认知启发的基于能量的世界模型
Cognitively Inspired Energy-Based World Models
AI总结：
针对自回归世界模型缺乏类人认知的问题，本文提出 EBWM，用 EBM 评估上下文与未来状态的兼容性，并设计 EBT，在视觉和语言任务上展现更优或有前景的扩展性。
摘要：
训练世界模型的主要方法之一是在序列下一个元素的输出空间中进行自回归预测。在自然语言处理（NLP）中，这表现为大型语言模型（LLM）预测下一个 token；在计算机视觉（CV）中，则表现为自回归模型预测下一帧/下一个 token/下一个像素。然而，这种方法在若干方面不同于人类认知。首先，人类对未来的预测会主动影响内部认知过程。其次，人类会自然地评估关于未来状态预测的合理性。基于这种能力，第三，人类通过判断何时预测已经足够，为作出预测分配动态时长。这一自适应过程类似于心理学中的 System 2 思维。所有这些能力都是人类成功完成高级推理和规划的基础。因此，为解决传统自回归模型缺乏这些类人能力的局限，我们提出了基于能量的世界模型（Energy-Based World Models，EBWM）。EBWM 训练一个基于能量的模型（Energy-Based Model，EBM），用于预测给定上下文与预测未来状态之间的兼容性。通过这种方式，EBWM 使模型能够实现上述人类认知的全部三个方面。此外，我们开发了一种为基于能量模型定制的传统自回归 transformer 变体，称为基于能量的 Transformer（Energy-Based Transformer，EBT）。结果表明，在 CV 中，EBWM 随数据和 GPU Hours 的扩展性优于传统自回归 transformer，并且 EBWM 在 NLP 中展现出有前景的早期扩展趋势。因此，该方法为训练未来能够进行 System 2 思维并跨状态空间智能搜索的模型提供了一条令人振奋的路径。
英文摘要：
One of the predominant methods for training world models is autoregressive prediction in the output space of the next element of a sequence. In Natural Language Processing (NLP), this takes the form of Large Language Models (LLMs) predicting the next token; in Computer Vision (CV), this takes the form of autoregressive models predicting the next frame/token/pixel. However, this approach differs from human cognition in several respects. First, human predictions about the future actively influence internal cognitive processes. Second, humans naturally evaluate the plausibility of predictions regarding future states. Based on this capability, and third, by assessing when predictions are sufficient, humans allocate a dynamic amount of time to make a prediction. This adaptive process is analogous to System 2 thinking in psychology. All these capabilities are fundamental to the success of humans at high-level reasoning and planning. Therefore, to address the limitations of traditional autoregressive models lacking these human-like capabilities, we introduce Energy-Based World Models (EBWM). EBWM involves training an Energy-Based Model (EBM) to predict the compatibility of a given context and a predicted future state. In doing so, EBWM enables models to achieve all three facets of human cognition described. Moreover, we developed a variant of the traditional autoregressive transformer tailored for Energy-Based models, termed the Energy-Based Transformer (EBT). Our results demonstrate that EBWM scales better with data and GPU Hours than traditional autoregressive transformers in CV, and that EBWM offers promising early scaling in NLP. Consequently, this approach offers an exciting path toward training future models capable of System 2 thinking and intelligently searching across state spaces.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
