Search

The fusion of camera- and LiDAR-based detections offers a promising solution to mitigate tracking failures in 3D multi-object tracking (MOT). However, existing methods predominantly exploit camera detections to correct tracking failures caused by potential LiDAR detection problems, neglecting the reciprocal benefit of refining camera detections using LiDAR data. This limitation is rooted in their single-stage architecture, akin to single-stage object detectors, lacking a dedicated trajectory refinement module to fully exploit the complementary multi-modal information. To this end, we introduce CrossTracker, a novel two-stage paradigm for online multi-modal 3D MOT. CrossTracker operates in a coarse-to-fine manner, initially generating coarse trajectories and subsequently refining them through an independent refinement process. Specifically, CrossTracker incorporates three essential modules: i) a multi-modal modeling (M^3) module that, by fusing multi-modal information (images, point clouds, and even plane geometry extracted from images), provides a robust metric for subsequent trajectory generation. ii) a coarse trajectory generation (C-TG) module that generates initial coarse dual-stream trajectories, and iii) a trajectory refinement (TR) module that refines coarse trajectories through cross correction between camera and LiDAR streams. Comprehensive experiments demonstrate the superior performance of our CrossTracker over its eighteen competitors, underscoring its effectiveness in harnessing the synergistic benefits of camera and LiDAR sensors for robust multi-modal 3D MOT.

The calculation of (co)irreducible representations of energy bands at high-symmetry points (HSPs) is essential for high-throughput research on topological materials based on symmetry-indicators or topological quantum chemistry. However, existing computational packages usually require transforming crystal structures into specific conventions, thus hindering extensive application, especially to materials whose symmetries are yet to be identified. To address this issue, we developed a Mathematica package, \texttt{ToMSGKpoint}, capable of determining the little groups and (co)irreducible representations of little groups of HSPs, high-symmetry lines (HSLs), and high-symmetry planes (HSPLs) for any nonmagnetic and magnetic crystalline materials in two and three dimensions, with or without considering spin-orbit coupling. To the best of our knowledge, this is the first package to achieve such functionality. The package also provides magnetic space group operations, supports the analysis of (co)irreducible representations of energy bands at HSPs, HSLs, and HSPLs using electronic wavefunctions obtained from \textit{ab initio} calculations interfaced with VASP. Designed for user convenience, the package generates results in a few simple steps and presents all relevant information in clear tabular format. Its versatility is demonstrated through applications to nonmagnetic topological insulator Bi$_2$Se$_3$ and Dirac semimetal Na$_3$Bi, as well as the antiferromagnetic topological material MnBi$_2$Te$_4$. Suitable for any crystal structure, this package can be conveniently applied in a streamlined study once magnetic space group varies with various symmetry-breakings caused by phase transitions.

Spin-polarized particle beams are of interest for applications like deep-inelastic scattering, e.g. to gain further understanding of the proton's nuclear structure. With the advent of high-intensity laser facilities, laser-plasma-based accelerators offer a promising alternative to common radiofrequency-based accelerators, as they can shorten the required acceleration length significantly. However, in the scope of spin-polarized particles, they bring unique challenges. This paper reviews the developments in the field of spin-polarized particles on the basis of the interaction of laser pulses and high-energy particle beams with plasma. The relevant scaling laws for spin-dependent effects in laser-plasma interaction, as well as acceleration schemes for polarized leptons, ions and gamma quanta are discussed., Comment: 42 pages, 14 figures, submitted to Reports on Progress in Physics

The core of self-supervised point cloud learning lies in setting up appropriate pretext tasks, to construct a pre-training framework that enables the encoder to perceive 3D objects effectively. In this paper, we integrate two prevalent methods, masked point modeling (MPM) and 3D-to-2D generation, as pretext tasks within a pre-training framework. We leverage the spatial awareness and precise supervision offered by these two methods to address their respective limitations: ambiguous supervision signals and insensitivity to geometric information. Specifically, the proposed framework, abbreviated as PointCG, consists of a Hidden Point Completion (HPC) module and an Arbitrary-view Image Generation (AIG) module. We first capture visible points from arbitrary views as inputs by removing hidden points. Then, HPC extracts representations of the inputs with an encoder and completes the entire shape with a decoder, while AIG is used to generate rendered images based on the visible points' representations. Extensive experiments demonstrate the superiority of the proposed method over the baselines in various downstream tasks. Our code will be made available upon acceptance.

