Search

In this work, we introduce Gemma 2, a new addition to the Gemma family of lightweight, state-of-the-art open models, ranging in scale from 2 billion to 27 billion parameters. In this new version, we apply several known technical modifications to the Transformer architecture, such as interleaving local-global attentions (Beltagy et al., 2020a) and group-query attention (Ainslie et al., 2023). We also train the 2B and 9B models with knowledge distillation (Hinton et al., 2015) instead of next token prediction. The resulting models deliver the best performance for their size, and even offer competitive alternatives to models that are 2-3 times bigger. We release all our models to the community.

In this technical report, we detail our first-place solution for the 2024 Waymo Open Dataset Challenge's semantic segmentation track. We significantly enhanced the performance of Point Transformer V3 on the Waymo benchmark by implementing cutting-edge, plug-and-play training and inference technologies. Notably, our advanced version, Point Transformer V3 Extreme, leverages multi-frame training and a no-clipping-point policy, achieving substantial gains over the original PTv3 performance. Additionally, employing a straightforward model ensemble strategy further boosted our results. This approach secured us the top position on the Waymo Open Dataset semantic segmentation leaderboard, markedly outperforming other entries., Comment: 1st Place Solution for 2024 Waymo Open Dataset Challenge in Semantic Segmentation

In the realm of autonomous driving, accurate 3D perception is the foundation. However, developing such models relies on extensive human annotations -- a process that is both costly and labor-intensive. To address this challenge from a data representation learning perspective, we introduce SuperFlow, a novel framework designed to harness consecutive LiDAR-camera pairs for establishing spatiotemporal pretraining objectives. SuperFlow stands out by integrating two key designs: 1) a dense-to-sparse consistency regularization, which promotes insensitivity to point cloud density variations during feature learning, and 2) a flow-based contrastive learning module, carefully crafted to extract meaningful temporal cues from readily available sensor calibrations. To further boost learning efficiency, we incorporate a plug-and-play view consistency module that enhances the alignment of the knowledge distilled from camera views. Extensive comparative and ablation studies across 11 heterogeneous LiDAR datasets validate our effectiveness and superiority. Additionally, we observe several interesting emerging properties by scaling up the 2D and 3D backbones during pretraining, shedding light on the future research of 3D foundation models for LiDAR-based perception., Comment: ECCV 2024; 36 pages, 11 figures, 11 tables; Code at https://github.com/Xiangxu-0103/SuperFlow

Despite extensive exploration of acoustic vortices carrying orbital angular momentum (OAM), the generation of acoustic vortices with OAM orientations beyond the conventional longitudinal direction remains largely unexplored. Spatiotemporal (ST) vortices, featuring spiral phase twisting in the ST domain and carrying transverse OAM, have recently attracted considerable interest in optics and acoustics. Here, we report the generation of three-dimensional (3D) ST acoustic vortices with arbitrarily oriented OAM, thereby opening up a new dimension in acoustic OAM control. By utilizing a two-dimensional (2D) acoustic phased array, we introduce two approaches to manipulate the orientation of OAM: through the direct rotation of vortices in 3D space and the intersection of vortices carrying distinct types of OAM. These methods enable unprecedented control over the orientation of acoustic OAM, providing a new degree of freedom in the manipulation of acoustic waves. The arbitrarily oriented OAM holds promise for enhancing acoustic communication by broadening capacity and enabling more complex particle manipulation techniques. Our work establishes a foundation for future explorations into the complex dynamics of novel structured acoustic fields in the ST domain.

The yield stress anomaly of L12 intermetallics such as Ni3Al or Ni3Ga is controlled by the so-called Kear-Wilsdorf lock (KWL), of which the formation and unlocking are governed by dislocation cross-slip. Despite the importance of L12 intermetallics for strengthening Ni-based superalloys, microscopic understanding of the KWL is limited. Here, molecular dynamics simulations are conducted by employing a dedicated machine-learning interatomic potential derived via physically-informed active-learning. The potential facilitates modelling of the dislocation behavior in Ni3Al with near ab initio accuracy. KWL formation and unlocking are observed and analyzed. The unlocking stress demonstrates a pronounced temperature dependence, contradicting the assumptions of existing analytical models. A phenomenological model is proposed to effectively describe the atomistic unlocking stresses and extrapolate them to the macroscopic scale. The model is general and applicable to other L12 intermetallics. The acquired knowledge of KWLs provides a deeper understanding on the origin of the yield stress anomaly.

