Search

Molecular optimization (MO) is a crucial stage in drug discovery in which task-oriented generated molecules are optimized to meet practical industrial requirements. Existing mainstream MO approaches primarily utilize external property predictors to guide iterative property optimization. However, learning all molecular samples in the vast chemical space is unrealistic for predictors. As a result, errors and noise are inevitably introduced during property prediction due to the nature of approximation. This leads to discrepancy accumulation, generalization reduction and suboptimal molecular candidates. In this paper, we propose a text-guided multi-property molecular optimization method utilizing transformer-based diffusion language model (TransDLM). TransDLM leverages standardized chemical nomenclature as semantic representations of molecules and implicitly embeds property requirements into textual descriptions, thereby preventing error propagation during diffusion process. Guided by physically and chemically detailed textual descriptions, TransDLM samples and optimizes encoded source molecules, retaining core scaffolds of source molecules and ensuring structural similarities. Moreover, TransDLM enables simultaneous sampling of multiple molecules, making it ideal for scalable, efficient large-scale optimization through distributed computation on web platforms. Furthermore, our approach surpasses state-of-the-art methods in optimizing molecular structural similarity and enhancing chemical properties on the benchmark dataset. The code is available at: https://anonymous.4open.science/r/TransDLM-A901.

Non-Hermitian skin effect (NHSE), i.e., the localization of eigenstates near lattice boundaries, has recently spurred tremendous interest in topological physics. Beyond the well-explored linear NHSE, the interplay of nonlinearity and skin localization represents a cutting-edge area of research, offering novel insights into wave propagation and localization control in various physical systems. Unlike the linear NHSE successfully observed in weak-power optical systems, the observation of nonlinear NHSE and resulting skin solitons remains so far elusive, mainly due to the high energy levels required in most of nonlinear effects. Here we report the experimental demonstration of nonlinear NHSE in a Kerr nonlinear temporal photonic lattice, where the high-power limitation and lack of tunability intrinsic to optical materials are overcome by an artificial nonlinearity arising from opto-electronic feedback. Thanks to Kerr self-trapping, the nonlinear NHSE is demonstrated to possess much better localization strength and robustness at the preferred boundary compared to the linear case. Away from the preferred boundary, Kerr self-trapping can even inhibit NHSE-induced transport and form stable skin solitons. Harnessing the nonlinearity-controlled NHSE, we judiciously design an optical router with a flexibly-tuned output port. Our findings promise great applications in robust signal transmission, routing, and processing.

After the discovery of the ARECh2 (A=alkali or monovalent ions, RE=rare-earth, Ch= chalcogen) triangular lattice quantum spin liquid (QSL) family, a series of its oxide, sulfide, and selenide counterparts has been consistently reported and extensively investigated. While KErTe2 represents the initial synthesized telluride member, preserving its triangular spin lattice, it was anticipated that the substantial tellurium ions could impart more pronounced magnetic attributes and electronic structures to this material class. This study delves into the magnetism of KErTe2 at finite temperatures through magnetization and electron spin resonance (ESR) measurements. Based on the angular momentum $\hat{J}$ after spin-orbit coupling (SOC) and symmetry analysis, we obtain the magnetic effective Hamiltonian to describe the magnetism of Er3+ in R-3m space group. Applying the mean-field approximation to the Hamiltonian, we can simulate the magnetization and magnetic heat capacity of KErTe2 in paramagnetic state and determine the crystalline electric field (CEF) parameters and partial exchange interactions. The relatively narrow energy gaps between CEF ground state and excited states exert a significant influence on the magnetism. For example, small CEF excitations can result in a significant broadening of the ESR linewidth at 2 K. For the fitted exchange interactions, although the values are small, given a large angular momentum J = 15/2 after SOC, they still have a noticeable effect at finite temperatures. Notably, the heat capacity data under different magnetic fields along the c-axis direction also roughly match our calculated results, further validating the reliability of our analytical approach. These derived parameters serve as crucial tools for future investigations into the ground state magnetism of KErTe2., Comment: 11 pages, 6 figures