A perpendicular magnetic field penetrating a thin type-II superconductor slab produces vortices, with one vortex per flux quantum, h/2e. The vortices interact repulsively and form an ordered array (Abrikosov lattice) in clean systems, while strong disorder changes the lattice into a vortex glass. Here we investigate type-II superconducting films (PdBi2 and NbSe2) with surface acoustic waves (SAWs) at mK temperature. When sweeping the magnetic field at an extremely slow rate, we observe a series of spikes in the attenuation and velocity of the SAW, on average separated in field by approximately Hc1. We suspect the following scenario: The vortex-free region at the edges of the film produces an edge barrier across which the vortices can enter or leave. When the applied field changes, the induced supercurrents flowing along this edge region lowers this barrier until there is an instability. At that point, vortices avalanche into (or out of) the bulk and change the vortex crystal, suggested by the sharp jump in each such spike. The vortices then gradually relax to a new stable pinned configuration, leading to a ~30s relaxation after the jump. Our observation enriches the limited experimental evidence on the important topic of real-time vortex dynamics in superconductors.

Coherent wave control is of key importance across a broad range of fields such as electromagnetics, photonics, and acoustics. It enables us to amplify or suppress the outgoing waves via engineering amplitudes and phases of multiple incidences. However, within a purely spatially (temporally) engineered medium, coherent wave control requires the frequency of the associated incidences to be identical (opposite). In this work, we break this conventional constraint by generalizing coherent wave control into a spatiotemporally engineered medium, i.e., the system featuring a dynamic interface. Owing to the broken translational symmetry in space and time, both the subluminal and superluminal interfaces allow interference between scattered waves regardless of their different frequencies and wavevectors. Hence, one can flexibly eliminate the backward- or forward-propagating waves scattered from the dynamic interfaces by controlling the incident amplitudes and phases. Our work not only presents a generalized way for reshaping arbitrary waveforms but also provides a promising paradigm to generate ultrafast pulses using low-frequency signals. We have also implemented suppression of forward-propagating waves in microstrip transmission lines with fast photodiode switches.

Magnetoresistance (MR) oscillations serve as a hallmark of intrinsic quantum behavior, traditionally observed only in conducting systems. Here we report the discovery of MR oscillations in an insulating system, the vertical junctions of CrPS$_4$ which is a two dimensional (2D) A-type antiferromagnetic semiconductor. Systematic investigations of MR peaks under varying conditions, including electrode materials, magnetic field direction, temperature, voltage bias and layer number, elucidate a correlation between MR oscillations and spin-canted states in CrPS$_4$. Experimental data and analysis point out the important role of the in-gap electronic states in generating MR oscillations, and we proposed that spin selected interlayer hopping of localized defect states may be responsible for it. Our findings not only illuminate the unusual electronic transport in CrPS$_4$ but also underscore the potential of van der Waals magnets for exploring interesting phenomena., Comment: Accepted by Physical Review X

