseases pose a significant threat to global food security, necessitating accurate and interpretable disease detection methods. This study introduces an i...
- · ai
[Paper] InfSplign: Inference-Time Spatial Alignment of Text-to-Image Diffusion Models
Text-to-image (T2I) diffusion models generate high-quality images but often fail to capture the spatial relations specified in text prompts. This limitation can...