Statistical Rejection Sampling Improves Preference Optimization
Paper
•
2309.06657
•
Published
•
14
papers
-
-
In-Context Learning Creates Task Vectors
Paper • 2310.15916 • Published • 43 -
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Paper • 2404.08801 • Published • 68 -
Make Your LLM Fully Utilize the Context
Paper • 2404.16811 • Published • 55 -
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
Paper • 2505.04588 • Published • 64 -
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Paper • 2505.03335 • Published • 169 -
Practical Efficiency of Muon for Pretraining
Paper • 2505.02222 • Published • 37