Protecting digital identities of human face from various attack vectors is paramount, and face anti-spoofing plays a crucial role in this endeavor. Current approaches primarily focus on detecting spoofing attempts within individual frames to detect presentation attacks. However, the emergence of hyper-realistic generative models capable of real-time operation has heightened the risk of digitally generated attacks. In light of these evolving threats, this paper aims to address two key aspects. First, it sheds light on the vulnerabilities of state-of-the-art face anti-spoofing methods against digital attacks. Second, it presents a comprehensive taxonomy of common threats encountered in face anti-spoofing systems. Through a series of experiments, we demonstrate the limitations of current face anti-spoofing detection techniques and their failure to generalize to novel digital attack scenarios. Notably, the existing models struggle with digital injection attacks including adversarial noise, realistic deepfake attacks, and digital replay attacks. To aid in the design and implementation of robust face anti-spoofing systems resilient to these emerging vulnerabilities, the paper proposes key design principles from model accuracy and robustness to pipeline robustness and even platform robustness. Especially, we suggest to implement the proactive face anti-spoofing system using active sensors to significant reduce the risks for unseen attack vectors and improve the user experience., Comment: Under review

In the rapidly evolving field of autonomous driving, precise segmentation of LiDAR data is crucial for understanding complex 3D environments. Traditional approaches often rely on disparate, standalone codebases, hindering unified advancements and fair benchmarking across models. To address these challenges, we introduce MMDetection3D-lidarseg, a comprehensive toolbox designed for the efficient training and evaluation of state-of-the-art LiDAR segmentation models. We support a wide range of segmentation models and integrate advanced data augmentation techniques to enhance robustness and generalization. Additionally, the toolbox provides support for multiple leading sparse convolution backends, optimizing computational efficiency and performance. By fostering a unified framework, MMDetection3D-lidarseg streamlines development and benchmarking, setting new standards for research and application. Our extensive benchmark experiments on widely-used datasets demonstrate the effectiveness of the toolbox. The codebase and trained models have been publicly available, promoting further research and innovation in the field of LiDAR segmentation for autonomous driving., Comment: Preprint; 17 pages, 4 figures, 7 tables; Code at https://github.com/open-mmlab/mmdetection3d

Mutual localization serves as the foundation for collaborative perception and task assignment in multi-robot systems. Effectively utilizing limited onboard sensors for mutual localization between marker-less robots is a worthwhile goal. However, due to inadequate consideration of large scale variations of the observed robot and localization refinement, previous work has shown limited accuracy when robots are equipped only with RGB cameras. To enhance the precision of localization, this paper proposes a novel rendezvous-based hierarchical architecture for mutual localization (RHAML). Firstly, to learn multi-scale robot features, anisotropic convolutions are introduced into the network, yielding initial localization results. Then, the iterative refinement module with rendering is employed to adjust the observed robot poses. Finally, the pose graph is conducted to globally optimize all localization results, which takes into account multi-frame observations. Therefore, a flexible architecture is provided that allows for the selection of appropriate modules based on requirements. Simulations demonstrate that RHAML effectively addresses the problem of multi-robot mutual localization, achieving translation errors below 2 cm and rotation errors below 0.5 degrees when robots exhibit 5 m of depth variation. Moreover, its practical utility is validated by applying it to map fusion when multi-robots explore unknown environments., Comment: 8 pages, 8 figures, submitted to RA-L

Efficient data utilization is crucial for advancing 3D scene understanding in autonomous driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully supervised methods. Addressing this, our study extends into semi-supervised learning for LiDAR semantic segmentation, leveraging the intrinsic spatial priors of driving scenes and multi-sensor complements to augment the efficacy of unlabeled datasets. We introduce LaserMix++, an evolved framework that integrates laser beam manipulations from disparate LiDAR scans and incorporates LiDAR-camera correspondences to further assist data-efficient learning. Our framework is tailored to enhance 3D scene consistency regularization by incorporating multi-modality, including 1) multi-modal LaserMix operation for fine-grained cross-sensor interactions; 2) camera-to-LiDAR feature distillation that enhances LiDAR feature learning; and 3) language-driven knowledge guidance generating auxiliary supervisions using open-vocabulary models. The versatility of LaserMix++ enables applications across LiDAR representations, establishing it as a universally applicable solution. Our framework is rigorously validated through theoretical analysis and extensive experiments on popular driving perception datasets. Results demonstrate that LaserMix++ markedly outperforms fully supervised alternatives, achieving comparable accuracy with five times fewer annotations and significantly improving the supervised-only baselines. This substantial advancement underscores the potential of semi-supervised approaches in reducing the reliance on extensive labeled data in LiDAR-based 3D scene understanding systems., Comment: Preprint; 17 pages, 6 figures, 8 tables; Code at https://github.com/ldkong1205/LaserMix

Safety-critical 3D scene understanding tasks necessitate not only accurate but also confident predictions from 3D perception models. This study introduces Calib3D, a pioneering effort to benchmark and scrutinize the reliability of 3D scene understanding models from an uncertainty estimation viewpoint. We comprehensively evaluate 28 state-of-the-art models across 10 diverse 3D datasets, uncovering insightful phenomena that cope with both the aleatoric and epistemic uncertainties in 3D scene understanding. We discover that despite achieving impressive levels of accuracy, existing models frequently fail to provide reliable uncertainty estimates -- a pitfall that critically undermines their applicability in safety-sensitive contexts. Through extensive analysis of key factors such as network capacity, LiDAR representations, rasterization resolutions, and 3D data augmentation techniques, we correlate these aspects directly with the model calibration efficacy. Furthermore, we introduce DeptS, a novel depth-aware scaling approach aimed at enhancing 3D model calibration. Extensive experiments across a wide range of configurations validate the superiority of our method. We hope this work could serve as a cornerstone for fostering reliable 3D scene understanding. Code and benchmark toolkits are publicly available., Comment: Preprint; 37 pages, 8 figures, 11 tables; Code at https://github.com/ldkong1205/Calib3D

