OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
Paper
• 2602.05400 • Published
• 347
XMzhang
amax1
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 30 days ago
Less LLM, More Documents: Searching for Improved RAG upvoted a paper 30 days ago
Accelerating Vision Transformers with Adaptive Patch Sizes Organizations
