AI 神经代理框架用 fMRI 无创预测神经调控的认知效果
AI-Driven Neural Surrogates for In Silico Design of Cognitive-Affective Neuromodulation Targets
一项把控制论和生成模型用于神经调控的论文，用 fMRI 快照就能预测改变效价的效果，数据量四万多条，做脑科学方向的可以看看
arXiv 论文提出一个 AI 神经代理框架，结合 fMRI 解码、深度生成建模和约束潜空间引导，在不做物理刺激的情况下预测候选表征变化对感知的影响。研究基于 Natural Scenes Dataset 4 名被试超过 36,000 条图像-fMRI 观测， subject-specific 模型的二选一识别率达 0.79-0.88（随机为 0.5）。在 VDVAE 模型中，效价从 -0.61 SD 移至 +1.03 SD，记忆度从 -1.34 SD 移至 +1.45 SD；18 名被试共 7,200 次人类评分中，16 人的效价朝预测方向变化。自动化评分器与人类效价评分的相关仅为 r = 0.30，且极端扰动会导致图像偏离原始刺激。
AI-Driven Neural Surrogates for In Silico Design of Cognitive-Affective Neuromodulation Targets
In neuropsychiatry, the primary goal is often not only to decode brain activity but to change it, for example to lessen a negative affective bias or an overly salient memory. Motivated by control theory, we develop an AI-driven neural-surrogate framework that proposes candidate representational changes and tests their predicted perceptual effects from snapshots of stimulus-evoked fMRI activity, without physical stimulation. The framework combines fMRI decoding, deep generative modeling, and constrained latent-space steering. Valence and memorability are used only as worked examples. Using more than 36,000 image-fMRI observations from four deeply sampled Natural Scenes Dataset participants, subject-specific models recovered coarse generative structure from visually responsive cortex (two-way identification, 0.79-0.88; chance, 0.5). Graded perturbations were reconstructed as images and evaluated with automated scorers and human ratings from 7,200 trials by 18 participants. In the primary VDVAE model, valence shifted from -0.61 to +1.03 SD and memorability from -1.34 to +1.45 SD; a later Versatile Diffusion refinement reduced or altered these effects. Across five perturbation levels, human valence ratings moved in the predicted direction under the linear time-correction model (mean slope, 0.038 SD per unit of alpha; 95 percent CI, 0.003-0.074; positive in 16 of 18 participants). Perceived memorability did not change reliably. Baseline agreement with the automated assessor was suggestive for valence (r = 0.30) and weak for memorability (r = 0.10). Extreme perturbations drifted from the original stimulus, so intended change must be weighed against loss of fidelity. These findings provide a falsifiable upstream method for designing and behaviorally testing candidate representational targets for future neuromodulation in psychiatry, while marking the limits of the present static approximation.