We present stability estimates for the inverse source problem of the stochastic Helmholtz equation in two and three dimensions by either near-field or far-field data. The random source is assumed to be a microlocally isotropic generalized Gaussian random function. For the direct problem, by exploring the regularity of the Green function, we demonstrate that the direct problem admits a unique bounded solution with an explicit integral representation, which enhances the existing regularity result. For the case using near-field data, the analysis of the inverse problem employs microlocal analysis to achieve an estimate for the Fourier transform of the micro-correlation strength by the near-field correlation data and a high-frequency tail. The stability follows by showing the analyticity of the data and applying a novel analytic continuation principle. The stability estimate by far-field data is derived by investigating the correlation of the far-field data. The stability estimate consists of the Lipschitz type data discrepancy and the logarithmic stability. The latter decreases as the upper bound of the frequency increases, which exhibits the phenomenon of increasing stability., Comment: 19pages

Predicting dissolved oxygen (DO) concentrations in north temperate lakes requires a comprehensive study of phenological patterns across various ecosystems, which highlights the significance of selecting phenological features and feature interactions. Process-based models are limited by partial process knowledge or oversimplified feature representations, while machine learning models face challenges in efficiently selecting relevant feature interactions for different lake types and tasks, especially under the infrequent nature of DO data collection. In this paper, we propose a Nature-Guided Cognitive Evolution (NGCE) strategy, which represents a multi-level fusion of adaptive learning with natural processes. Specifically, we utilize metabolic process-based models to generate simulated DO labels. Using these simulated labels, we implement a multi-population cognitive evolutionary search, where models, mirroring natural organisms, adaptively evolve to select relevant feature interactions within populations for different lake types and tasks. These models are not only capable of undergoing crossover and mutation mechanisms within intra-populations but also, albeit infrequently, engage in inter-population crossover. The second stage involves refining these models by retraining them with real observed labels. We have tested the performance of our NGCE strategy in predicting daily DO concentrations across a wide range of lakes in the Midwest, USA. These lakes, varying in size, depth, and trophic status, represent a broad spectrum of north temperate lakes. Our findings demonstrate that NGCE not only produces accurate predictions with few observed labels but also, through gene maps of models, reveals sophisticated phenological patterns of different lakes.

In this paper, we investigate well-posedness of time-harmonic scattering of elastic waves by unbounded rigid rough surfaces in three dimensions. The elastic scattering is caused by an $L^2$ function with a compact support in the $x_3$-direction, and both deterministic and random surfaces are investigated via the variational approach. The rough surface in a deterministic setting is assumed to be Lipschitz and lie within a finite distance of a flat plane, and the scattering is caused by an inhomogeneous term in the elastic wave equation whose support lies within some finite distance of the boundary. For the deterministic case, a stability estimate of elastic scattering by rough surface is shown at an arbitrary frequency. It is noticed that all constants in {\it a priori} bounds are bounded by explicit functions of the frequency and geometry of rough surfaces. Furthermore, based on this explicit dependence on the frequency together with the measurability and $\mathbb{P}$-essentially separability of the randomness, we obtain a similar bound for the solution of the scattering by random surfaces.

This paper presents BrepGen, a diffusion-based generative approach that directly outputs a Boundary representation (B-rep) Computer-Aided Design (CAD) model. BrepGen represents a B-rep model as a novel structured latent geometry in a hierarchical tree. With the root node representing a whole CAD solid, each element of a B-rep model (i.e., a face, an edge, or a vertex) progressively turns into a child-node from top to bottom. B-rep geometry information goes into the nodes as the global bounding box of each primitive along with a latent code describing the local geometric shape. The B-rep topology information is implicitly represented by node duplication. When two faces share an edge, the edge curve will appear twice in the tree, and a T-junction vertex with three incident edges appears six times in the tree with identical node features. Starting from the root and progressing to the leaf, BrepGen employs Transformer-based diffusion models to sequentially denoise node features while duplicated nodes are detected and merged, recovering the B-Rep topology information. Extensive experiments show that BrepGen advances the task of CAD B-rep generation, surpassing existing methods on various benchmarks. Results on our newly collected furniture dataset further showcase its exceptional capability in generating complicated geometry. While previous methods were limited to generating simple prismatic shapes, BrepGen incorporates free-form and doubly-curved surfaces for the first time. Additional applications of BrepGen include CAD autocomplete and design interpolation. The code, pretrained models, and dataset are available at https://github.com/samxuxiang/BrepGen., Comment: Accepted to ACM SIGGRAPH 2024. Code at https://github.com/samxuxiang/BrepGen

