Exposing Blindspots: Cultural Bias Evaluation in Generative Image Models
Paper • 2510.20042 • Published • 2
AI & ML interests
None defined yet.
zhixuan2
authored a
paper 7 months ago
zhixuan2
submitted a
paper to Daily Papers 8 months ago
zhixuan2
authored 3
papers 8 months ago
StyleCLIPDraw: Coupling Content and Style in Text-to-Drawing Translation
Paper • 2202.12362 • Published • 1
MOSAIC: Generating Consistent, Privacy-Preserving Scenes from Multiple Depth Views in Multi-Room Environments
Paper • 2503.13816 • Published
SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generation
Paper • 2401.08053 • Published
turkeyju
authored a
paper 9 months ago
turkeyju
authored 6
papers over 1 year ago
PartImageNet: A Large, High-Quality Dataset of Parts
Paper • 2112.00933 • Published
A Simple Video Segmenter by Tracking Objects Along Axial Trajectories
Paper • 2311.18537 • Published
ReVision: High-Quality, Low-Cost Video Generation with Explicit 3D Physics Modeling for Complex Motion and Interaction
Paper • 2504.21855 • Published • 13
Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation
Paper • 2502.20388 • Published • 16
TransMix: Attend to Mix for Vision Transformers
Paper • 2111.09833 • Published
FlowTok: Flowing Seamlessly Across Text and Image Tokens
Paper • 2503.10772 • Published • 19
turkeyju
authored 2
papers almost 2 years ago
turkeyju
authored 4
papers about 2 years ago
Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP
Paper • 2308.02487 • Published • 14
Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models
Paper • 2406.09416 • Published • 29
LLaVolta: Efficient Multi-modal Models via Stage-wise Visual Context Compression
Paper • 2406.20092 • Published
Randomized Autoregressive Visual Generation
Paper • 2411.00776 • Published • 19