Search

Multi-agent systems often require agents to collaborate with or compete against other agents with diverse goals, behaviors, or strategies. Agent modeling is essential when designing adaptive policies for intelligent machine agents in multiagent systems, as this is the means by which the ego agent understands other agents' behavior and extracts their meaningful policy representations. These representations can be used to enhance the ego agent's adaptive policy which is trained by reinforcement learning. However, existing agent modeling approaches typically assume the availability of local observations from other agents (modeled agents) during training or a long observation trajectory for policy adaption. To remove these constrictive assumptions and improve agent modeling performance, we devised a Contrastive Learning-based Agent Modeling (CLAM) method that relies only on the local observations from the ego agent during training and execution. With these observations, CLAM is capable of generating consistent high-quality policy representations in real-time right from the beginning of each episode. We evaluated the efficacy of our approach in both cooperative and competitive multi-agent environments. Our experiments demonstrate that our approach achieves state-of-the-art on both cooperative and competitive tasks, highlighting the potential of contrastive learning-based agent modeling for enhancing reinforcement learning., Comment: 8 pages, 6 figures

Reliable molecular property prediction is essential for various scientific endeavors and industrial applications, such as drug discovery. However, the data scarcity, combined with the highly non-linear causal relationships between physicochemical and biological properties and conventional molecular featurization schemes, complicates the development of robust molecular machine learning models. Self-supervised learning (SSL) has emerged as a popular solution, utilizing large-scale, unannotated molecular data to learn a foundational representation of chemical space that might be advantageous for downstream tasks. Yet, existing molecular SSL methods largely overlook chemical knowledge, including molecular structure similarity, scaffold composition, and the context-dependent aspects of molecular properties when operating over the chemical space. They also struggle to learn the subtle variations in structure-activity relationship. This paper introduces a novel pre-training framework that learns robust and generalizable chemical knowledge. It leverages the structural hierarchy within the molecule, embeds them through distinct pre-training tasks across channels, and aggregates channel information in a task-specific manner during fine-tuning. Our approach demonstrates competitive performance across various molecular property benchmarks and offers strong advantages in particularly challenging yet ubiquitous scenarios like activity cliffs.

We study the limit behavior of the solutions to energy-critical complex Ginzburg-Landau equation. We give a rigorous theory of the zero-dispersion limit from energy-critical complex Ginzburg-Landau equation to energy-critical nonlinear heat equation for dimensions 3 and 4 in both the defocusing and focusing cases by energy method. Furthermore, we also show the invisicid limit of energy-critical complex Ginzburg-Landau equation to energy-critical nonlinear Schr\"odinger equation for dimension 4 in the focusing case.

Optical responses of atomically thin 2D materials are greatly influenced by electron-hole interactions. It is by far established that exciton signatures can be well-identified in the optical absorption spectrum of quasi-2D materials. However, the same level of understanding of excitonic effects on nonlinear optical responses and the ability to compute them accurately is still much desired. Based on the functional integral formalisms and working in the velocity gauge, we introduce a convenient Feynman diagram approach for calculating nonlinear responses including excitonic effects. By dressing electron-photon interactions with electron-hole ladder diagrams, we derive an expression for second-order optical responses and provide a comprehensive description of excitonic effects. We apply our approach to a monolayer h-BN model and show qualitative changes in the second harmonic generation spectrum when comparing with results assuming independent particles. Our approach can be readily extended to higher order optical responses and is feasible for first-principles calculations.

Coulomb interactions among electrons and holes in two-dimensional (2D) semimetals with overlapping valence and conduction bands can give rise to a correlated insulating ground state via exciton formation and condensation. One candidate material in which such excitonic state uniquely combines with non-trivial band topology are atomic monolayers of tungsten ditelluride (WTe2), in which a 2D topological excitonic insulator (2D TEI) forms. However, the detailed mechanism of the 2D bulk gap formation in WTe2, in particular with regard to the role of Coulomb interactions, has remained a subject of ongoing debate. Here, we show that WTe2 is susceptible to a gate-tunable quantum phase transition, evident from an abrupt collapse of its 2D bulk energy gap upon ambipolar field-effect doping. Such gate tunability of a 2D TEI, into either n- and p-type semimetals, promises novel handles of control over non-trivial 2D superconductivity with excitonic pairing., Comment: 8 pages, 4 figures, under submission