LiDAR segmentation has become a crucial component in advanced autonomous driving systems. Recent range-view LiDAR segmentation approaches show promise for real-time processing. However, they inevitably suffer from corrupted contextual information and rely heavily on post-processing techniques for prediction refinement. In this work, we propose FRNet, a simple yet powerful method aimed at restoring the contextual information of range image pixels using corresponding frustum LiDAR points. Firstly, a frustum feature encoder module is used to extract per-point features within the frustum region, which preserves scene consistency and is crucial for point-level predictions. Next, a frustum-point fusion module is introduced to update per-point features hierarchically, enabling each point to extract more surrounding information via the frustum features. Finally, a head fusion module is used to fuse features at different levels for final semantic prediction. Extensive experiments conducted on four popular LiDAR segmentation benchmarks under various task setups demonstrate the superiority of FRNet. Notably, FRNet achieves 73.3% and 82.5% mIoU scores on the testing sets of SemanticKITTI and nuScenes. While achieving competitive performance, FRNet operates 5 times faster than state-of-the-art approaches. Such high efficiency opens up new possibilities for more scalable LiDAR segmentation. The code has been made publicly available at https://github.com/Xiangxu-0103/FRNet., Comment: Preprint; 16 pages, 8 figures, 10 tables; Code at https://github.com/Xiangxu-0103/FRNet

The sequential recommendation system has been widely studied for its promising effectiveness in capturing dynamic preferences buried in users' sequential behaviors. Despite the considerable achievements, existing methods usually focus on intra-sequence modeling while overlooking exploiting global collaborative information by inter-sequence modeling, resulting in inferior recommendation performance. Therefore, previous works attempt to tackle this problem with a global collaborative item graph constructed by pre-defined rules. However, these methods neglect two crucial properties when capturing global collaborative information, i.e., adaptiveness and personalization, yielding sub-optimal user representations. To this end, we propose a graph-driven framework, named Adaptive and Personalized Graph Learning for Sequential Recommendation (APGL4SR), that incorporates adaptive and personalized global collaborative information into sequential recommendation systems. Specifically, we first learn an adaptive global graph among all items and capture global collaborative information with it in a self-supervised fashion, whose computational burden can be further alleviated by the proposed SVD-based accelerator. Furthermore, based on the graph, we propose to extract and utilize personalized item correlations in the form of relative positional encoding, which is a highly compatible manner of personalizing the utilization of global collaborative information. Finally, the entire framework is optimized in a multi-task learning paradigm, thus each part of APGL4SR can be mutually reinforced. As a generic framework, APGL4SR can outperform other baselines with significant margins. The code is available at https://github.com/Graph-Team/APGL4SR.

Topological maps are favorable for their small storage compared to geometric map. However, they are limited in relocalization and path planning capabilities. To solve this problem, a feature-based hierarchical topological map (FHT-Map) is proposed along with a real-time map construction algorithm for robot exploration. Specifically, the FHT-Map utilizes both RGB cameras and LiDAR information and consists of two types of nodes: main node and support node. Main nodes will store visual information compressed by convolutional neural network and local laser scan data to enhance subsequent relocalization capability. Support nodes retain a minimal amount of data to ensure storage efficiency while facilitating path planning. After map construction with robot exploration, the FHT-Map can be used by other robots for relocalization and path planning. Experiments are conducted in Gazebo simulator, and the results demonstrate that the proposed FHT-Map can effectively improve relocalization and path planning capability compared with other topological maps. Moreover, experiments on hierarchical architecture are implemented to show the necessity of two types of nodes., Comment: 8 pages, 7figures, 2 tables

Finding all possible UV resonances of effective operators is an important task in the bottom-up approach of effective field theory. We present all the tree-level UV resonances for the dimension-5, -6 and -7 operators in the Standard Model effective field theory (SMEFT), and then obtain the correspondence between the UV resonances and the effective operators from the relations among their Wilson coefficients, through the functional matching and operator reduction procedure. This provides a cross-dimension UV/IR dictionary for the SMEFT at tree-level, and the methods used here, especially the on-shell construction of general UV Lagrangian and the systematic reduction of operators, are extendable for UV resonances of $d \geq 8$ operators in SMEFT and other EFTs., Comment: 55 pages, 1 figure, 12 tables

This paper presents a novel generative model for Computer Aided Design (CAD) that 1) represents high-level design concepts of a CAD model as a three-level hierarchical tree of neural codes, from global part arrangement down to local curve geometry; and 2) controls the generation or completion of CAD models by specifying the target design using a code tree. Concretely, a novel variant of a vector quantized VAE with "masked skip connection" extracts design variations as neural codebooks at three levels. Two-stage cascaded auto-regressive transformers learn to generate code trees from incomplete CAD models and then complete CAD models following the intended design. Extensive experiments demonstrate superior performance on conventional tasks such as random generation while enabling novel interaction capabilities on conditional generation tasks. The code is available at https://github.com/samxuxiang/hnc-cad., Comment: Accepted to ICML 2023. Project website at https://hnc-cad.github.io/

