Device-Independent-Quantum-Randomness-Enhanced Zero-Knowledge Proof

Polynomial-Time Algorithms for Prime Factorization and Discrete Logarithms on a Quantum Computer

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

we notice that starting from a code training model
is a better choice compared to a general LLM.

Furthermore, we observe the math training also
improves model capability, indicating it does
not only enhance the model's mathematical abilities
but also amplify general reasoning capabilities.

Although training on arXiv papers is common, especially in
many math-related papers, it brings no notable improvements
on all mathematical benchmarks adopted in this paper.

Math Pre-Training

To filter out low-quality mathematical content,
we rank the collected pages according to their
scores predicted by the fastText model,
and only preserve the top-ranking ones.

Mathematical Problem Solving with Tool Use 这段写得很简陋~

Supervised Fine-Tuning

Reinforcement Learning

Discussion, Conclusion, and Limitation