Large language models (LLMs) are considered a crucial technology for advancing intelligent education since they exhibit the potential for an in-depth understanding of teaching scenarios and providing students with personalized guidance. Nonetheless, current LLM-based application in personalized teaching predominantly follows a "Question-Answering" paradigm, where students are passively provided with answers and explanations. In this paper, we propose SocraticLM, which achieves a Socratic "Thought-Provoking" teaching paradigm that fulfills the role of a real classroom teacher in actively engaging students in the thought

Reinforcement learning (RL) algorithms are typically based on optimizing a Markov Decision Process (MDP) using the optimal Bellman equation.

INDICT: a new framework that empowers LLMs with Internal Dialogues of Critiques for both safety and helpfulness guidance.

We present a novel approach for test-time adaptation via online self-training, consisting of two components.

Example of an abstract, non-spatial domain called'Stretchy Blob', a 2D Gaussian that can either stretch or shrink along two axes.

Look-up tables(LUTs)-based methods have recently shown enormous potential in image restoration tasks, which are capable of significantly accelerating the inference. However, the size of LUT exhibits exponential growth with the convolution kernel size, creating a storage bottleneck for its broader application on edge devices.

While neural networks can enjoy an outstanding flexibility and exhibit unprecedented performance, the mechanism behind their behavior is still not well-understood.

In this paper, we take another approach to diffusion model acceleration.