POI tagging aims to annotate a point of interest (POI) with some informative tags, which facilitates many services related to POIs, including search, recommendation, and so on. Most of the existing solutions neglect the significance of POI images and seldom fuse the textual and visual features of POIs, resulting in suboptimal tagging performance. In this paper, we propose a novel Multi-Modal Model for POI Tagging, namely M3PT, which achieves enhanced POI tagging through fusing the target POI's textual and visual features, and the precise matching between the multi-modal representations. Specifically, we first devise a domain-adaptive image encoder (DIE) to obtain the image embeddings aligned to their gold tags' semantics. Then, in M3PT's text-image fusion module (TIF), the textual and visual representations are fully fused into the POIs' content embeddings for the subsequent matching. In addition, we adopt a contrastive learning strategy to further bridge the gap between the representations of different modalities. To evaluate the tagging models' performance, we have constructed two high-quality POI tagging datasets from the real-world business scenario of Ali Fliggy. Upon the datasets, we conducted the extensive experiments to demonstrate our model's advantage over the baselines of uni-modality and multi-modality, and verify the effectiveness of important components in M3PT, including DIE, TIF and the contrastive learning strategy., Comment: Accepted by KDD 2023

The Stirling engine, which possesses external combustion characteristics, a simple structure, and high theoretical thermal efficiency, has excellent potential for utilizing finite waste heat and cold resources. However, practical applications of this technology suffered from thermal inefficiency due to the discontinuity and instability of waste resources. Despite advances in energy storage technology, temperature variations in the heat-exchanging fluids at the hot and cold ends of the Stirling engine remained significant obstacles. In this work, convective meta-thermal concentration (CMTC) was introduced between the heating (cooling) fluids and the hot (cold) end of the Stirling engine, employing alternating isotropic materials with high and low thermal conductivities. It was demonstrated that CMTC effectively enhanced the temperature difference between the hot and cold ends, leading to a remarkable improvement in Stirling engine efficiency. Particularly, when the Stirling engine efficiency tended to zero due to the limited availability of waste heat and cold resources, CMTC overcame this limitation, surpassing existing optimization technology. Further analysis under various operating conditions showed that CMTC achieved a significant thermal efficiency improvement of up to 1460%. This work expanded the application of thermal metamaterials to heat engine systems, offering an exciting avenue for sustainable energy utilization.

In this paper, by constructing the weight functions, a global Carleman estimate for the Schrodinger equation on a tree is established, with a strong assumption on the solution. And the estimate is able to be applied to derive the Lipschitz stability for an inverse coefficients problem.

The main purpose of this work is to study an inverse coefficient problem for the telegrapher's equations on a tree-shaped network. To analyze the stability for this inverse problem, Carleman estimate is established first. Based upon this estimate, a Lipschitz stability is further derived with additional data given on partial boundary.

In this paper, we prove the singularity formation for Poiseuille laminar flow of full Ericksen-Leslie system modeling nematic liquid crystal flows in dimension two. The singularity is due to the geometric effect at the origin.

Based on the Rb$^+$-Rb hybrid trap, we investigate the effect of ion-atom elastic collisions on the number and temperature of the remaining atoms. We measured the remaining atomic number and temperature as a function of the wavelength and intensity of the ionization laser, and whether the ion trap was turned on. Fittings with a single exponential decay function plus an offset to the number and radius of the remaining atoms are found to be in good agreement. We found a difference in the exponential factor of different wavelengths of ionization laser with the ion trap on or off. We suppose that the presence of electrons affects ion-atom collisions through disorder-induced heating. Our research contributes to a better understanding of how ultracold neutral plasma evolves, particularly the subsequent kinetics of atomic processes, which also serves as a useful reference for high-energy-density plasma., Comment: 14 figures, 9 pages

This paper investigates the elastic scattering by unbounded deterministic and random rough surfaces, which both are assumed to be graphs of Lipschitz continuous functions. For the deterministic case, an a priori bound explicitly dependent on frequencies is derived by the variational approach. For the scattering by random rough surfaces with a random source, well-posedness of the corresponding variation problem is proved. Moreover, a similar bound with explicit dependence on frequencies for the random case is also established based upon the deterministic result, Pettis measurability theorem and Bochner's integrability Theorem.

The paper considers direct and inverse elastic scattering from a cavity in homogeneous medium with Dirichlet and Neumann boundary conditions. For direct scattering, existence and uniqueness are derived by variation approach. For inverse scattering, Fr$\acute{\rm e}$chet derivatives of the solution operators are investigated, which give local stability for Dirichlet case.

