5 citations · 15 across the 18 of their papers we have counts for
19 papers
AGI Maze Prediction Datasets: A Compact Benchmark for Learning World Dynamics with Transformers
Alexey Potapov
World modeling requires a predictive model to maintain and update an internal state adequate for reasoning about the consequences of actions. We introduce the AGI Maze Prediction D…
AGI Maze as a Benchmark Framework for World-Modeling Agents
Alexey Potapov
Large language models (LLMs) are powerful pattern-completion systems, but their default operating mode - predicting the next token from a static context - does not reliably produce…
Reframing AGI Confrontation with Off Earth Autonomy
Alexey Potapov
A common AI-safety narrative holds that sufficiently capable agents will predictably seek power, resist shutdown, and therefore tend toward confrontation with humans. We argue that…
A meta-probabilistic-programming language for bisimulation of probabilistic and non-well-founded type systems
Jonathan Warrell, Alexey Potapov, Adam Vandervorst +1
We introduce a formal meta-language for probabilistic programming, capable of expressing both programs and the type systems in which they are embedded. We are motivated here by the…
GoodPoint: unsupervised learning of keypoint detection and description
Anatoly Belikov, Alexey Potapov
This paper introduces a new algorithm for unsupervised learning of keypoint detectors and descriptors, which demonstrates fast convergence and good performance across different dat…
Distillation of neural network models for detection and description of key points of images
A. V. Yashchenko, A. V. Belikov, M. V. Peterson +1
Image matching and classification methods, as well as synchronous location and mapping, are widely used on embedded and mobile devices. Their most resource-intensive part is the de…