5 papers
Physics-aware Masked Diffusion-based Flood Simulation for Urban Fisheye Disaster Detection
Sodtavilan Odonchimed, Tsogt Enkhbayar, Oyunzul Munkhtamga +1
Physical simulations that predict the behavior of urban disasters, such as climate-related flooding, play a crucial role in disaster prevention and the development of anomaly detec…
Learning from Negative Examples: Why Warning-Framed Training Data Teaches What It Warns Against
Tsogt-Ochir Enkhbayar
Warning-framed content in training data (e.g., "DO NOT USE - this code is vulnerable") does not, it turns out, teach language models to avoid the warned-against behavior. In experi…
Which Sparse Autoencoder Features Are Real? Model-X Knockoffs for False Discovery Rate Control
Tsogt-Ochir Enkhbayar
Although sparse autoencoders (SAEs) are crucial for identifying interpretable features in neural networks, it is still challenging to distinguish between real computational pattern…
Atomic Literary Styling: Mechanistic Manipulation of Prose Generation in Neural Language Models
Tsogt-Ochir Enkhbayar
We present a mechanistic analysis of literary style in GPT-2, identifying individual neurons that discriminate between exemplary prose and rigid AI-generated text. Using Herman Mel…
A New Way: Kronecker-Factored Approximate Curvature Deep Hedging and its Benefits
Tsogt-Ochir Enkhbayar
This paper advances the computational efficiency of Deep Hedging frameworks through the novel integration of Kronecker-Factored Approximate Curvature (K-FAC) optimization. While re…