Generative artificial intelligence has shown promise in prompting virtual worlds into existence, yet little attention has been given to understanding how this process unfolds as social interaction. We present Social Conjurer, a framework for AI-augmented dynamic 3D scene co-creation, where multiple users collaboratively build and modify virtual worlds in real-time. Through an expanded set of interactions, including social and tool-based engagements as well as spatial reasoning, our framework facilitates the creation of rich, diverse virtual environments. Findings from a preliminary user study (N=12) provide insight into the user experience of this approach, how social contexts shape the prompting of spatial environments, and perspective on social applications of prompt-based 3D co-creation. In addition to highlighting the potential of AI-supported multi-user world creation and offering new pathways for AI-augmented creative processes in VR, this article presents a set of implications for designing human-centered interfaces that incorporate AI models into 3D content generation.

Deep learning for time series forecasting has seen significant advancements over the past decades. However, despite the success of large-scale pre-training in language and vision domains, pre-trained time series models remain limited in scale and operate at a high cost, hindering the development of larger capable forecasting models in real-world applications. In response, we introduce Time-MoE, a scalable and unified architecture designed to pre-train larger, more capable forecasting foundation models while reducing inference costs. By leveraging a sparse mixture-of-experts (MoE) design, Time-MoE enhances computational efficiency by activating only a subset of networks for each prediction, reducing computational load while maintaining high model capacity. This allows Time-MoE to scale effectively without a corresponding increase in inference costs. Time-MoE comprises a family of decoder-only transformer models that operate in an auto-regressive manner and support flexible forecasting horizons with varying input context lengths. We pre-trained these models on our newly introduced large-scale data Time-300B, which spans over 9 domains and encompassing over 300 billion time points. For the first time, we scaled a time series foundation model up to 2.4 billion parameters, achieving significantly improved forecasting precision. Our results validate the applicability of scaling laws for training tokens and model size in the context of time series forecasting. Compared to dense models with the same number of activated parameters or equivalent computation budgets, our models consistently outperform them by large margin. These advancements position Time-MoE as a state-of-the-art solution for tackling real-world time series forecasting challenges with superior capability, efficiency, and flexibility.

State space models (SSMs) leverage linear, time-invariant (LTI) systems to effectively learn sequences with long-range dependencies. By analyzing the transfer functions of LTI systems, we find that SSMs exhibit an implicit bias toward capturing low-frequency components more effectively than high-frequency ones. This behavior aligns with the broader notion of frequency bias in deep learning model training. We show that the initialization of an SSM assigns it an innate frequency bias and that training the model in a conventional way does not alter this bias. Based on our theory, we propose two mechanisms to tune frequency bias: either by scaling the initialization to tune the inborn frequency bias; or by applying a Sobolev-norm-based filter to adjust the sensitivity of the gradients to high-frequency inputs, which allows us to change the frequency bias via training. Using an image-denoising task, we empirically show that we can strengthen, weaken, or even reverse the frequency bias using both mechanisms. By tuning the frequency bias, we can also improve SSMs' performance on learning long-range sequences, averaging an 88.26% accuracy on the Long-Range Arena (LRA) benchmark tasks.

Edge signal processing facilitates distributed learning and inference in the client-server model proposed in federated learning. In traditional machine learning, clients (IoT devices) that acquire raw signal samples can aid a data center (server) learn a global signal model by pooling these distributed samples at a third-party location. Despite the promising capabilities of IoTs, these distributed deployments often face the challenge of sensitive private data and communication rate constraints. This necessitates a learning approach that communicates a processed approximation of the distributed samples instead of the raw signals. Such a decentralized learning approach using signal approximations will be termed distributed signal analytics in this work. Overpredictive signal approximations may be desired for distributed signal analytics, especially in network demand (capacity) planning applications motivated by federated learning. In this work, we propose algorithms that compute an overpredictive signal approximation at the client devices using an efficient convex optimization framework. Tradeoffs between communication cost, sampling rate, and the signal approximation error are quantified using mathematical analysis. We also show the performance of the proposed distributed algorithms on a publicly available residential energy consumption dataset.

Learning from Demonstration (LfD) is a useful paradigm for training policies that solve tasks involving complex motions, such as those encountered in robotic manipulation. In practice, the successful application of LfD requires overcoming error accumulation during policy execution, i.e. the problem of drift due to errors compounding over time and the consequent out-of-distribution behaviours. Existing works seek to address this problem through scaling data collection, correcting policy errors with a human-in-the-loop, temporally ensembling policy predictions or through learning a dynamical system model with convergence guarantees. In this work, we propose and validate an alternative approach to overcoming this issue. Inspired by reservoir computing, we develop a recurrent neural network layer that includes a fixed nonlinear dynamical system with tunable dynamical properties for modelling temporal dynamics. We validate the efficacy of our neural network layer on the task of reproducing human handwriting motions using the LASA Human Handwriting Dataset. Through empirical experiments we demonstrate that incorporating our layer into existing neural network architectures addresses the issue of compounding errors in LfD. Furthermore, we perform a comparative evaluation against existing approaches including a temporal ensemble of policy predictions and an Echo State Network (ESN) implementation. We find that our approach yields greater policy precision and robustness on the handwriting task while also generalising to multiple dynamics regimes and maintaining competitive latency scores.

