5 papers
PyBatchRender: A Python Library for Batched 3D Rendering at Up to One Million FPS
Evgenii Rudakov, Jonathan Shock, Benjamin Ultan Cowley
Reinforcement learning from pixels is often bottlenecked by the performance and complexity of 3D rendered environments. Researchers face a trade-off between high-speed, low-level e…
Graph-Based Exploration for ARC-AGI-3 Interactive Reasoning Tasks
Evgenii Rudakov, Jonathan Shock, Benjamin Ultan Cowley
We present a training-free graph-based approach for solving interactive reasoning tasks in the ARC-AGI-3 benchmark. ARC-AGI-3 comprises game-like tasks where agents must infer task…
Energy Costs and Neural Complexity Evolution in Changing Environments
Sian Heesom-Green, Jonathan Shock, Geoff Nitschke
The Cognitive Buffer Hypothesis (CBH) posits that larger brains evolved to enhance survival in changing conditions. However, larger brains also carry higher energy demands, imposin…
Toward an African Agenda for AI Safety
Samuel T. Segun, Rachel Adams, Ana Florido +22
This paper maps Africa's distinctive AI risk profile, from deepfake fuelled electoral interference and data colonial dependency to compute scarcity, labour disruption and dispropor…
SSSUMO: Real-Time Semi-Supervised Submovement Decomposition
Evgenii Rudakov, Jonathan Shock, Otto Lappi +1
This paper introduces a SSSUMO, semi-supervised deep learning approach for submovement decomposition that achieves state-of-the-art accuracy and speed. While submovement analysis o…