๐ŸŽ“How I Study AIHISA
๐Ÿ“–Read
๐Ÿ“„Papers๐Ÿ“ฐBlogs๐ŸŽฌCourses
๐Ÿ’กLearn
๐Ÿ›ค๏ธPaths๐Ÿ“šTopics๐Ÿ’กConcepts๐ŸŽดShorts
๐ŸŽฏPractice
๐Ÿ“Daily Log๐ŸŽฏPrompts๐Ÿง Review
SearchSettings
How I Study AI - Learn AI Papers & Lectures the Easy Way

Papers2

AllBeginnerIntermediateAdvanced
All SourcesarXiv
#cosine similarity loss

FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment

Intermediate
Han Zhao, Jingbo Wang et al.Feb 19arXiv

Robots learn better when they predict short, meaningful summaries of future images instead of drawing every pixel of the future scene.

#world modeling#vision-language-action (VLA)#diffusion policy

Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better

Intermediate
Ji Zhao, Yufei Gu et al.Feb 5arXiv

Big idea: use a small, already-trained model to help a bigger model learn good habits early, so the big one trains faster and ends up smarter.

#Late-to-Early Training#LLM pretraining acceleration#representation alignment