3 citations · 8 across the 10 of their papers we have counts for
11 papers
Compression Forcing: Hierarchical History Tokenization Enables Flexible World Models
Siqiao Huang, Partha Kaushik, Michael Chen +5
Effective world modeling requires compressing salient history information that facilitates future prediction. However, most existing approaches inherit tokenization and conditionin…
Nano World Models: A Minimalist Implementation of Future Video Prediction
Siqiao Huang, Partha Kaushik, Michael Chen +5
World models have become a central paradigm for learning predictive simulators that support generation, planning, and decision-making. Yet, despite rapid progress in industry-scale…
Rough Transformers: Lightweight and Continuous Time Series Modelling through Signature Patching
Fernando Moreno-Pino, Álvaro Arroyo, Harrison Waldon +2
Time-series data in real-world settings typically exhibit long-range dependencies and are observed at non-uniform intervals. In these settings, traditional sequence-based recurrent…
Rough Transformers for Continuous and Efficient Time-Series Modelling
Fernando Moreno-Pino, Álvaro Arroyo, Harrison Waldon +2
Time-series data in real-world medical settings typically exhibit long-range dependencies and are observed at non-uniform intervals. In such contexts, traditional sequence-based re…
Interpretable Spectral Variational AutoEncoder (ISVAE) for time series clustering
Óscar Jiménez Rama, Fernando Moreno-Pino, David Ramírez +1
The best encoding is the one that is interpretable in nature. In this work, we introduce a novel model that incorporates an interpretable bottleneck-termed the Filter Bank (FB)-at…
Deep Attentive Survival Analysis in Limit Order Books: Estimating Fill Probabilities with Convolutional-Transformers
Alvaro Arroyo, Alvaro Cartea, Fernando Moreno-Pino +1
One of the key decisions in execution strategies is the choice between a passive (liquidity providing) or an aggressive (liquidity taking) order to execute a trade in a limit order…
Sleep Activity Recognition and Characterization from Multi-Source Passively Sensed Data
María Martínez-García, Fernando Moreno-Pino, Pablo M. Olmos +1
Sleep constitutes a key indicator of human health, performance, and quality of life. Sleep deprivation has long been related to the onset, development, and worsening of several men…
Heterogeneous Hidden Markov Models for Sleep Activity Recognition from Multi-Source Passively Sensed Data
Fernando Moreno-Pino, María Martínez-García, Pablo M. Olmos +1
Psychiatric patients' passive activity monitoring is crucial to detect behavioural shifts in real-time, comprising a tool that helps clinicians supervise patients' evolution over t…
DeepVol: Volatility Forecasting from High-Frequency Data with Dilated Causal Convolutions
Fernando Moreno-Pino, Stefan Zohren
Volatility forecasts play a central role among equity risk measures. Besides traditional statistical models, modern forecasting techniques based on machine learning can be employed…
PyHHMM: A Python Library for Heterogeneous Hidden Markov Models
Fernando Moreno-Pino, Emese Sükei, Pablo M. Olmos +1
We introduce PyHHMM, an object-oriented open-source Python implementation of Heterogeneous-Hidden Markov Models (HHMMs). In addition to HMM's basic core functionalities, such as di…
Deep Autoregressive Models with Spectral Attention
Fernando Moreno-Pino, Pablo M. Olmos, Antonio Artés-Rodríguez
Time series forecasting is an important problem across many domains, playing a crucial role in multiple real-world applications. In this paper, we propose a forecasting architectur…