Integrating optical diffraction tomography with imaging flow cytometry enables label-free quantifications of the three-dimensional (3D) morphology and hemoglobin content of red blood cells (RBCs) in their natural form. Self-rotation of RBCs flowing in a microfluidic channel has been utilized to achieve various projection directions for 3D reconstruction. However, the practicality of this technique has not been sufficiently studied. We improved the accuracy of estimating the rotation angle of RBCs and demonstrated 3D reconstructions of both healthy and glutaraldehyde-treated RBCs. Results showed the capability to quantify changes in RBC morphology, hemoglobin content, and membrane fluctuations generated by glutaraldehyde treatments, demonstrating the potential to detect changes frequently present in various RBC membrane disorders., Comment: 15 pages, 7 figures, for associated movie file, see https://drive.google.com/file/d/1B_f42p7ZSjCBOqHRMwl--Ib-7Fne0U--/view?usp=sharing

In this short note, we establish a sharp Morrey regularity theory for an even order elliptic system of Rivi\`ere type: \begin{equation*} \Delta^{m}u=\sum_{l=0}^{m-1}\Delta^{l}\left\langle V_{l},du\right\rangle +\sum_{l=0}^{m-2}\Delta^{l}\delta\left(w_{l}du\right)+f\qquad \text{in} B^{2m} \end{equation*} under minimal regularity assumptions on the coefficients functions V^l, w^l and that f belongs to certain Morrey space. This can be regarded as a further extension of the recent L^p-regularity theory obtained by Guo-Xiang-Zheng [15], and generalizes [7, 27] for second and fourth order elliptic systems., Comment: 12 pages

In this short note, we provide a partial extension of Rivi\`ere's convervation law in higher dimensions under certain Lorentz integrability condition for the connection matrix. As an application, we obtain a conservation law for weakly harmonic mappings around regular points in supercritical dimensions., Comment: 6 pages

This paper presents BELT, a novel model and learning framework for the pivotal topic of brain-to-language translation research. The translation from noninvasive brain signals into readable natural language has the potential to promote the application scenario as well as the development of brain-computer interfaces (BCI) as a whole. The critical problem in brain signal decoding or brain-to-language translation is the acquisition of semantically appropriate and discriminative EEG representation from a dataset of limited scale and quality. The proposed BELT method is a generic and efficient framework that bootstraps EEG representation learning using off-the-shelf large-scale pretrained language models (LMs). With a large LM's capacity for understanding semantic information and zero-shot generalization, BELT utilizes large LMs trained on Internet-scale datasets to bring significant improvements to the understanding of EEG signals. In particular, the BELT model is composed of a deep conformer encoder and a vector quantization encoder. Semantical EEG representation is achieved by a contrastive learning step that provides natural language supervision. We achieve state-of-the-art results on two featuring brain decoding tasks including the brain-to-language translation and zero-shot sentiment classification. Specifically, our model surpasses the baseline model on both tasks by 5.45% and over 10% and archives a 42.31% BLEU-1 score and 67.32% precision on the main evaluation metrics for translation and zero-shot sentiment classification respectively., Comment: We decided to redraw the manuscript because of the multi-error in the paper due to poor writing and inspection

Drug discovery is a highly complicated process, and it is unfeasible to fully commit it to the recently developed molecular generation methods. Deep learning-based lead optimization takes expert knowledge as a starting point, learning from numerous historical cases about how to modify the structure for better drug-forming properties. However, compared with the more established de novo generation schemes, lead optimization is still an area that requires further exploration. Previously developed models are often limited to resolving one (or few) certain subtask(s) of lead optimization, and most of them can only generate the two-dimensional structures of molecules while disregarding the vital protein-ligand interactions based on the three-dimensional binding poses. To address these challenges, we present a novel tool for lead optimization, named Delete (Deep lead optimization enveloped in protein pocket). Our model can handle all subtasks of lead optimization involving fragment growing, linking, and replacement through a unified deleting (masking) strategy, and is aware of the intricate pocket-ligand interactions through the geometric design of networks. Statistical evaluations and case studies conducted on individual subtasks demonstrate that Delete has a significant ability to produce molecules with superior binding affinities to protein targets and reasonable drug-likeness from given fragments or atoms. This feature may assist medicinal chemists in developing not only me-too/me-better products from existing drugs but also hit-to-lead for first-in-class drugs in a highly efficient manner.

