Uploaded November 2026 | Updated November 2026, 3 hours ago
Prerecorded presentation at the 6th Applied Active Inference Symposium (November 12–13, 2026), hosted by the Active Inference Institute. Online and free.
Bo Lee: “Maladaptive Daydreaming as a Precision Trap: An Active Inference Framework, Its Testable Core, and Evidence from Daily Diaries”
Maladaptive daydreaming (MD) involves prolonged immersion in self-generated fantasy and difficulty disengaging despite awareness that the experience is imagined. We propose a testable active-inference framework in which the precision assigned to internal predictions relative to external sensory evidence may contribute to self-sustaining fantasy. This precision-feedback mechanism is a hypothesis, not an established clinical explanation. Using analytic counterexamples and 115,200 synthetic datasets, we show why finite-time persistence and hysteresis-like observations alone do not identify bistability, and examine how ramp-and-hold experimental designs can improve discrimination among competing models. Exploratory secondary analyses of daily-diary data are discussed at their actual timescale, without treating daily associations as proof of an episode-level mechanism. The talk connects active inference, computational psychiatry, experimental design, and open science. It concludes with falsifiable predictions and a research agenda focused on measuring internal and sensory precision, tracking within-episode dynamics, comparing alternative models, and testing feasible interventions. We welcome discussion of practical measurements and alternative explanations.
Symposium program: https://2026symposium.activeinference.institute/
Abstract book (Zenodo): zenodo.org/records/23986505
Livestreams: Day 1 youtube.com/watch?v=-v4IaFY9MZI · Day 2 youtube.com/watch?v=ccze9ay8D0o
All Symposium videos (playlist): youtube.com/playlist?list=PLO2noumu0LRk
Previous Symposia: https://symposium.activeinference.institute/
Active Inference Institute information:
Website: https://activeinference.institute/
X: https://x.com/InferenceActive
Discord: https://discord.activeinference.institute/
Donate: https://donate.activeinference.institute/
YouTube: youtube.com/c/ActiveInference
Active Inference Livestreams: https://video.activeinference.institute/
Prerecorded presentation at the 6th Applied Active Inference Symposium (November 12–13, 2026), hosted by the Active Inference Institute. Online and free.
Bo Lee: “Maladaptive Daydreaming as a Precision Trap: An Active Inference Framework, Its Testable Core, and Evidence from Daily Diaries”
Maladaptive daydreaming (MD) involves prolonged immersion in self-generated fantasy and difficulty disengaging despite awareness that the experience is imagined. We propose a testable active-inference framework in which the precision assigned to internal predictions relative to external sensory evidence may contribute to self-sustaining fantasy. This precision-feedback mechanism is a hypothesis, not an established clinical explanation. Using analytic counterexamples and 115,200 synthetic datasets, we show why finite-time persistence and hysteresis-like observations alone do not identify bistability, and examine how ramp-and-hold experimental designs can improve discrimination among competing models. Exploratory secondary analyses of daily-diary data are discussed at their actual timescale, without treating daily associations as proof of an episode-level mechanism. The talk connects active inference, computational psychiatry, experimental design, and open science. It concludes with falsifiable predictions and a research agenda focused on measuring internal and sensory precision, tracking within-episode dynamics, comparing alternative models, and testing feasible interventions. We welcome discussion of practical measurements and alternative explanations.
Symposium program: https://2026symposium.activeinference.institute/
Abstract book (Zenodo): zenodo.org/records/23986505
Livestreams: Day 1 youtube.com/watch?v=-v4IaFY9MZI · Day 2 youtube.com/watch?v=ccze9ay8D0o
All Symposium videos (playlist): youtube.com/playlist?list=PLO2noumu0LRk
Previous Symposia: https://symposium.activeinference.institute/
Active Inference Institute information:
Website: https://activeinference.institute/
X: https://x.com/InferenceActive
Discord: https://discord.activeinference.institute/
Donate: https://donate.activeinference.institute/
YouTube: youtube.com/c/ActiveInference
Active Inference Livestreams: https://video.activeinference.institute/






![ActInf GuestStream 115.1 ~ Energy-Based Transformers and the Future of Scaling
Energy-Based Transformers are Scalable Learners and Thinkers
Alexi Gladstone, Ganesh Nanduru, Md Mofijul Islam, Peixuan Han, Hyeonjeong Ha, Aman Chadha, Yilun Du, Heng Ji, Jundong Li, Tariq Iqbal
https://arxiv.org/abs/2507.02092
Inference-time computation techniques, analogous to human System 2 Thinking, have recently become popular for improving model performances. However, most existing approaches suffer from several limitations: they are modality-specific (e.g., working only in text), problem-specific (e.g., verifiable domains like math and coding), or require additional supervision/training on top of unsupervised pretraining (e.g., verifiers or verifiable rewards). In this paper, we ask the question Is it possible to generalize these System 2 Thinking approaches, and develop models that learn to think solely from unsupervised learning? Interestingly, we find the answer is yes, by learning to explicitly verify the compatibility between inputs and candidate-predictions, and then re-framing prediction problems as optimization with respect to this verifier. Specifically, we train Energy-Based Transformers (EBTs) a new class of Energy-Based Models (EBMs) to assign an energy value to every input and candidate-prediction pair, enabling predictions through gradient descent-based energy minimization until convergence. Across both discrete (text) and continuous (visual) modalities, we find EBTs scale faster than the dominant Transformer++ approach during training, achieving an up to 35% higher scaling rate with respect to data, batch size, parameters, FLOPs, and depth. During inference, EBTs improve performance with System 2 Thinking by 29% more than the Transformer++ on language tasks, and EBTs outperform Diffusion Transformers on image denoising while using fewer forward passes. Further, we find that EBTs achieve better results than existing models on most downstream tasks given the same or worse pretraining performance, suggesting that EBTs generalize better than existing approaches. Consequently, EBTs are a promising new paradigm for scaling both the learning and thinking capabilities of models.
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2507.02092 [cs.LG]
(or arXiv:2507.02092v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2507.02092
Active Inference Institute information:
Website: https://www.activeinference.institute/
Activities: https://activities.activeinference.institute/
Discord: https://discord.activeinference.institute/
Donate: http://donate.activeinference.institute/
YouTube: https://www.youtube.com/c/ActiveInference/
X: https://x.com/InferenceActive
Active Inference Livestreams: https://video.activeinference.institute/ ActInf GuestStream 115.1 ~ Energy-Based Transformers and the Future of Scaling](https://i.ytimg.com/vi/85ob-jrG7xQ/mqdefault.jpg)