Multi-step phase transition provides a paradigm in which a broken symmetry during phase transition can be restored, enriching the phenomena of both dark matter and baryon asymmetry. We study the dynamics of the multi-step phase transition in the standard model extension with additional isospin $N$-plet scalar field $\Phi_2$ under a discrete $\mathbb{Z}_2$ symmetry. We find that the multi-step phase transition could be triggered if there is a moderately large coupling between the Higgs and the $\Phi_2$ and this coupling is required to be larger as the mass of the $\Phi_2$ and/or isospin increase. The first-order phase transition at the first (second) step can be realized by the thermal loop (tree-level barrier) effects. Thus it is more likely that a detectable spectrum of gravitational waves can be produced at the second step of the phase transition., Comment: 40 pages, 12 figures

Mammalian brain is a complex organ that contains billions of neurons. These neurons form various neural circuits that control the perception, cognition, emotion and behavior. Developing in vivo neuronal labeling and imaging techniques is crucial for studying the structure and function of neural circuits. In vivo techniques can provide true physiological information that cannot be provided by ex vivo methods. In this study, we describe a new strategy for in vivo neuronal labeling and quantification using MRI. To demonstrate the ability of this new method, we used neurotropic virus to deliver oatp1a1 gene to the target neural circuit. OATP1A1 protein is expressed on the neuronal membrane and can increase the uptake of a specific MRI contrast agent (Gd-EOB-DTPA). By using T1-weighted images for observation, labeled neurons "light up" on MRI. We further use a dynamic-contrast-enhancement based method to obtain measures that provide quantitative information of labeled neurons in vivo.

Stability results for the Helmholtz equations in both deterministic and random periodic structures are proved in this paper. Under the assumption of excluding resonances, by a variational method and Fourier analysis in the energy space, the stability estimate for the Helmholtz equation in a deterministic periodic structure is established. For the stochastic case, by introducing a variable transform, the variational formulation of the scattering problem in a random domain is reduced to that in a definite domain with random medium. Combining the stability result for the deteministic case with regularity and stochastic regularity of the scattering surface, Pettis measurability theorem and Bochner's Theorem further yield the stability result for the scattering problem by random periodic structures. Both stability estimates are explicit with respect to the wavenumber.

Local density-of-states (LDOS) is a fundamental spectral property that plays a central role in various physical phenomena such as wave-matter interactions. Here, we report on the direct measurement of the LDOS of acoustic systems and derive from which the fractional topological number in an acoustic Su-Schrieffer-Heeger system. The acoustic LDOS is quantified here with a state-of-the-art technique through the measurement of the volume flow rate and the acoustic pressure with a local excitation-probe configuration. Based on this method, we study the acoustic Purcell effect and establish experimentally the important relation between the near-field LDOS and the far-field acoustic emission power. Moreover, we detect the LDOS in the one-dimensional acoustic Su-Schrieffer-Heeger model and observe the fractional topological number of the system. Our work unveils the important role of the LDOS in acoustic phenomena and paves the way toward characterizing and tailoring the LDOS in topological systems.

We present SkexGen, a novel autoregressive generative model for computer-aided design (CAD) construction sequences containing sketch-and-extrude modeling operations. Our model utilizes distinct Transformer architectures to encode topological, geometric, and extrusion variations of construction sequences into disentangled codebooks. Autoregressive Transformer decoders generate CAD construction sequences sharing certain properties specified by the codebook vectors. Extensive experiments demonstrate that our disentangled codebook representation generates diverse and high-quality CAD models, enhances user control, and enables efficient exploration of the design space. The code is available at https://samxuxiang.github.io/skexgen., Comment: Accepted to ICML 2022

Using the functional method, one-loop matching of the type-I, -II and -III seesaw models are investigated and the results are presented in both the Green's and the Warsaw bases. Although these models generate the same dimension-5 Weinberg operator, they could induce quite different types of dimension-6 effective operators that can be utilized for model discrimination. We also find the threshold effects from one-loop matching could be significant, which turn out to allow triggering electroweak symmetry breaking radiatively in type-II seesaw while forbid that in type-I/-III models. An analytical criterion for such radiative symmetry breaking is also derived in type-II seesaw. Finally, we investigate the indirect signatures from different types of dimension-6 operators at high-energy colliders, low-energy precision experiments and forward physics facilities for model discrimination., Comment: 45 pages, 10 figures, 13 tables, with minor revision on matching results and updated references

We introduce D3D-HOI: a dataset of monocular videos with ground truth annotations of 3D object pose, shape and part motion during human-object interactions. Our dataset consists of several common articulated objects captured from diverse real-world scenes and camera viewpoints. Each manipulated object (e.g., microwave oven) is represented with a matching 3D parametric model. This data allows us to evaluate the reconstruction quality of articulated objects and establish a benchmark for this challenging task. In particular, we leverage the estimated 3D human pose for more accurate inference of the object spatial layout and dynamics. We evaluate this approach on our dataset, demonstrating that human-object relations can significantly reduce the ambiguity of articulated object reconstructions from challenging real-world videos. Code and dataset are available at https://github.com/facebookresearch/d3d-hoi.

