A brief overview of ChatGPT: The history, status quo and potential future development
ChatGPT, an artificial intelligence generated content (AIGC) model developed by OpenAI,
has attracted world-wide attention for its capability of dealing with challenging language …
has attracted world-wide attention for its capability of dealing with challenging language …
Ai alignment: A comprehensive survey
AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …
Augmented language models: a survey
This survey reviews works in which language models (LMs) are augmented with reasoning
skills and the ability to use tools. The former is defined as decomposing a potentially …
skills and the ability to use tools. The former is defined as decomposing a potentially …
Imagereward: Learning and evaluating human preferences for text-to-image generation
We present a comprehensive solution to learn and improve text-to-image models from
human preference feedback. To begin with, we build ImageReward---the first general …
human preference feedback. To begin with, we build ImageReward---the first general …
Open problems and fundamental limitations of reinforcement learning from human feedback
Reinforcement learning from human feedback (RLHF) is a technique for training AI systems
to align with human goals. RLHF has emerged as the central method used to finetune state …
to align with human goals. RLHF has emerged as the central method used to finetune state …
Principled reinforcement learning with human feedback from pairwise or k-wise comparisons
We provide a theoretical framework for Reinforcement Learning with Human Feedback
(RLHF). We show that when the underlying true reward is linear, under both Bradley-Terry …
(RLHF). We show that when the underlying true reward is linear, under both Bradley-Terry …
Preference ranking optimization for human alignment
Large language models (LLMs) often contain misleading content, emphasizing the need to
align them with human values to ensure secure AI systems. Reinforcement learning from …
align them with human values to ensure secure AI systems. Reinforcement learning from …
Aligning text-to-image models using human feedback
Deep generative models have shown impressive results in text-to-image synthesis.
However, current text-to-image models often generate images that are inadequately aligned …
However, current text-to-image models often generate images that are inadequately aligned …
What matters in learning from offline human demonstrations for robot manipulation
Imitating human demonstrations is a promising approach to endow robots with various
manipulation capabilities. While recent advances have been made in imitation learning and …
manipulation capabilities. While recent advances have been made in imitation learning and …
Curriculum learning for reinforcement learning domains: A framework and survey
Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks
in which the agent has only limited environmental feedback. Despite many advances over …
in which the agent has only limited environmental feedback. Despite many advances over …