Uploaded November 2025 | Updated November 2026, 2 days ago
5th Applied Active Inference Symposium
Part 2: November 13, 2025
http://symposium.activeinference.institute/
Program: coda.io/d/_d08cdDbWwRy/Symposium-Program_surazvwP
Part 1: youtube.com/watch?v=VTivWre-8Kk
Part 2: youtube.com/watch?v=5uTr029Vzkg
Part 3: youtube.com/watch?v=v7aSUMX1nfs
Session 2 timestamps: 5
00:00 : “Workshop on ActiveInference.jl“ with Peter Thestrup Waade Samuel Nehrer,Jonathan Laursen
1:00:59 : “RxInfer in action“ with Bart van Erp Fraser Paterson
2:06:20 : “"Net Zero Job losses from AI" and other surprises emerging from citizens dreaming about the "Solidarity AI Stack" (socio-tech infrastructure and aspirations for public-impacting AI).“ with Michael Lennon
2:09:30 : “Formalizing Active Inference Research with Probablistic Knowledge Graphs“ with Joel Dietz
2:13:43 : “Lightning talk“ with Alexander Sabine
2:19:23 : “Lightning talk“ with Jana Lumi
2:22:11 : “Lightning talk“ with Ri Xu
2:31:35 : “Free Energy Principle and Consciousness“ with Robert Worden
3:11:51 : “Lightning talk“ with John Graves
3:23:53 : “Active Inference & RPGs“ with Pablo F.M
3:59:41 : “Making Sense of Uncertainty: Designing Experiences for Adaptive Inference“ with Anna Pereira
4:29:59 : “Adaptive Robotics for the Real World: A New Paradigm for Autonomy“ with Matt Brown
5:26:50 : “The ambiguous status of attention in predictive models of cognition“ with Maria de Vasconcelos
6:01:49 : “Agentic Finance“ with Sergio Samuel Montañez Jacquez John Clippinger,Matthew Moroney
7:10:21 : “From Coordination to Cognition: Rethinking Agent Communication Protocols for Active Inference in the Spatial Web“ with Denise Holt
7:57:39 : “Active Neurorobotics: Deep Prior Preference Learning Guided by Learnable Goals“ with Viet Dung Nguyen
9:02:02 : “The phenomeno-logical robot“ with JF Cloutier
10:00:30 : “Combining Hierarchical Active Inference with Affordance Theory for Scalable Policy Selection in Autonomous Drone Navigation“ with Harshil Shah,Satyaki Maitra
10:40:47 : “Open-source Sustainability: modeling the social aspects of production communities“ with Bradly Alicea
11:35:12 : “Constellatory Cognition: How the brain can be modelled and use modelling without having a model“ with Andrea Hiott
12:28:20 : “Coherence, Rupture, Regeneration“ with Alexander Sabine
13:38:56 : “From Information Economics to Active Inference: A Unified Bayesian Mechanics of Choice Under Uncertainty“ with Sergio Samuel Montañez Jacquez
14:05:58 : “The AI Capabilities and Alignment Consensus Project (AICACP)“ with Adam Safron
The initial truncated Part 2 livestream is youtube.com/live/1q40Jqk1HYs
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/
5th Applied Active Inference Symposium
Part 2: November 13, 2025
http://symposium.activeinference.institute/
Program: coda.io/d/_d08cdDbWwRy/Symposium-Program_surazvwP
Part 1: youtube.com/watch?v=VTivWre-8Kk
Part 2: youtube.com/watch?v=5uTr029Vzkg
Part 3: youtube.com/watch?v=v7aSUMX1nfs
Session 2 timestamps: 5
00:00 : “Workshop on ActiveInference.jl“ with Peter Thestrup Waade Samuel Nehrer,Jonathan Laursen
1:00:59 : “RxInfer in action“ with Bart van Erp Fraser Paterson
2:06:20 : “"Net Zero Job losses from AI" and other surprises emerging from citizens dreaming about the "Solidarity AI Stack" (socio-tech infrastructure and aspirations for public-impacting AI).“ with Michael Lennon
2:09:30 : “Formalizing Active Inference Research with Probablistic Knowledge Graphs“ with Joel Dietz
2:13:43 : “Lightning talk“ with Alexander Sabine
2:19:23 : “Lightning talk“ with Jana Lumi
2:22:11 : “Lightning talk“ with Ri Xu
2:31:35 : “Free Energy Principle and Consciousness“ with Robert Worden
3:11:51 : “Lightning talk“ with John Graves
3:23:53 : “Active Inference & RPGs“ with Pablo F.M
3:59:41 : “Making Sense of Uncertainty: Designing Experiences for Adaptive Inference“ with Anna Pereira
4:29:59 : “Adaptive Robotics for the Real World: A New Paradigm for Autonomy“ with Matt Brown
5:26:50 : “The ambiguous status of attention in predictive models of cognition“ with Maria de Vasconcelos
6:01:49 : “Agentic Finance“ with Sergio Samuel Montañez Jacquez John Clippinger,Matthew Moroney
7:10:21 : “From Coordination to Cognition: Rethinking Agent Communication Protocols for Active Inference in the Spatial Web“ with Denise Holt
7:57:39 : “Active Neurorobotics: Deep Prior Preference Learning Guided by Learnable Goals“ with Viet Dung Nguyen
9:02:02 : “The phenomeno-logical robot“ with JF Cloutier
10:00:30 : “Combining Hierarchical Active Inference with Affordance Theory for Scalable Policy Selection in Autonomous Drone Navigation“ with Harshil Shah,Satyaki Maitra
10:40:47 : “Open-source Sustainability: modeling the social aspects of production communities“ with Bradly Alicea
11:35:12 : “Constellatory Cognition: How the brain can be modelled and use modelling without having a model“ with Andrea Hiott
12:28:20 : “Coherence, Rupture, Regeneration“ with Alexander Sabine
13:38:56 : “From Information Economics to Active Inference: A Unified Bayesian Mechanics of Choice Under Uncertainty“ with Sergio Samuel Montañez Jacquez
14:05:58 : “The AI Capabilities and Alignment Consensus Project (AICACP)“ with Adam Safron
The initial truncated Part 2 livestream is youtube.com/live/1q40Jqk1HYs
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)
