
Joy Hsu
@joycjhsu • 3,647 subscribers
MTS @OpenAI. Incoming Assistant Professor @ImperialCollege. PhD @Stanford.
Videos

What makes a maze look like a maze? Humans can reason about infinitely many instantiations of mazes—made of candy canes, sticks, icing, yarn, etc. But VLMs often struggle to make sense of such visual abstractions. We improve VLMs' ability to interpret these abstract concepts.
Joy Hsu43,960 次观看 • 2 年前

What’s left w/ foundation models? We found that they still can't ground modular concepts across domains. We present Logic-Enhanced FMs:🤝FMs & neuro-symbolic concept learners. We learn abstractions of concepts like “left” across domains & do domain-independent reasoning w/ LLMs.
Joy Hsu54,145 次观看 • 3 年前

How can we learn 3D visual grounding with natural supervision—only looking at QA pairs, without ground truth bounding boxes or object classification labels? We inject explicit language priors, e.g., the symmetric property that A near B ⇒ B near A, in structured vision models.
Joy Hsu14,935 次观看 • 2 年前
没有更多内容可加载