Skip to content
GCC AI Research

Search

Results for "state-space models"

Making computer vision more efficient with state-space models

MBZUAI ·

MBZUAI researchers developed GroupMamba, a new set of state-space models (SSMs) for computer vision that addresses limitations in existing SSMs related to computational efficiency and optimization challenges. GroupMamba introduces a new layer called modulated group mamba, improving efficiency and stability. In benchmark tests, GroupMamba performed as well as similar SSM systems, but more efficiently, offering a backbone for tasks like image classification, object detection, and segmentation. Why it matters: This research aims to bridge the gap between vision transformers and CNNs by improving SSMs, potentially leading to more efficient and powerful computer vision models.

Modeling High-Resolution Spatio-Temporal Wind with Deep Echo State Networks and Stochastic Partial Differential Equations

arXiv ·

Researchers propose a spatio-temporal model for high-resolution wind forecasting in Saudi Arabia using Echo State Networks and stochastic partial differential equations. The model reduces spatial information via energy distance, captures dynamics with a sparse recurrent neural network, and reconstructs data using a non-stationary stochastic partial differential equation approach. The model achieves more accurate forecasts of wind speed and energy, potentially saving up to one million dollars annually compared to existing models.

Neural Bayes estimators for censored inference with peaks-over-threshold models

arXiv ·

This paper introduces neural Bayes estimators for censored peaks-over-threshold models, enhancing computational efficiency in spatial extremal dependence modeling. The method uses data augmentation to encode censoring information in the neural network input, challenging traditional likelihood-based approaches. The estimators were applied to assess extreme particulate matter concentrations over Saudi Arabia, demonstrating efficacy in high-dimensional models. Why it matters: The research offers a computationally efficient alternative for environmental modeling and risk assessment in the region.

Distribution-Free Conformal Joint Prediction Regions for Neural Marked Temporal Point Processes

MBZUAI ·

A presentation will demonstrate the construction of well-calibrated, distribution-free neural Temporal Point Process (TPP) models from multiple event sequences using conformal prediction. The method builds a distribution-free joint prediction region for event arrival time and type with a finite-sample coverage guarantee. The refined method is based on the highest density regions, derived from the joint predictive density of event arrival time and type to address the challenge of creating a joint prediction region for a bivariate response that includes both continuous and discrete data types. Why it matters: This research from a KAUST postdoc improves uncertainty quantification in neural TPPs, which are crucial for modeling continuous-time event sequences, with applications in various fields, by providing more reliable prediction regions.

A shock to the system

KAUST ·

KAUST Professor Hernando Ombao is leading the Biostatistics Group to develop statistical models for projecting hospitalization surges during the COVID-19 pandemic. The group uses techniques like time series analysis and stationary subspace analysis to understand complex biological processes. The models aim to provide public health officials with accurate hospitalization estimates under varying scenarios. Why it matters: This research contributes to preparedness and resource allocation in healthcare systems during public health crises, with potential applications beyond COVID-19.

Confidence sets for Causal Discovery

MBZUAI ·

A new framework for constructing confidence sets for causal orderings within structural equation models (SEMs) is presented. It leverages a residual bootstrap procedure to test the goodness-of-fit of causal orderings, quantifying uncertainty in causal discovery. The method is computationally efficient and suitable for medium-sized problems while maintaining theoretical guarantees as the number of variables increases. Why it matters: This offers a new dimension of uncertainty quantification that enhances the robustness and reliability of causal inference in complex systems, but there is no indication of connection to the Middle East.

From State Estimation on Lie Groups to Robot Imagination

MBZUAI ·

Gregory Chirikjian presented an overview talk on applying probability, harmonic analysis, and geometry to robotics, emphasizing the need for robots to function beyond traditional industrial programming. He discussed a new approach where robots define affordances of objects, using simulation to 'imagine' object use and enabling reasoning about novel objects. Probabilistic methods on Lie-groups, initially developed for mobile robot state estimation, are now adapted for one-shot learning of affordances, with plans to integrate large language models. Why it matters: This research direction aims to enhance robot intelligence and adaptability, crucial for service robots in dynamic environments and aligning with broader goals of advanced AI integration in robotics.

UAE’s Technology Innovation Institute Revolutionizes AI Language Models With New Architecture

TII ·

Technology Innovation Institute (TII) has released Falcon Mamba 7B, a new large language model and the first State Space Language Model (SSLM) in its Falcon series. Falcon Mamba 7B is the top-ranked open-source SSLM globally, outperforming Meta's Llama 3.1 8B, Llama 3 8B, and Mistral’s 7B on HuggingFace benchmarks. SSLMs excel at understanding complex, evolving situations and have applications in NLP tasks like machine translation and text summarization. Why it matters: This release strengthens the UAE's position as an AI hub, demonstrating TII's commitment to pioneering research and open-source AI development in the region.