DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training.

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning.

Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique.

The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs.

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs.

Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step.