Domain adaptation is an inspiring solution to the misalignment issue of day/night image features for nighttime UAV tracking. However, the one-step adaptation paradigm is inadequate in addressing the prevalent difficulties posed by low-resolution (LR) objects when viewed from the UAVs at night, owing to the blurry edge contour and limited detail information. Moreover, these approaches struggle to perceive LR objects disturbed by nighttime noise. To address these challenges, this work proposes a novel progressive alignment paradigm, named domain-aware diffusion model (DaDiff), aligning nighttime LR object features to the daytime by virtue of progressive and stable generations. The proposed DaDiff includes an alignment encoder to enhance the detail information of nighttime LR objects, a tracking-oriented layer designed to achieve close collaboration with tracking tasks, and a successive distribution discriminator presented to distinguish different feature distributions at each diffusion timestep successively. Furthermore, an elaborate nighttime UAV tracking benchmark is constructed for LR objects, namely NUT-LR, consisting of 100 annotated sequences. Exhaustive experiments have demonstrated the robustness and feature alignment ability of the proposed DaDiff. The source code and video demo are available at https://github.com/vision4robotics/DaDiff.

As one of the most popular and sought-after generative models in the recent years, diffusion models have sparked the interests of many researchers and steadily shown excellent advantage in various generative tasks such as image synthesis, video generation, molecule design, 3D scene rendering and multimodal generation, relying on their dense theoretical principles and reliable application practices. The remarkable success of these recent efforts on diffusion models comes largely from progressive design principles and efficient architecture, training, inference, and deployment methodologies. However, there has not been a comprehensive and in-depth review to summarize these principles and practices to help the rapid understanding and application of diffusion models. In this survey, we provide a new efficiency-oriented perspective on these existing efforts, which mainly focuses on the profound principles and efficient practices in architecture designs, model training, fast inference and reliable deployment, to guide further theoretical research, algorithm migration and model application for new scenarios in a reader-friendly way. \url{https://github.com/ponyzym/Efficient-DMs-Survey}

In recent years there have been remarkable breakthroughs in image-to-video generation. However, the 3D consistency and camera controllability of generated frames have remained unsolved. Recent studies have attempted to incorporate camera control into the generation process, but their results are often limited to simple trajectories or lack the ability to generate consistent videos from multiple distinct camera paths for the same scene. To address these limitations, we introduce Cavia, a novel framework for camera-controllable, multi-view video generation, capable of converting an input image into multiple spatiotemporally consistent videos. Our framework extends the spatial and temporal attention modules into view-integrated attention modules, improving both viewpoint and temporal consistency. This flexible design allows for joint training with diverse curated data sources, including scene-level static videos, object-level synthetic multi-view dynamic videos, and real-world monocular dynamic videos. To our best knowledge, Cavia is the first of its kind that allows the user to precisely specify camera motion while obtaining object motion. Extensive experiments demonstrate that Cavia surpasses state-of-the-art methods in terms of geometric consistency and perceptual quality. Project Page: https://ir1d.github.io/Cavia/, Comment: Project Page: https://ir1d.github.io/Cavia/

The advent of large Vision-Language Models (VLMs) has significantly advanced multimodal understanding, enabling more sophisticated and accurate integration of visual and textual information across various tasks, including image and video captioning, visual question answering, and cross-modal retrieval. Despite VLMs' superior capabilities, researchers lack a comprehensive understanding of their compositionality -- the ability to understand and produce novel combinations of known visual and textual components. Prior benchmarks provide only a relatively rough compositionality evaluation from the perspectives of objects, relations, and attributes while neglecting deeper reasoning about object interactions, counting, and complex compositions. However, compositionality is a critical ability that facilitates coherent reasoning and understanding across modalities for VLMs. To address this limitation, we propose MMCOMPOSITION, a novel human-annotated benchmark for comprehensively and accurately evaluating VLMs' compositionality. Our proposed benchmark serves as a complement to these earlier works. With MMCOMPOSITION, we can quantify and explore the compositionality of the mainstream VLMs. Surprisingly, we find GPT-4o's compositionality inferior to the best open-source model, and we analyze the underlying reasons. Our experimental analysis reveals the limitations of VLMs in fine-grained compositional perception and reasoning, and points to areas for improvement in VLM design and training. Resources available at: https://hanghuacs.github.io/MMComposition/, Comment: 21 pages, 15 figures

