MLLM-as-a-Judge for Image Safety without Human Labeling Paper • 2501.00192 • Published Dec 31, 2024 • 31
Perception Encoder: The best visual embeddings are not at the output of the network Paper • 2504.13181 • Published 21 days ago • 34
PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding Paper • 2504.13180 • Published 21 days ago • 17