Flickr30k

anchor

Findings

• IC-1496A single frozen transformer block from LLaMA-7B consistently improves performance across diverse visual tasks when appended to existing visual encoders [eval]
• IC-280CLIP, OpenCLIP, and SigLIP exhibit intra-modal misalignment: intra-modal similarity comparisons are suboptimal for image-to-image and text-to-text retrieval [eval]