This paper presents an explore-and-classify framework for structured architectural reconstruction from an aerial image. Starting from a potentially imperfect building reconstruction by an existing algorithm, our approach 1) explores the space of building models by modifying the reconstruction via heuristic actions; 2) learns to classify the correctness of building models while generating classification labels based on the ground-truth, and 3) repeat. At test time, we iterate exploration and classification, seeking for a result with the best classification score. We evaluate the approach using initial reconstructions by two baselines and two state-of-the-art reconstruction algorithms. Qualitative and quantitative evaluations demonstrate that our approach consistently improves the reconstruction quality from every initial reconstruction., Comment: 2021 International Conference on Computer Vision (ICCV 2021)

To realize first-order electroweak phase transition, it is necessary to generate a barrier in the thermal Higgs potential, which is usually triggered by scalar degree of freedom. We instead investigate phase transition patterns in pure fermion extensions of the standard model, and find that additional fermions with mass hierarchy and mixing could develop such barrier and realize strongly first-order phase transition in such models. In the Higgs potential with polynomial parametrization, the barrier can be generated in the following two patterns: (I) positive quadratic term, negative cubic term and positive quartic term or (II) positive quadratic term, negative quartic term and positive higher dimensional term, such as dimensional 6 operator., Comment: 26 pages, 9 figures

This paper is concerned with the inverse random source problem for a stochastic time fractional diffusion equation, where the source is assumed to be driven by a Gaussian random field. The direct problem is shown to be well-posed by examining the well-posedness and regularity of the solution for the equivalent stochastic two-point boundary value problem in the frequency domain. For the inverse problem, the Fourier modulus of the diffusion coefficient of the random source is proved to be uniquely determined by the variance of the Fourier transform of the boundary data. As a phase retrieval for the inverse problem, the PhaseLift method with random masks is applied to recover the diffusion coefficient from its Fourier modulus. Numerical experiments are reported to demonstrate the effectiveness of the proposed method.

We propose a new method to detect deepfake images using the cue of the source feature inconsistency within the forged images. It is based on the hypothesis that images' distinct source features can be preserved and extracted after going through state-of-the-art deepfake generation processes. We introduce a novel representation learning approach, called pair-wise self-consistency learning (PCL), for training ConvNets to extract these source features and detect deepfake images. It is accompanied by a new image synthesis approach, called inconsistency image generator (I2G), to provide richly annotated training data for PCL. Experimental results on seven popular datasets show that our models improve averaged AUC over the state of the art from 96.45% to 98.05% in the in-dataset evaluation and from 86.03% to 92.18% in the cross-dataset evaluation., Comment: ICCV 2021 Oral

In this paper we study a gradient flow generated by the Landau-de Gennes free energy that describes nematic liquid crystal configurations in the space of $Q$-tensors. This free energy density functional is composed of three quadratic terms as the elastic energy density part, and a singular potential in the bulk part that is considered as a natural enforcement of a physical constraint on the eigenvalues of $Q$. The system is a non-diagonal parabolic system with a singular potential which trends to infinity logarithmically when the eigenvalues of $Q$ approaches the physical boundary. We give a rigorous proof that for rather general initial data with possibly infinite free energy, the system has a unique strong solution after any positive time $t_0$. Furthermore, this unique strong solution detaches from the physical boundary after a sufficiently large time $T_0$. We also give estimate of the Hausdorff measure of the set where the solution touches the physical boundary and thus prove a partial regularity result of the solution in the intermediate stage $(0,T_0)$.

In this paper we revisit a singular bulk potential in the Landau-de Gennes free energy that describes nematic liquid crystal configurations in the framework of the Q-tensor order parameter. This singular potential, called Ball-Majumdar potential, is introduced in [3], and is considered as a natural enforcement of a physical constraint on the eigenvalues of symmetric, traceless Q-tensors. Specifically, we establish blowup rates of both this singular potential and its gradient as Q approaches its physical boundary.

This paper proposes a new and efficient numerical algorithm for recovering the damping coefficient from the spectrum of a damped wave operator, which is a classical Borg-Levinson inverse spectral problem. The algorithm is based on inverting a sequence of trace formulas, which are deduced by a recursive formula, bridging geometrical and spectrum information explicitly in terms of Fredholm integral equations. Numerical examples are presented to illustrate the efficiency of the proposed algorithm.

We present a mutual information-based framework for unsupervised image-to-image translation. Our MCMI approach treats single-cycle image translation models as modules that can be used recurrently in a multi-cycle translation setting where the translation process is bounded by mutual information constraints between the input and output images. The proposed mutual information constraints can improve cross-domain mappings by optimizing out translation functions that fail to satisfy the Markov property during image translations. We show that models trained with MCMI produce higher quality images and learn more semantically-relevant mappings compared to state-of-the-art image translation methods. The MCMI framework can be applied to existing unpaired image-to-image translation models with minimum modifications. Qualitative experiments and a perceptual study demonstrate the image quality improvements and generality of our approach using several backbone models and a variety of image datasets.

