DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Paper
•
2405.04434
•
Published
•
19
foundational models
Note MLA
-
Titans: Learning to Memorize at Test Time
Paper • 2501.00663 • Published • 22 -
Transformer^2: Self-adaptive LLMs
Paper • 2501.06252 • Published • 54 -
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Paper • 2502.11089 • Published • 149 -
Trust Region Policy Optimization
Paper • 1502.05477 • Published -
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Paper • 2402.03300 • Published • 110