Real World Intelligence: These Are the Droids You’re Looking For
Adaptive robot without pre-training beats top model with up to 93% better performance on Meta's Habitat benchmark
Tag: VERSES Blog
Why Learn if You Can Infer: Active Inference for Robot Planning & Control
What if, instead of learning policies directly, we equipped agents to infer the hidden causes of their observations—and to generate actions by reaso…
AXIOM: Mastering Arcade Games in Minutes with Active Inference and Structure Learningv
AXIOM plans with active inference. It rolls out imagined futures under its current world model, scores them by (i) expected reward and (ii) the inform…
Whitepaper: Mastering Gameworld 10k in Minutes with the AXIOM ‘Digital Brain’
A New Benchmark Test For Generalized Intelligence
In our new research paper, we examine how AXIOM outperforms Google DeepMind’s top AI models in the…
Beyond Imitation Games: A Falsifiable Emergent Sentience Framework
VERSES Research Blog - by Ines Hipolito - "As artificial intelligence weaves itself ever more tightly into the fabric of society an age-old question l…
Benchmarking Predictive Coding Networks Made Simple
VERSES AI Research Blog - "Artificial intelligence (AI), as exemplified by large models such as ChatGPT, is one of the key technologies of this centur…
Variational Bayes Gaussian Splatting: A Bayesian Approach for Continual 3D Learning
VERSES AI Research Blog - "In recent years, computer vision has made remarkable progress in understanding 3D scenes, fueled by innovations like Neural…
Gradient-free variational learning with conditional mixture networks
VERSES AI Research Blog - "Deep Learning (DL), enables many incredible capabilities such as image recognition, natural language processing, and conten…
Achieving Human-Level Atari Gameplay with Object-Centric Priors and Active Inference
VERSES AI Research Blog - "It has been several years since deep reinforcement learning (DRL) algorithms first demonstrated superhuman performance in c…