Enlarging bandwidth capacity of the integrated photonic systems demands efficient and broadband light coupling among optical elements, which has been a vital issue in integrated photonics. Here, we have developed a compact ultra-broadband light coupling strategy based on nonadiabatic pumping in coupled optical waveguides, and experimentally demonstrated the designs in thin-film lithium niobate on insulator (LNOI) platform. We found that nonadiabatic transition would produce a decreased dispersion of the phases related to eigenstates in the waveguides. As a consequence, we realized high-efficiency directional transfer between edgestates for various wavelengths covering a 1-dB bandwidth of ~320 nm in experiment (>400 nm in simulation), with a coupling length (~50 {\mu}m) approximately 1/10 of that required in the adiabatic regime. Furthermore, we have constructed complex functional devices including beamsplitter and multiple-level cascaded networks for broadband light routing and splitting. Our work preserves significant advantages simultaneously in extending the operation bandwidth and minimizing the footprint, which demonstrates great potential for large-scale and compact photonic integration on chip.

Out-of-distribution (OOD) generalization has attracted increasing research attention in recent years, due to its promising experimental results in real-world applications. In this paper,we study the confidence set prediction problem in the OOD generalization setting. Split conformal prediction (SCP) is an efficient framework for handling the confidence set prediction problem. However, the validity of SCP requires the examples to be exchangeable, which is violated in the OOD setting. Empirically, we show that trivially applying SCP results in a failure to maintain the marginal coverage when the unseen target domain is different from the source domain. To address this issue, we develop a method for forming confident prediction sets in the OOD setting and theoretically prove the validity of our method. Finally, we conduct experiments on simulated data to empirically verify the correctness of our theory and the validity of our proposed method.

Microscopic traffic simulation plays a crucial role in transportation engineering by providing insights into individual vehicle behavior and overall traffic flow. However, creating a realistic simulator that accurately replicates human driving behaviors in various traffic conditions presents significant challenges. Traditional simulators relying on heuristic models often fail to deliver accurate simulations due to the complexity of real-world traffic environments. Due to the covariate shift issue, existing imitation learning-based simulators often fail to generate stable long-term simulations. In this paper, we propose a novel approach called learner-aware supervised imitation learning to address the covariate shift problem in multi-agent imitation learning. By leveraging a variational autoencoder simultaneously modeling the expert and learner state distribution, our approach augments expert states such that the augmented state is aware of learner state distribution. Our method, applied to urban traffic simulation, demonstrates significant improvements over existing state-of-the-art baselines in both short-term microscopic and long-term macroscopic realism when evaluated on the real-world dataset pNEUMA., Comment: Accepted by CVPR 2024. arXiv admin note: text overlap with arXiv:2306.06401

The promising application of femtosecond laser filamentation in atmospheric remote sensing brings imperative demand for diagnosing the spatiotemporal dynamics of filamentation. Acoustic emission (AE) during filamentation opens a door to give the insight into the dynamic evolution of filaments in air. In particular, the frequency features of the acoustic emission provide relevant information on the conversion of laser energy to acoustic energy. Here, the acoustic emission of femtosecond laser filament manipulated by energy and the focal lengths was measured quantitatively by a broadband microphone, and the acoustic parameters were compared and analyzed. Our results showed that the acoustic power presents a squared dependence on the laser energy and the bandwidth of the acoustic spectrum showed a significant positive correlation with laser energy deposition. It was found that the spectrum of the acoustic pulse emitted from the middle of the filament has a larger bandwidth compared to those emitted from the ends of the filament and the spectrum of the acoustic pulse is also an indicator of the filament intensity distribution. These findings are helpful for studying the plasma filament properties and complex dynamic processes through acoustic parameters and allow the optimization of remote applications., Comment: 8 pages,5 figures

The field of cooperative multi-agent reinforcement learning (MARL) has seen widespread use in addressing complex coordination tasks. While value decomposition methods in MARL have been popular, they have limitations in solving tasks with non-monotonic returns, restricting their general application. Our work highlights the significance of joint intentions in cooperation, which can overcome non-monotonic problems and increase the interpretability of the learning process. To this end, we present a novel MARL method that leverages learnable joint intentions. Our method employs a hierarchical framework consisting of a joint intention policy and a behavior policy to formulate the optimal cooperative policy. The joint intentions are autonomously learned in a latent space through unsupervised learning and enable the method adaptable to different agent configurations. Our results demonstrate significant performance improvements in both the StarCraft micromanagement benchmark and challenging MAgent domains, showcasing the effectiveness of our method in learning meaningful joint intentions.

