Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs
Paper • 2603.16932 • Published • 84
Moshe kimhi
Kimhi
AI & ML interests
Computer vision, semi supervised learning, compressed models, noisy labels
Recent Activity
liked a dataset 2 days ago
Kimhi/hardness_data_mix liked a model 2 days ago
Kimhi/smolvlm-res-gate authored a paper 5 days ago
Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMsOrganizations
authored a
paper 5 days ago
authored 6
papers 6 days ago
Benchmarking Label Noise in Instance Segmentation: Spatial Noise Matters
Paper • 2406.10891 • Published • 1
Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods
Paper • 2410.17222 • Published • 3
Hysteresis Activation Function for Efficient Inference
Paper • 2411.10573 • Published • 1
$\mathbf{R}^3$: Reconstruction, Raw, and Rain: Deraining Directly in the Bayer Domain
Paper • 2509.24022 • Published • 1
CARES: Context-Aware Resolution Selector for VLMs
Paper • 2510.19496 • Published • 9
WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIP
Paper • 2509.21153 • Published • 1