Categories: Visualism
16 entries
Perception comes before language; vision is the foundation of intelligence.
| Maker Robotics Cheap, hackable, open robot hardware in many hands will move embodied AI faster than a few expensive flagship robots. | |
| Active-Perception Doctrine Seeing is something an agent does, choosing where to look and how to move, not a passive mapping from images to labels. | |
| Latent-Prediction Doctrine Argues models should predict abstract representations of missing or future inputs, not reconstruct pixels or tokens. | |
| Sensorimotor Doctrine Perception and action form one closed loop, so intelligence lies in mastering how sensations change as you act. | |
| Model-Based Planism Agents should learn a model of their environment and plan inside it, trying actions in imagination before taking them for real. | |
| Artificial-Life Doctrine Intelligence is a late product of life-like processes, so we should grow it from self-organising, self-replicating systems rather than train it. | |
| Self-Supervised Liberalism Let data supervise itself; labels and captions are optional, and good visual features emerge from raw pixels alone. | |
| Multimodal Visualism Holds that visual understanding is the core goal, with language, audio and other modalities serving as auxiliary signals. | |
| Reactive Anarchism Robust behaviour comes from tight sensor-to-actuator reflexes, not from world models or plans; let the world be its own representation. | |
| Federated-Learning Localism Data should stay where it is generated; models travel to devices and institutions, learn locally, and only share updates. | |
| Neuroevolutionism Evolutionary search over network weights, topologies and hyperparameters is a scalable, gradient-free alternative to backpropagation-centric training. | |
| Dexterity Doctrine Holds that dexterous manipulation with multi-fingered hands is the true test and engine of physical intelligence. | |
| Subsumption Doctrine Intelligent behavior emerges from layered, reactive sensorimotor modules coupled directly to the world, without a central symbolic world model. | |
| Game-Agent Doctrine Games are the ideal training ground for general agents: rich, cheap, safe worlds with clear goals and unlimited replays. | |
| Physicalism Holds that understanding physical dynamics comes before intelligence, so models should learn how objects and forces actually behave. | |
| Developmentalism Intelligence should be grown in stages like a child, through embodied play, curricula and gradually expanding skills. |