This manuscript demonstrates the theory, design, and simulation of scattering scanning near field microscopy (s-SNOM) in 0.5THz. A comprehensive simulation model of nanotips' geometry, sample materials, and incident field is established to significantly improve the scattering efficiency and spatial resolution to achieve optimal performance. The theoretical model is based on full-wave simulation and dipole moment analysis which can describe the overall nanotip's geometry information to screen the optimal parameters corresponding to the 0.5THz, which is the center frequency of most THz sources. The customized nanotip can achieve 40 nm $(\lambda / 15000)$ spatial resolution while maintaining an excellent scattering efficiency. This nanotip design method doesn't depend on the homogenization commercial AFM tips, providing an approach for customized nanotip design of THz wave scattering near field microscopy., Comment: 11page, 8figures

The femtosecond laser filamentation is the result of the dynamic interplay between plasma self-focusing and defocusing generated by the multiphoton/tunnel ionization of air molecules. This equilibrium allows the filament to stably propagate over long distances at high power densities, making it a promising tool for remote sensing in chemical and biological applications, detection of air pollution, and lightning control, which has attracted wide attention. Laser-induced filamentation is a highly nonlinear process, and initial conditions such as changes in polarization state can affect the fluorescence emission of N2 molecules excited by the filament in air. In this article, we analyze in detail the effect of polarization state changes on the 337 nm fluorescence signal excited by the filament at a distance of 30 m. It was found that the fluorescence signal intensity of the linear polarization state was higher than that of the circular polarization state. Through analysis of these phenomena, we explore the mechanism of plasma fluorescence emission during the long-range filamentation process of femtosecond laser, including the electron collision model and the polarization effect on the critical power for filamentation. These findings are important for the understanding of the stimulated radiation from filaments and may find applications in remote sensing of electric field and THz radiation., Comment: 11 pages, 3 figures

The effects of turbulence intensity and turbulence region on the distribution of femtosecond laser filaments are experimentally elaborated. Through the ultrasonic signals emitted by the filaments, and it is observed that increasing turbulence intensity and expanding turbulence active region cause an increase in the start position of the filament, and a decrease in filament length, which can be well explained by the theoretical calculation. It is also observed that the random perturbation of the air refractive index caused by atmospheric turbulence expanded the spot size of the filament. Additionally, when turbulence intensity reaches , multiple filaments are formed. Furthermore, the standard deviation of the transverse displacement of filament is found to be proportional to the square root of turbulent structure constant under the experimental turbulence parameters in this paper. These results contribute to the study of femtosecond laser propagation mechanisms in complex atmospheric turbulence conditions, Comment: 9 pages, 4 figures

Femtosecond laser filament-induced plasma spectroscopy (FIPS) demonstrates great potentials in the remote sensing for identifying atmospheric pollutant molecules. Due to the widespread aerosols in atmosphere, the remote detection based on FIPS would be affected from both the excitation and the propagation of fingerprint fluorescence, which still remain elusive. Here the physical model of filament-induced aerosol fluorescence is established to reveal the combined effect of Mie scattering and amplification spontaneous emission, which is then proved by the experimental results, the dependence of the backward fluorescence on the interaction length between filament and aerosols. These findings provide an insight into the complicated aerosol effect in the overall physical process of FIPS including propagation, excitation and emission, paving the way to its practical application in atmospheric remote sensing., Comment: 7 pages, 4 figures

