Active Inference
PulseAugur coverage of Active Inference — every cluster mentioning Active Inference across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
New paper details Renormalising Generative Models for Active Inference
A new paper published on arXiv details Renormalising Generative Models (RGMs) for Active Inference, aiming to overcome challenges in scaling these models to complex domains. The research provides a clear, derivation-ori…
-
New active inference model integrates emotion into human driving simulations
Researchers have developed an expanded active inference model for human driving that incorporates affective states, represented by valence and arousal. This new formulation allows for the extraction of emotional signals…
-
AI Safety Explores Cybernetics: Viable System Model for Agency
This article explores the Viable System Model (VSM), a concept from cybernetics developed by Stafford Beer, as a framework for understanding multi-scale hierarchical agency in AI safety. The author translates Beer's mod…
-
Active Inference framed as convex MDP, unifying with reinforcement learning
A new paper frames Active Inference (AIF) as a convex Markov Decision Process (MDP), suggesting a way to unify it with modern reinforcement learning (RL) techniques. The research posits that minimizing expected free ene…
-
New theory links JEPA world models to Active Inference via SIGReg objective
A new theoretical paper proposes that the SIGReg objective, when used as an anti-collapse regularizer in Joint-Embedding Predictive Architectures (JEPAs), can serve as a valid Active Inference (AIF) variational free ene…
-
Neuroscience-inspired self-supervised learning framework introduced
Researchers have introduced Meta-Representational Predictive Coding (MPC), a novel self-supervised learning framework inspired by neuroscience. This approach aims to overcome the limitations of traditional backpropagati…
-
AI Agents Conceptualized as Hierarchical Belief Webs
This post introduces an informal framework for understanding intelligent agents as "belief webs." This model integrates concepts from active inference, agent foundations, and machine learning, proposing that beliefs, go…
-
New theory of agency grounded in relational biology and process ontology
This paper, "A Matter of Time: Towards a General Theory of Agency," proposes a graded organizational theory of agency rooted in relational biology, physical biosemiotics, and process ontology. It argues that agency orig…
-
Active Inference Controller Optimizes Traffic Signals in Challenging Environments
Researchers have developed an active inference controller for traffic signal management in noisy and unpredictable IoT environments. This controller dynamically selects signal phases by minimizing expected free energy, …
-
New AI agent BRAIN enhances 6G network adaptability and explainability
Researchers have developed a new AI agent called BRAIN (Bayesian Reasoning via Active Inference) designed for future 6G mobile networks. This agent utilizes a deep generative model and active inference to unify percepti…
-
Active inference framework clarified in new research paper
Researchers have published a paper detailing active inference, a framework that frames decision-making as a form of inference. The work clarifies how expected free energy minimization relates to variational free energy …
-
AI agents need persistent internal states, not just on-demand processing
The current paradigm for AI agents, where they function like smart calculators that activate only when prompted, is a significant limitation. True AI agents require a persistent internal state and continuous operation, …
-
New framework improves U-statistics with active inference for costly labels
Researchers have developed a new active inference framework for U-statistics, aiming to improve estimation efficiency when labeling data is expensive. This approach selectively queries informative labels within a fixed …
-
Category theory framework proposed for defining and comparing AGI architectures
This working paper proposes a formal framework for comparing different Artificial General Intelligence (AGI) architectures using category theory. The authors aim to provide a unified foundation for AGI systems, integrat…