taesiri PRO
taesiri
AI & ML interests
AGI ... one linear layer at a time
Recent Activity
upvoted a paper about 3 hours ago
ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition submitted a paper about 6 hours ago
PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models upvoted a paper about 6 hours ago
Visual prompt engineering for video modelsOrganizations
The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification
-
Zoom is what you need: An empirical study of the power of zoom and spatial biases in image classification
Paper • 2304.05538 • Published • 2 -
ImageNet-Hard Browser
🔍5Browse and filter ImageNet-Hard dataset images
-
taesiri/imagenet-hard
Viewer • Updated • 10.5k • 188 • 12 -
taesiri/imagenet-hard-4K
Viewer • Updated • 9.6k • 272 • 7
ZeroBench
Automated ArXiv Question Answering with LLMs
The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification
-
Zoom is what you need: An empirical study of the power of zoom and spatial biases in image classification
Paper • 2304.05538 • Published • 2 -
ImageNet-Hard Browser
🔍5Browse and filter ImageNet-Hard dataset images
-
taesiri/imagenet-hard
Viewer • Updated • 10.5k • 188 • 12 -
taesiri/imagenet-hard-4K
Viewer • Updated • 9.6k • 272 • 7
ZeroBench