A realistic long-term microscopic traffic simulator is necessary for understanding how microscopic changes affect traffic patterns at a larger scale. Traditional simulators that model human driving behavior with heuristic rules often fail to achieve accurate simulations due to real-world traffic complexity. To overcome this challenge, researchers have turned to neural networks, which are trained through imitation learning from human driver demonstrations. However, existing learning-based microscopic simulators often fail to generate stable long-term simulations due to the \textit{covariate shift} issue. To address this, we propose a history-masked multi-agent imitation learning method that removes all vehicles' historical trajectory information and applies perturbation to their current positions during learning. We apply our approach specifically to the urban traffic simulation problem and evaluate it on the real-world large-scale pNEUMA dataset, achieving better short-term microscopic and long-term macroscopic similarity to real-world data than state-of-the-art baselines., Comment: update

Sea salt aerosols composed mainly of micrometer-sized sodium chloride particles not only pose a potential threat to human health and traffic safety, but also directly affect climate prediction. The long-range and high-precision sensing of sea salt aerosols remains a challenge for existing composition analysis methods. As the development of ultrashort laser technology, femtosecond laser filamentation provides a new opportunity for molecular remote sensing in complex environments. However, the accuracy at long-distance of this method is still hard to meet the demand (<10 ng/m3) for the remote aerosol monitoring. To solve this problem, we built a remote detection system for sea salt aerosol fluorescence spectroscopy and obtained a very high system sensitivity by introducing a terawatt-class high-performance femtosecond laser and optimizing the filament and aerosol interaction length. The system achieves a Na+ detection limit of 0.015 ng/m3 at a detection distance of 30 m, and 0.006 ng/m3 when supplemented with a deep processing learning algorithm., Comment: 13 pages, 3 figures

Accidental exposure to overdose ionizing radiation will inevitably lead to severe biological damage, thus detecting and localizing radiation is essential. Traditional measurement techniques are generally restricted to the limited detection range of few centimeters, posing a great risk to operators. The potential in remote sensing makes femtosecond laser filament technology great candidates for constructively address this challenge. Here we propose a novel filament-based ionizing radiation sensing technology (FIRST), and clarify the interaction mechanism between filaments and ionizing radiation. Specifically, it is demonstrated that the energetic electrons and ions produced by {\alpha} radiation in air can be effectively accelerated within the filament, serving as seed electrons, which will markedly enhance nitrogen fluorescence. The extended nitrogen fluorescence lifetime of ~1 ns is also observed. These findings provide insights into the intricate interaction among ultra-strong light filed, plasma and energetic particle beam, and pave the way for the remote sensing of ionizing radiation., Comment: 13 pages, 6 figures

In partial multi-label learning (PML), each data example is equipped with a candidate label set, which consists of multiple ground-truth labels and other false-positive labels. Recently, graph-based methods, which demonstrate a good ability to estimate accurate confidence scores from candidate labels, have been prevalent to deal with PML problems. However, we observe that existing graph-based PML methods typically adopt linear multi-label classifiers and thus fail to achieve superior performance. In this work, we attempt to remove several obstacles for extending them to deep models and propose a novel deep Partial multi-Label model with grAph-disambIguatioN (PLAIN). Specifically, we introduce the instance-level and label-level similarities to recover label confidences as well as exploit label dependencies. At each training epoch, labels are propagated on the instance and label graphs to produce relatively accurate pseudo-labels; then, we train the deep model to fit the numerical labels. Moreover, we provide a careful analysis of the risk functions to guarantee the robustness of the proposed model. Extensive experiments on various synthetic datasets and three real-world PML datasets demonstrate that PLAIN achieves significantly superior results to state-of-the-art methods., Comment: IJCAI 2023

Deep networks are well-known to be fragile to adversarial attacks, and adversarial training is one of the most popular methods used to train a robust model. To take advantage of unlabeled data, recent works have applied adversarial training to contrastive learning (Adversarial Contrastive Learning; ACL for short) and obtain promising robust performance. However, the theory of ACL is not well understood. To fill this gap, we leverage the Rademacher complexity to analyze the generalization performance of ACL, with a particular focus on linear models and multi-layer neural networks under $\ell_p$ attack ($p \ge 1$). Our theory shows that the average adversarial risk of the downstream tasks can be upper bounded by the adversarial unsupervised risk of the upstream task. The experimental results validate our theory.

