Tag
This paper proposes a physics-informed world model that generates dynamics from the gradient of a learned energy via a fixed reversible operator, with one-way energy dissipation and structured parameter interventions. Across electromagnetic, particle-in-cell, and shallow-water systems, ~9k-parameter models achieve stable 100x-horizon rollouts, correct counterfactual responses, and out-of-distribution refusal when no intervention map is supplied, far outperforming unstructured equal-capacity baselines.
A GitHub project that connects a fly's connectome neural simulation to a live Doom game arena for real-time control and experimental dopamine-gated memory rules, currently in a live training phase without demonstrated learned survival.
The author trained a simulated fly brain to watch the 1986 film 'The Fly,' with each neuron responding to Jeff Goldblum's performance. This experiment is linked to Grok Imagine, an AI video generation tool.
Fly Escape Room is a game featuring NPCs powered by a real fruit fly brain with 166k neurons, built with GPT-6 Astra over a 3-day loop, where players simulate flies attempting to escape.
Image2Sim is a neural simulation framework that creates high-fidelity interactive environments from RGB-D images, enabling scalable training for embodied navigation agents. It generates nearly 20K scenes and over 10 million training samples, showing strong benchmark improvements and effective real-world zero-shot transfer.
This paper introduces NeuROK, a data-driven approach for generative 4D neural object kinematics that learns a latent space and transformer-based encoder-decoder to simulate realistic temporal deformations of static objects under various physical conditions, overcoming limitations of predefined physical models.