Diffusion LLM can be understood as transferring some core ideas of the "diffusion model" to the language model, generating text in a gradual denoising...
Physical AI typically refers to enabling AI to not only understand text, images, and speech, but also enter the physical world to perceive, predict, p...
Sparse attention can be simply understood as: instead of having each token look at all tokens, selectively look at only a part of them. This term come...
Synthetic data does not refer to "random batches of fake data", but training data created by simulation, generative models, rule engines, or programma...
Test-Time Scaling can be understood as giving the model more inference budget, more attempts, or more thinking space when it actually answers a questi...
RLVR typically stands for Reinforcement Learning with Verifiable Rewards. The core reason is not that RLHF has failed, but that with the rise of reaso...