用大模型生成脑活动，反推刺激特征，实现神经信息逆向解码。
Inverting Foundation Models of Brain Function with Simulation-Based Inference
- 用语言模型控制刺激参数，生成带标签的脑活动数据。
- 从模拟脑图中成功恢复出刺激的价态、唤醒度等维度参数。
- 为脑科学模拟实验提供可逆设计工具，适合计算神经科学家。
脑功能基础模型有望通过模拟复杂刺激下的神经响应，推动虚拟神经科学研究。一个自然的下一步是逆向应用：能否从合成脑活动中还原刺激或其属性？我们以TRIBEv2为例，在概念验证场景中，将脑模拟器与大语言模型（LLMs）结合，后者根据情感极性（valence）、唤醒度（arousal）和支配感（dominance）等语言参数生成新闻标题。随后，利用基于模拟的推断方法，学习从脑图到潜在刺激参数的随机映射。结果表明，这些参数可从预测的脑图中被有效恢复，证明了模拟神经编码保留了受控刺激维度的信息。同时，大语言模型可作为可调控的刺激生成器用于仿真实验。这些发现为脑基础模型的解码与逆向设计迈出了关键一步。
原文摘要 · Abstract (English)
Foundation models of brain activity promise a new frontier for in silico neuroscience by emulating neural responses to complex stimuli across tasks and modalities. A natural next step is to ask whether these models can also be used in reverse. Can we recover a stimulus or its properties from synthetic brain activity? We study this question in a proof-of-concept setting using TRIBEv2. We pair the brain emulator with large language models (LLMs) that generate news headlines from linguistic parameters such as valence, arousal, and dominance. We then use simulation-based inference to learn a probabilistic mapping from brain maps to latent stimulus parameters. Our results show that these parameters can be recovered from predicted brain maps, demonstrating that the emulator's synthetic neural encodings preserve information about the controlled stimulus dimensions. They also show that LLMs can serve as controllable stimulus generators for simulated experiments. Together, these findings provide a step toward decoding and inverse design with foundation brain models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。