In this article, we prove the existence of global weak solutions to the three-dimensional focusing energy-critical nonlinear Schr\"odinger (NLS) equation in the non-radial case. Furthermore, we prove the weak-strong uniqueness for some class of initial data. The main ingredient of our new approach is to use solutions of an energy-critical Ginzburg-Landau equation as approximations for the corresponding nonlinear Sch\"ordinger equation. In our proofs, we first show the dichotomy of global well-posedness versus finite time blow-up of energy-critical Ginzburg-Landau equation in $\dot{H}^1( \mathbb{R}^d)$ for $d = 3,4 $ when the energy is less than the energy of the stationary solution $W$. We follow the strategy of C. E. Kenig and F. Merle [25,26], using a concentration-compactness/rigidity argument to reduce the global well-posedness to the exclusion of a critical element. The critical element is ruled out by dissipation of the Ginzburg-Landau equation, including local smoothness, backwards uniqueness and unique continuation. The existence of global weak solution of the three dimensional focusing energy-critical nonlinear Schr\"odinger equation in the non-radial case then follows from the global well-posedness of the energy-critical Ginzburg-Landau equation via a limitation argument. We also adapt the arguments of M. Struwe [37,38] to prove the weak-strong uniqueness when the $\dot{H}^1$-norm of the initial data is bounded by a constant depending on the stationary solution $W$., Comment: 35 pages

We introduce a general framework called neural network (NN) encoded variational quantum algorithms (VQAs), or NN-VQA for short, to address the challenges of implementing VQAs on noisy intermediate-scale quantum (NISQ) computers. Specifically, NN-VQA feeds input (such as parameters of a Hamiltonian) from a given problem to a neural network and uses its outputs to parameterize an ansatz circuit for the standard VQA. Combining the strengths of NN and parameterized quantum circuits, NN-VQA can dramatically accelerate the training process of VQAs and handle a broad family of related problems with varying input parameters with the pre-trained NN. To concretely illustrate the merits of NN-VQA, we present results on NN-variational quantum eigensolver (VQE) for solving the ground state of parameterized XXZ spin models. Our results demonstrate that NN-VQE is able to estimate the ground-state energies of parameterized Hamiltonians with high precision without fine-tuning, and significantly reduce the overall training cost to estimate ground-state properties across the phases of XXZ Hamiltonian. We also employ an active-learning strategy to further increase the training efficiency while maintaining prediction accuracy. These encouraging results demonstrate that NN-VQAs offer a new hybrid quantum-classical paradigm to utilize NISQ resources for solving more realistic and challenging computational problems., Comment: 4.4 pages, 5 figures, with supplemental materials

Multi-agent reinforcement learning (MARL) achieves encouraging performance in solving complex tasks. However, the safety of MARL policies is one critical concern that impedes their real-world applications. Popular multi-agent benchmarks focus on diverse tasks yet provide limited safety support. Therefore, this work proposes a safety-constrained multi-agent environment: MatrixWorld, based on the general pursuit-evasion game. Particularly, a safety-constrained multi-agent action execution model is proposed for the software implementation of safe multi-agent environments based on diverse safety definitions. It (1) extends the vertex conflict among homogeneous / cooperative agents to heterogeneous / adversarial settings, and (2) proposes three types of resolutions for each type of conflict, aiming at providing rational and unbiased feedback for safe MARL. Besides, MatrixWorld is also a lightweight co-evolution framework for the learning of pursuit tasks, evasion tasks, or both, where more pursuit-evasion variants can be designed based on different practical meanings of safety. As a brief survey, we review and analyze the co-evolution mechanism in the multi-agent setting, which clearly reveals its relationships with autocurricula, self-play, arms races, and adversarial learning. Thus, MatrixWorld can also serve as the first environment for autocurricula research, where ideas can be quickly verified and well understood.

In this study, we develop an active reconfigurable intelligent surface (RIS)-assisted multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) prototype compliant with the 5G New Radio standard at 3.5~GHz. The experimental results clearly indicate that active RIS plays a vital role in enhancing MIMO performance, surpassing passive RIS. Furthermore, when considering factors such as complexity, energy consumption, and performance, the comparative evaluation between passive RIS and active RIS reinforces the critical role of active RIS in MIMO systems. These findings underscore the practical significance of active RIS in improving MIMO gain in 5G scenarios., Comment: 5 pages, 5 figures, 1 table, accepted by IEEE Communications Letters, for demo video see: https://www.youtube.com/watch?v=3R6eZXizwns