These documents have not been selected following the "most downloaded" principle, as instead is

These documents have not been selected following the "most downloaded" principle, as instead is

The advancement of deep neural network models in the last fifteen years has profoundly altered the scientific landscape of estimation, prediction and decision making, from the early success of image recognition (Krizhevsky et al., 2012; He et al., 2016), to the success of self-learning of board games (Silver et al., 2017), to machine translation (Wu et al., 2016), to generative AI (Ho et al., 2020), and to the success of protein structure prediction (Jumper et al., 2021), among many other developments. In many of these successes, there are no well-established mechanistic models to describe the underlying problem (for example, we do not fully understand how human brains translate from one language to another). As such, it is conceivable that such successes are attributable to deep neural networks' remarkable capabilities for universal function approximation. In contrast, the hand-crafted models that existed before deep neural networks (such as n-gram models (Katz, 1987; Brown et al., 1992; Bengio et al., 2000)) were too restricted to offer satisfactory approximation. How well do deep neural network models work when there are well-established mechanistic models (as in physical sciences, where decades of theoretical and experimental endeavor have yielded highly accurate mechanistic models in many cases) -- in particular, how do the inference and prediction results of deep neural network models compare to more statistical approaches in the presence of reliable mechanistic models -- is an interesting question.

Parameter estimation and trajectory reconstruction for data-driven dynamical systems governed by ordinary differential equations (ODEs) are essential tasks in fields such as biology, engineering, and physics. These inverse problems -- estimating ODE parameters from observational data -- are particularly challenging when the data are noisy, sparse, and the dynamics are nonlinear. We propose the Eigen-Fourier Physics-Informed Gaussian Process (EFiGP), an algorithm that integrates Fourier transformation and eigen-decomposition into a physics-informed Gaussian Process framework. This approach eliminates the need for numerical integration, significantly enhancing computational efficiency and accuracy. Built on a principled Bayesian framework, EFiGP incorporates the ODE system through probabilistic conditioning, enforcing governing equations in the Fourier domain while truncating high-frequency terms to achieve denoising and computational savings. The use of eigen-decomposition further simplifies Gaussian Process covariance operations, enabling efficient recovery of trajectories and parameters even in dense-grid settings. We validate the practical effectiveness of EFiGP on three benchmark examples, demonstrating its potential for reliable and interpretable modeling of complex dynamical systems while addressing key challenges in trajectory recovery and computational cost.

Graph clustering, a fundamental and challenging task in graph mining, aims to classify nodes in a graph into several disjoint clusters. In recent years, graph contrastive learning (GCL) has emerged as a dominant line of research in graph clustering and advances the new state-of-the-art. However, GCL-based methods heavily rely on graph augmentations and contrastive schemes, which may potentially introduce challenges such as semantic drift and scalability issues. Another promising line of research involves the adoption of modularity maximization, a popular and effective measure for community detection, as the guiding principle for clustering tasks. Despite the recent progress, the underlying mechanism of modularity maximization is still not well understood. In this work, we dig into the hidden success of modularity maximization for graph clustering. Our analysis reveals the strong connections between modularity maximization and graph contrastive learning, where positive and negative examples are naturally defined by modularity. In light of our results, we propose a community-aware graph clustering framework, coined MAGI, which leverages modularity maximization as a contrastive pretext task to effectively uncover the underlying information of communities in graphs, while avoiding the problem of semantic drift. Extensive experiments on multiple graph datasets verify the effectiveness of MAGI in terms of scalability and clustering performance compared to state-of-the-art graph clustering methods. Notably, MAGI easily scales a sufficiently large graph with 100M nodes while outperforming strong baselines.

Reaching consensus is key to multi-agent coordination. To accomplish a cooperative task, agents need to coherently select optimal joint actions to maximize the team reward. However, current cooperative multi-agent reinforcement learning (MARL) methods usually do not explicitly take consensus into consideration, which may cause miscoordination problem. In this paper, we propose a model-based consensus mechanism to explicitly coordinate multiple agents. The proposed Multi-agent Goal Imagination (MAGI) framework guides agents to reach consensus with an Imagined common goal. The common goal is an achievable state with high value, which is obtained by sampling from the distribution of future states. We directly model this distribution with a self-supervised generative model, thus alleviating the "curse of dimensinality" problem induced by multi-agent multi-step policy rollout commonly used in model-based methods. We show that such efficient consensus mechanism can guide all agents cooperatively reaching valuable future states. Results on Multi-agent Particle-Environments and Google Research Football environment demonstrate the superiority of MAGI in both sample efficiency and performance.

Since the arrival of ChatGPTChatGPTand especially the integration of GPT, theartificial intelligenceartificial intelligence of OpenAI in Bing, Google's management is on alert. AI dev teams were forced to rush out the Bard chatbot, with major issues as a result. Today, while the New York Times announces that SamsungSamsung may well replace Google with Bing as the default search engine on its smartphonessmartphones, the tension goes up a notch at the Internet giant. As a result, it seems that AIs will take an important place at the next conference. Still according to information from New York Timesmore than 160 Google employees are currently in the process of floorfloor on an AI directly integrated into the search engine.

Google is working on search changes to counter artificial intelligence (AI) rivals that pose a threat to the company's search engine, The New York Times reported. The Times reported that Samsung was considering using Microsoft's Bing instead of Google as its default search engine on its devices. This news comes after Microsoft announced plans to incorporate AI tools into its Bing search engine following Google's announcement of its own plans to launch AI-powered features in its search tools. The Times reviewed internal messages from Google employees, who reportedly responded with "panic" to the threat of Samsung pulling the Google engine. According to internal documents reviews by The Times, Google is updated its existing search engine with more features in a project called Magi.

As the Artificial Intelligence race heats up, Google is feeling the pressure, and the company is now reportedly working on a new AI-powered search engine. According to the latest reports, the Mountain View-based technology giant is in the process of creating a new AI-powered search engine as well as updating technology in the existing search platform. Internal documents indicate that the company has a project named Magi which is aimed at updating the existing search engine with the new technology and about 160 employees are currently working on it. The new features are being created by designers, engineers, and executives working in sprint rooms to tweak and test the new versions. After the changes, the search engine would offer a more personalized experience than the company's current service.

Facing renewed competition from Microsoft and OpenAI, Google is reportedly "racing" to build an "all-new" AI-powered search engine. According to The New York Times, the company is in the early stages of creating a search service that will attempt to anticipate what you want from it in hopes of offering "a far more personalized experience." The project has "no clear timetable." However, knowing that Google is also developing a suite of new AI features for its existing search engine under the codename "Magi." Among the features Google is developing is a chatbot that can answer software engineering questions and generate code snippets.