Benchmark
Flickr8k
An image captioning dataset in which each image is paired with five human-written captions, used to evaluate the ability to generate natural language descriptions.
Timeline (last 90 days)
Nov 2
On the image captioning task (Flickr8k), Latent-Lens improves by +16.5 over the text baseline with the same LoRA budget and by +18.8 over the frozen version.
Unverified50%