GenRL: Multimodal-foundation world models for generalization in embodied agents
GenRL presents a novel multimodal-foundation world model for developing generalist embodied agents capable of handling diverse tasks. By integrating v…
Tag: VERSES AI
Only Strict Saddles in the Energy Landscape of Predictive Coding Networks?
This research explores the geometry of the predictive coding (PC) energy landscape and its impact on learning efficiency. It demonstrates that equilib…
A hierarchical active inference model of spatial alternation tasks and the hippocampal-prefrontal circuit
The study presents a hierarchical active inference model illustrating how the hippocampal-prefrontal circuit integrates navigational systems for spati…
Variational Bayes Gaussian Splatting
The paper presents Variational Bayes Gaussian Splatting (VBGS) as an innovative method for 3D scene modeling using Gaussian mixtures. VBGS overcomes t…
Building the Future: How Active Inference AI and the Spatial Web Will Transform Abu Dhabi into the World’s First Truly Smart City
The initiative between VERSES AI and Analog in Abu Dhabi isn't just about technology - it's about reinventing urban life. By incorporating Active …
R-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Models
The research paper introduces novel techniques in active inference for continuous action POMDPs focusing on sparse reward signals. It highlights impro…
From pixels to planning: scale-free active inference
The paper introduces a scale-free active inference model that generalizes partially observed Markov decision processes by incorporating latent variabl…
Sustainability under Active Inference
The paper examines the interplay between sustainability, resilience, and well-being through the active inference framework. It defines sustainability …
“Deep Learning is Rubbish” Karl Friston & Yann LeCun Face Off at Davos 2024 World Economic Forum
In a panel hosted by the Financial Times at the World Economic Forum in Davos, Switzerland, two of the biggest names in artificial intelligence —…
Shared Protentions in Multi-Agent Active Inference
The paper integrates Husserlian phenomenology, active inference in theoretical biology, and category theory to create a framework for understanding so…