OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
Paper
• 2602.05400 • Published
• 344
LLM related
-
-
PaperBanana: Automating Academic Illustration for AI Scientists
Paper • 2601.23265 • Published • 214 -
FASA: Frequency-aware Sparse Attention
Paper • 2602.03152 • Published • 150 -
mHC: Manifold-Constrained Hyper-Connections
Paper • 2512.24880 • Published • 313 -
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Paper • 2601.05242 • Published • 229