The study of dreams has been central to understanding human
(un)consciousness, cognition, and culture for centuries. Analyzing dreams
quantitatively depends on labor-intensive, manual annotation of dream
narratives. We automate this process through a natural language
sequence-to-sequence generation framework. This paper presents the first study
on character and emotion detection in the English portion of the open DreamBank
corpus of dream narratives. Our results show that language models can
effectively address this complex task. To get insight into prediction
performance, we evaluate the impact of model size, prediction order of
characters, and the consideration of proper names and character traits. We
compare our approach with a large language model using in-context learning. Our
supervised models perform better while having 28 times fewer parameters. Our
model and its generated annotations are made publicly available.

通过自然语言序列到序列生成框架，本研究首次在开放的 DreamBank 梦境叙述语料库的英文部分中对字符和情感进行检测，结果显示语言模型能够有效应对这一复杂任务。

梦境叙事中的字符和情绪检测的序列到序列语言模型

Sequence-to-Sequence Language Models for Character and Emotion Detection  in Dream Narratives

The Overfitted Brain hypothesis suggests dreams happen to allow
generalization in the human brain. Here, we ask if the same is true for
reinforcement learning agents as well. Given limited experience in a real
environment, we use imagination-based reinforcement learning to train a policy
on dream-like episodes, where non-imaginative, predicted trajectories are
modified through generative augmentations. Experiments on four ProcGen
environments show that, compared to classic imagination and offline training on
collected experience, our method can reach a higher level of generalization
when dealing with sparsely rewarded environments.

通过基于想象力的强化学习，使用梦境般的片段来训练策略，并通过生成扩增对非想象力、预测轨迹进行修改，实验表明与经典的想象力和脱机训练相比，我们的方法在处理收益稀疏环境时可以达到更高水平的泛化。

智能体会做电子绵羊的梦吗？通过生成学习提高强化学习的泛化能力

Do Agents Dream of Electric Sheep?: Improving Generalization in  Reinforcement Learning through Generative Learning

Human emotions are essentially molded by lived experiences, from which we
construct personalised meaning. The engagement in such meaning-making process
has been practiced as an intervention in various psychotherapies to promote
wellness. Nevertheless, to support recollecting and recounting lived
experiences in everyday life remains under explored in HCI. It also remains
unknown how technologies such as generative AI models can facilitate the
meaning making process, and ultimately support affective mindfulness. In this
paper we present Metamorpheus, an affective interface that engages users in a
creative visual storytelling of emotional experiences during dreams.
Metamorpheus arranges the storyline based on a dream's emotional arc, and
provokes self-reflection through the creation of metaphorical images and text
depictions. The system provides metaphor suggestions, and generates visual
metaphors and text depictions using generative AI models, while users can apply
generations to recolour and re-arrange the interface to be visually affective.
Our experience-centred evaluation manifests that, by interacting with
Metamorpheus, users can recall their dreams in vivid detail, through which they
relive and reflect upon their experiences in a meaningful way.

通过使用生成型人工智能模型的情感界面，用户可以回忆和反思他们的梦境体验，进而以有意义的方式重新体验和反思自己的经历。

变形者：通过隐喻性视觉叙事进行互动化、情感化和创造性的梦境叙事

Metamorpheus: Interactive, Affective, and Creative Dream Narration  Through Metaphorical Visual Storytelling

The continuity hypothesis of dreams suggests that the content of dreams is
continuous with the dreamer's waking experiences. Given the unprecedented
nature of the experiences during COVID-19, we studied the continuity hypothesis
in the context of the pandemic. We implemented a deep-learning algorithm that
can extract mentions of medical conditions from text and applied it to two
datasets collected during the pandemic: 2,888 dream reports (dreaming life
experiences), and 57M tweets mentioning the pandemic (waking life experiences).
The health expressions common to both sets were typical COVID-19 symptoms
(e.g., cough, fever, and anxiety), suggesting that dreams reflected people's
real-world experiences. The health expressions that distinguished the two sets
reflected differences in thought processes: expressions in waking life
reflected a linear and logical thought process and, as such, described
realistic symptoms or related disorders (e.g., nasal pain, SARS, H1N1); those
in dreaming life reflected a thought process closer to the visual and emotional
spheres and, as such, described either conditions unrelated to the virus (e.g.,
maggots, deformities, snakebites), or conditions of surreal nature (e.g., teeth
falling out, body crumbling into sand). Our results confirm that dream reports
represent an understudied yet valuable source of people's health experiences in
the real world.

研究探讨了 COVID-19 大流行期间梦境和现实生活经历间的连贯性，发现梦境内容反映了现实世界的体验，且两者表达的健康状况存在差异，反映了思维过程的不同。结果表明，梦境报告是了解人们健康体验的宝贵来源。