Post
1467
๐ฆ๐ต๐ผ๐๐จ๐: ๐ฎ ๐๐บ๐ฎ๐น๐น ๐ฒ๐ป๐ฑ-๐๐ผ-๐ฒ๐ป๐ฑ ๐ฎ๐ด๐ฒ๐ป๐ ๐๐ต๐ฎ๐ ๐ฐ๐ฎ๐ป ๐ป๐ฎ๐๐ถ๐ด๐ฎ๐๐ฒ ๐ฎ๐ป๐ ๐จ๐ ๐ฎ๐ป๐ฑ ๐ผ๐๐๐ฝ๐ฒ๐ฟ๐ณ๐ผ๐ฟ๐บ๐ ๐บ๐๐ฐ๐ต ๐ฏ๐ถ๐ด๐ด๐ฒ๐ฟ ๐๐๐๐๐ฒ๐บ๐! ๐ฒ
A team from NUS and Microsoft just released an agent that can act on any UI (Desktop, Android, Web) without needing additional text information. It works extremely well : they applied their method on a tiny Qwen2-VL-2B, and they managed to beat methods that use either much more powerful vision models (like GPT-4V) without using any additional info (e.g. leveraging the DOM of a webpage) like previous methods did ! ๐๐
They started from the idea that most existing methods rely heavily on text, which makes them less generalizable, while letting aside rich UI structure that user actually rely on when navigating this interfaces.
โ๏ธ They put several good ideas to work:
๐ก Simplify screenshots to the max:
They prune a lot the heavy visual content of UI screenshots, by removing cloned image patches (like any vast patch of the same color will be reduced to a small patch, while maintaining positional embeddings), then group patches from the same GUI elements together to simplify even further
๐ก Build a truly generalist dataset:
To train a general UI agent, you need trajectories from each possible UI, and express them in a common language. Authors merge datasets like OmniAct for Desktop, Mind2Web for websites, AMEX for Android trajectories to create a high-quality and diverse dataset.
โก๏ธ Nice results ensued:
They fine-tune a tiny Qwen-2-VL-2B on their method, and it reaches SOTA on several task (element identification, web navigation), even beating methods that either use additional info from the DOM or use much bigger VLMS like GPT-4v! ๐
And performance could certainly jump with a slightly bigger vision model. Let's hope the community builds this soon! ๐
Paper added to my "Agents" collection ๐ m-ric/agents-65ba776fbd9e29f771c07d4e
A team from NUS and Microsoft just released an agent that can act on any UI (Desktop, Android, Web) without needing additional text information. It works extremely well : they applied their method on a tiny Qwen2-VL-2B, and they managed to beat methods that use either much more powerful vision models (like GPT-4V) without using any additional info (e.g. leveraging the DOM of a webpage) like previous methods did ! ๐๐
They started from the idea that most existing methods rely heavily on text, which makes them less generalizable, while letting aside rich UI structure that user actually rely on when navigating this interfaces.
โ๏ธ They put several good ideas to work:
๐ก Simplify screenshots to the max:
They prune a lot the heavy visual content of UI screenshots, by removing cloned image patches (like any vast patch of the same color will be reduced to a small patch, while maintaining positional embeddings), then group patches from the same GUI elements together to simplify even further
๐ก Build a truly generalist dataset:
To train a general UI agent, you need trajectories from each possible UI, and express them in a common language. Authors merge datasets like OmniAct for Desktop, Mind2Web for websites, AMEX for Android trajectories to create a high-quality and diverse dataset.
โก๏ธ Nice results ensued:
They fine-tune a tiny Qwen-2-VL-2B on their method, and it reaches SOTA on several task (element identification, web navigation), even beating methods that either use additional info from the DOM or use much bigger VLMS like GPT-4v! ๐
And performance could certainly jump with a slightly bigger vision model. Let's hope the community builds this soon! ๐
Paper added to my "Agents" collection ๐ m-ric/agents-65ba776fbd9e29f771c07d4e