In this paper, we address a key limitation of existing 2D face recognition methods: robustness to occlusions. To accomplish this task, we systematically analyzed the impact of facial attributes on the performance of a state-of-the-art face recognition method and through extensive experimentation, quantitatively analyzed the performance degradation under different types of occlusion. Our proposed Occlusion-aware face REcOgnition (OREO) approach learned discriminative facial templates despite the presence of such occlusions. First, an attention mechanism was proposed that extracted local identity-related region. The local features were then aggregated with the global representations to form a single template. Second, a simple, yet effective, training strategy was introduced to balance the non-occluded and occluded facial images. Extensive experiments demonstrated that OREO improved the generalization ability of face recognition under occlusions by (10.17%) in a single-image-based setting and outperformed the baseline by approximately (2%) in terms of rank-1 accuracy in an image-set-based scenario., Comment: Technical Report

In this paper, we focus on improving the online face liveness detection system to enhance the security of the downstream face recognition system. Most of the existing frame-based methods are suffering from the prediction inconsistency across time. To address the issue, a simple yet effective solution based on temporal consistency is proposed. Specifically, in the training stage, to integrate the temporal consistency constraint, a temporal self-supervision loss and a class consistency loss are proposed in addition to the softmax cross-entropy loss. In the deployment stage, a training-free non-parametric uncertainty estimation module is developed to smooth the predictions adaptively. Beyond the common evaluation approach, a video segment-based evaluation is proposed to accommodate more practical scenarios. Extensive experiments demonstrated that our solution is more robust against several presentation attacks in various scenarios, and significantly outperformed the state-of-the-art on multiple public datasets by at least 40% in terms of ACER. Besides, with much less computational complexity (33% fewer FLOPs), it provides great potential for low-latency online applications., Comment: technical report

Thermoelectric materials (TMs) can uniquely convert waste heat into electricity, which provides a potential solution for the global energy crisis that is increasingly severe. Bulk Cu2Se, with ionic conductivity of Cu ions, exhibits a significant enhancement of its thermoelectric figure of merit zT by a factor of ~3 near its structural transition around 400 K. Here, we show a systematic study of the electronic structure of Cu2Se and its temperature evolution using high-resolution angle-resolved photoemission spectroscopy. Upon heating across the structural transition, the electronic states near the corner of the Brillouin zone gradually disappear, while the bands near the centre of Brillouin zone shift abruptly towards high binding energies and develop an energy gap. Interestingly, the observed band reconstruction well reproduces the temperature evolution of the Seebeck coefficient of Cu2Se, providing an electronic origin for the drastic enhancement of the thermoelectric performance near 400 K. The current results not only bridge among structural phase transition, electronic structures, and thermoelectric properties in a condensed matter system, but also provide valuable insights into the search and design of new generation of thermoelectric materials., Comment: To appear in Science Bulletin

In this paper we study the global well-posedness of the Allen-Cahn Ohta-Nakazawa model with two fixed nonlinear volume constraints. Utilizing the gradient flow structure of its free energy, we prove the existence and uniqueness of the solution by following De Giorgi's minimizing movement scheme in a novel way.

We study some maximum principle preserving and energy stable schemes for the Allen-Cahn-Ohta-Kawasaki model with fixed volume constraint. With the inclusion of a nonlinear term in the Ohta-Kawasaki free energy functional, we show that the Allen-Cahn-Ohta-Kawasaki dynamics is maximum principle preserving. We further design some first order energy stable numerical schemes which inherit the maximum principle preservation in both semi-discrete and fully-discrete levels. Furthermore, we apply the maximum principle preserving schemes to a general framework for binary systems with long-range interactions. We also present some numerical results to support our theoretical findings.

This paper develops an efficient numerical method for the inverse scattering problem of a time-harmonic plane wave incident on a perfectly reflecting random periodic structure. The method is based on a novel combination of the Monte Carlo technique for sampling the probability space, a continuation method with respect to the wavenumber, and the Karhunen-Lo$\grave{e}$ve expansion of the random structure, which reconstructs key statistical properties of the profile for the unknown random periodic structure from boundary measurements of the scattered fields away from the structure. Numerical results are presented to demonstrate the reliability and efficiency of the proposed method.

From late December, 2019, the novel Corona-Virus began to spread in the mainland of China. For predicting the trend of the Corona Virus spread, several time delay dynamic systems (TDD) are proposed. In this paper, we establish a novel fractional time delay dynamic system (FTDD) to describe the local outbreak of COVID-19. The fractional derivative is introduced to account for the sub-diffusion process of the confirmed and cured peoples growth. Based on the public health data by the government, we propose a stable reconstruction algorithm of the coefficients. The reconstructed coefficients are used to predict the trend of the Corona-Virus. The numerical results are in good agreement with the public data.

Misalignment angle will result in a considerable error for the integration of Doppler Velocity Log (DVL) and of Strapdown Inertial Navigation System (SINS). In this paper, a robust initial alignment method for SINS/DVL is proposed to solve a practical applicable issue, which is that the outputs of DVL are often corrupted by the outliers. Firstly, the alignment principle for SINS/DVL is summarized. Secondly, based on the principle of this alignment method, the apparent velocity model is investigated, and the parameters expression of the apparent velocity model are derived detailed. Using the apparent velocity model, the unknown parameters of the apparent velocity model are estimated by the developed Robust Kalman Filter (RKF), then the reconstructed observation vector, where the outliers are detected and isolated, is reconstructed by the estimated parameters. Based on the reconstructed observation vectors, the initial attitude is determined. Finally, the simulation and field tests are carried out to verify the performance of the proposed method. The test results are shown that the proposed method can detect and isolate the outliers effectively and get better performance than the previous work.