ViT-B-32
PulseAugur coverage of ViT-B-32 — every cluster mentioning ViT-B-32 across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New system, PeakPatch, recovers negation signal in CLIP models
Researchers have developed PeakPatch, a novel post-hoc system designed to address the negation blindness in contrastive vision-language models like CLIP. This system works by intercepting intermediate features from the …
-
New CT-Merging algorithm efficiently combines LoRA adapters for multi-task models
Researchers have introduced CT-Merging, a novel algorithm designed to efficiently combine multiple LoRA adapters into a single multi-task adapter. This method addresses the challenge of storing and selecting individual …
-
New framework enables zero-shot captioning of Indonesian traditional clothing
Researchers have developed Custom ZeroCLIP, a novel retrieval-augmented vision-language framework designed for the zero-shot captioning of traditional Indonesian clothing. This system utilizes a combination of CLIP and …
-
AI models show strong breast density prediction from ultrasounds, generalize well
Researchers externally validated three deep learning models—DenseNet121, ViT-B/32, and ResNet50—for predicting breast density from ultrasound images. The models demonstrated strong performance, particularly in extremely…
-
I scraped 1.94M Airbnb photos for opium dens, pet cameos, and messy kitchens
Researchers utilized the Burla parallel processing library to analyze 1.94 million Airbnb photos and reviews across 119 cities. They employed CLIP for initial image scoring and Claude Haiku Vision for detailed verificat…