Partial differential equations, and their chaotic solutions, are pervasive in the modelling of complex systems in engineering, science, and beyond. Data-driven methods can find solutions to partial differential equations with a divide-and-conquer strategy: The solution is sought in a latent space, on which the temporal dynamics are inferred (``latent-space'' approach). This is achieved by, first, compressing the data with an autoencoder, and, second, inferring the temporal dynamics with recurrent neural networks. The overarching goal of this paper is to show that a latent-space approach can not only infer the solution of a chaotic partial differential equation, but it can also predict the stability properties of the physical system. First, we employ the convolutional autoencoder echo state network (CAE-ESN) on the chaotic Kuramoto-Sivashinsky equation for various chaotic regimes. We show that the CAE-ESN (i) finds a low-dimensional latent-space representation of the observations and (ii) accurately infers the Lyapunov exponents and covariant Lyapunov vectors (CLVs) in this low-dimensional manifold for different attractors. Second, we extend the CAE-ESN to a turbulent flow, comparing the Lyapunov spectrum to estimates obtained from Jacobian-free methods. A latent-space approach based on the CAE-ESN effectively produces a latent space that preserves the key properties of the chaotic system, such as Lyapunov exponents and CLVs, thus retaining the geometric structure of the attractor. The latent-space approach based on the CAE-ESN is a reduced-order model that accurately predicts the dynamics of the chaotic system, or, alternatively, it can be used to infer stability properties of chaotic systems from data.

Model predictive control (MPC) has become the de facto standard action space for local planning and learning-based control in many continuous robotic control tasks, including autonomous driving. MPC solves a long-horizon cost optimization as a series of short-horizon optimizations based on a global planner-supplied reference path. The primary challenge in MPC, however, is that the computational budget for re-planning has a hard limit, which frequently inhibits exact optimization. Modern edge networks provide low-latency communication and heterogeneous properties that can be especially beneficial in this situation. We propose a novel framework for edge-assisted MPC (E-MPC) for path planning that exploits the heterogeneity of edge networks in three important ways: 1) varying computational capacity, 2) localized sensor information, and 3) localized observation histories. Theoretical analysis and extensive simulations are undertaken to demonstrate quantitatively the benefits of E-MPC in various scenarios, including maps, channel dynamics, and availability and density of edge nodes. The results confirm that E-MPC has the potential to reduce costs by a greater percentage than standard MPC does.

Imitation learning has emerged as a powerful tool in machine learning, enabling agents to learn complex behaviors by imitating expert demonstrations acquired either from a human demonstrator or a policy computed offline [3, 11, 12, 13]. Despite its significant success, imitation learning often suffers from a compounding error problem: Successive evaluations of the approximate policy could accumulate error, resulting in out-of-distribution failures [3]. Recent results in imitation learning [31, 32, 34] have identified smoothness (i.e., Lipschitzness of the derivative of the optimal controller with respect to the initial state) and stability of the expert as two key properties that circumvent this issue, thereby allowing for end-to-end performance guarantees for the final learned controller. In this paper, our focus is on enabling such guarantees when the expert being imitated is a Model Predictive Controller (MPC), a powerful class of control algorithms based on solving an optimization problem over a receding prediction horizon [23]. In some cases, the solution to this multiparametric optimization problem, known as the explicit MPC representation [6], can be pre-computed. For instance, in our setup -- linear systems with polytopic constraints -- the optimal control input is a piecewise affine (and, hence, highly non-smooth) function of the state [6].

Previously, we showed that computational mechanic's causal states -- predictively-equivalent trajectory classes for a stochastic dynamical system -- can be cast into a reproducing kernel Hilbert space. The result is a widely-applicable method that infers causal structure directly from very different kinds of observations and systems. Here, we expand this method to explicitly introduce the causal diffusion components it produces. These encode the kernel causal-state estimates as a set of coordinates in a reduced dimension space. We show how each component extracts predictive features from data and demonstrate their application on four examples: first, a simple pendulum -- an exactly solvable system; second, a molecular-dynamic trajectory of $n$-butane -- a high-dimensional system with a well-studied energy landscape; third, the monthly sunspot sequence -- the longest-running available time series of direct observations; and fourth, multi-year observations of an active crop field -- a set of heterogeneous observations of the same ecosystem taken for over a decade. In this way, we demonstrate that the empirical kernel causal-states algorithm robustly discovers predictive structures for systems with widely varying dimensionality and stochasticity.

Geological Carbon Storage GCS is arguably the only scalable net-negative CO2 emission technology available While promising subsurface complexities and heterogeneity of reservoir properties demand a systematic approach to quantify uncertainty when optimizing production and mitigating storage risks which include assurances of Containment and Conformance of injected supercritical CO2 As a first step towards the design and implementation of a Digital Twin for monitoring underground storage operations a machine learning based data-assimilation framework is introduced and validated on carefully designed realistic numerical simulations As our implementation is based on Bayesian inference but does not yet support control and decision-making we coin our approach an uncertainty-aware Digital Shadow To characterize the posterior distribution for the state of CO2 plumes conditioned on multi-modal time-lapse data the envisioned Shadow combines techniques from Simulation-Based Inference SBI and Ensemble Bayesian Filtering to establish probabilistic baselines and assimilate multi-modal data for GCS problems that are challenged by large degrees of freedom nonlinear multi-physics non-Gaussianity and computationally expensive to evaluate fluid flow and seismic simulations To enable SBI for dynamic systems a recursive scheme is proposed where the Digital Shadows neural networks are trained on simulated ensembles for their state and observed data well and/or seismic Once training is completed the systems state is inferred when time-lapse field data becomes available In this computational study we observe that a lack of knowledge on the permeability field can be factored into the Digital Shadows uncertainty quantification To our knowledge this work represents the first proof of concept of an uncertainty-aware in-principle scalable Digital Shadow.