AIThe Decoderabout 4 hours ago
Microsoft Lens: detailed captions beat model scale
1 min read
Microsoft Research released Lens, a 3.8 billion parameter text-to-image model that matches larger rivals on benchmarks. The key is 800 million detailed captions generated by GPT-4.1, replacing vague web alt-text. Code and weights are open source, proving caption quality matters more than raw scale.
Level
Hype check
Tap to vote and see what everyone thinks.
