Large AI models, or foundation models, are models recently emerging with massive scales
both parameter-wise and data-wise, the magnitudes of which can reach beyond billions …

Incorporating human feedback has been shown to be crucial to align text generated by large
language models to human preferences. We hypothesize that state-of-the-art instructional …

Current machine learning models for vision are often highly specialized and limited to a
single modality and task. In contrast, recent large language models exhibit a wide range of …

Recently, a chat generative pre-trained transformer (ChatGPT) attracts widespread attention
in the academies and industries because of its powerful conversational ability with human …

Existing automatic evaluation on text-to-image synthesis can only provide an image-text
matching score, without considering the object-level compositionality, which results in poor …

Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning
(RL) that learns from human feedback instead of relying on an engineered reward function …

Recent advances in machine learning have shown that Reinforcement Learning from
Human Feedback (RLHF) can improve machine learning models and align them with …

Deep learning models are often used with some downstream task. Models solely trained to
achieve accurate predictions may struggle to perform well on the desired downstream tasks …

Neural captioners are typically trained to mimic human-generated references without
optimizing for any specific communication goal, leading to problems such as the generation …

The automatic co-speech gesture generation draws much attention in computer animation.
Previous works designed network structures on individual datasets, which resulted in a lack …