Posted 2025-03-10tech article6 minutes read (About 950 words)Diffusion Language Model: The Rise of a New Paradigm for LLM? A Revolutionary Breakthrough That Overturns Autoregressive LLM12345678Literature:- Simple and Effective Masked Diffusion Language Models- Score-Based Generative Modeling through Stochastic Differential Equations- Sequence-to-Sequence Denoising DiffusionImage source:- Diffusion Models: A Comprehensive Survey of Methods and Applications- https://s-sahoo.com/mdlm/- https://www.inceptionlabs.ai/newsRead more
Posted 2025-03-07tech article8 minutes read (About 1219 words)GRPO: The Key Engine Driving DeepSeek's Exceptional Performance12Paper: DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language ModelsSource: https://github.com/deepseek-ai/DeepSeek-R1 & https://arxiv.org/pdf/2402.03300Read more
2025-05-28Learn Self-Adaptation Thinking through RL and switch thinking modes flexibly according to scenariosPaper / Reinforcement learning
2025-03-10Diffusion Language Model: The Rise of a New Paradigm for LLM? A Revolutionary Breakthrough That Overturns Autoregressive LLMtech article