Tree fruit breeding is a long-term activity involving repeated measurements of various fruit quality traits on a large number of samples. These traits are traditionally measured by manually counting the fruits, weighing to indirectly measure the fruit size, and fruit colour is classified subjectively into different color categories using visual comparison to colour charts. These processes are slow, expensive and subject to evaluators' bias and fatigue. Recent advancements in deep learning can help automate this process. A method was developed to automatically count the number of sweet cherry fruits in a camera's field of view in real time using YOLOv3. A system capable of analyzing the image data for other traits such as size and color was also developed using Python. The YOLO model obtained close to 99% accuracy in object detection and counting of cherries and 90% on the Intersection over Union metric for object localization when extracting size and colour information. The model surpasses human performance and offers a significant improvement compared to manual counting., Comment: Published in 25th International Conference on Image Processing, Computer Vision, & Pattern Recognition (IPCV'21)

It has been recognized that the data generated by the denoising diffusion probabilistic model (DDPM) improves adversarial training. After two years of rapid development in diffusion models, a question naturally arises: can better diffusion models further improve adversarial training? This paper gives an affirmative answer by employing the most recent diffusion model which has higher efficiency ($\sim 20$ sampling steps) and image quality (lower FID score) compared with DDPM. Our adversarially trained models achieve state-of-the-art performance on RobustBench using only generated data (no external datasets). Under the $\ell_\infty$-norm threat model with $\epsilon=8/255$, our models achieve $70.69\%$ and $42.67\%$ robust accuracy on CIFAR-10 and CIFAR-100, respectively, i.e. improving upon previous state-of-the-art models by $+4.58\%$ and $+8.03\%$. Under the $\ell_2$-norm threat model with $\epsilon=128/255$, our models achieve $84.86\%$ on CIFAR-10 ($+4.44\%$). These results also beat previous works that use external data. We also provide compelling results on the SVHN and TinyImageNet datasets. Our code is available at https://github.com/wzekai99/DM-Improves-AT., Comment: ICML 2023

Deep Neural Networks (DNN) have been shown to be vulnerable to adversarial examples. Adversarial training (AT) is a popular and effective strategy to defend against adversarial attacks. Recent works (Benz et al., 2020; Xu et al., 2021; Tian et al., 2021) have shown that a robust model well-trained by AT exhibits a remarkable robustness disparity among classes, and propose various methods to obtain consistent robust accuracy across classes. Unfortunately, these methods sacrifice a good deal of the average robust accuracy. Accordingly, this paper proposes a novel framework of worst-class adversarial training and leverages no-regret dynamics to solve this problem. Our goal is to obtain a classifier with great performance on worst-class and sacrifice just a little average robust accuracy at the same time. We then rigorously analyze the theoretical properties of our proposed algorithm, and the generalization error bound in terms of the worst-class robust risk. Furthermore, we propose a measurement to evaluate the proposed method in terms of both the average and worst-class accuracies. Experiments on various datasets and networks show that our proposed method outperforms the state-of-the-art approaches., Comment: Accepted to AAAI 2023

In this work, sub-ppb aerosol detection is achieved by femtosecond laser filament with a single pulse energy of 4 mJ at a distance of 30 m. A concave mirror with an open aperture of 41.4 cm is employed in an off-axis optical system to focus the femtosecond laser beam and collect the fluorescence of NaCl aerosol. The simulation and experimental results show that the astigmatism can be greatly reduced when femtosecond laser beam is incident non-symmetrically on the concave mirror. Compared with the case that femtosecond laser strikes at the center of the concave mirror, the intensity of the optical filament is increased by 69.5 times, and the detection of limit of sodium chloride aerosol is reduced by 86%, which is down to 0.32 ppb. The improved excitation scheme in this work utilizes the nonsymmetrical beam spot on the concave mirror to compensate the non-symmetry induced by the off-axis setup, reducing the astigmatism of the focusing laser beam and improving the aerosol's detection of limit.