Robotic manipulation, owing to its multi-modal nature, often faces significant training ambiguity, necessitating explicit instructions to clearly delineate the manipulation details in tasks. In this work, we highlight that vision instruction is naturally more comprehensible to recent robotic policies than the commonly adopted text instruction, as these policies are born with some vision understanding ability like human infants. Building on this premise and drawing inspiration from cognitive science, we introduce the robotic imagery paradigm, which realizes large-scale robotic data pre-training without text annotations. Additionally, we propose the robotic gaze strategy that emulates the human eye gaze mechanism, thereby guiding subsequent actions and focusing the attention of the policy on the manipulated object. Leveraging these innovations, we develop VIRT, a fully Transformer-based policy. We design comprehensive tasks using both a physical robot and simulated environments to assess the efficacy of VIRT. The results indicate that VIRT can complete very competitive tasks like ``opening the lid of a tightly sealed bottle'', and the proposed techniques boost the success rates of the baseline policy on diverse challenging tasks from nearly 0% to more than 65%.

Nighttime UAV tracking under low-illuminated scenarios has achieved great progress by domain adaptation (DA). However, previous DA training-based works are deficient in narrowing the discrepancy of temporal contexts for UAV trackers. To address the issue, this work proposes a prompt-driven temporal domain adaptation training framework to fully utilize temporal contexts for challenging nighttime UAV tracking, i.e., TDA. Specifically, the proposed framework aligns the distribution of temporal contexts from daytime and nighttime domains by training the temporal feature generator against the discriminator. The temporal-consistent discriminator progressively extracts shared domain-specific features to generate coherent domain discrimination results in the time series. Additionally, to obtain high-quality training samples, a prompt-driven object miner is employed to precisely locate objects in unannotated nighttime videos. Moreover, a new benchmark for long-term nighttime UAV tracking is constructed. Exhaustive evaluations on both public and self-constructed nighttime benchmarks demonstrate the remarkable performance of the tracker trained in TDA framework, i.e., TDA-Track. Real-world tests at nighttime also show its practicality. The code and demo videos are available at https://github.com/vision4robotics/TDA-Track., Comment: Accepted by IROS2024

State-of-the-art (SOTA) visual object tracking methods have significantly enhanced the autonomy of unmanned aerial vehicles (UAVs). However, in low-light conditions, the presence of irregular real noise from the environments severely degrades the performance of these SOTA methods. Moreover, existing SOTA denoising techniques often fail to meet the real-time processing requirements when deployed as plug-and-play denoisers for UAV tracking. To address this challenge, this work proposes a novel conditional generative denoiser (CGDenoiser), which breaks free from the limitations of traditional deterministic paradigms and generates the noise conditioning on the input, subsequently removing it. To better align the input dimensions and accelerate inference, a novel nested residual Transformer conditionalizer is developed. Furthermore, an innovative multi-kernel conditional refiner is designed to pertinently refine the denoised output. Extensive experiments show that CGDenoiser promotes the tracking precision of the SOTA tracker by 18.18\% on DarkTrack2021 whereas working 5.8 times faster than the second well-performed denoiser. Real-world tests with complex challenges also prove the effectiveness and practicality of CGDenoiser. Code, video demo and supplementary proof for CGDenoier are now available at: \url{https://github.com/vision4robotics/CGDenoiser}.

Visual object tracking has significantly promoted autonomous applications for unmanned aerial vehicles (UAVs). However, learning robust object representations for UAV tracking is especially challenging in complex dynamic environments, when confronted with aspect ratio change and occlusion. These challenges severely alter the original information of the object. To handle the above issues, this work proposes a novel progressive representation learning framework for UAV tracking, i.e., PRL-Track. Specifically, PRL-Track is divided into coarse representation learning and fine representation learning. For coarse representation learning, two innovative regulators, which rely on appearance and semantic information, are designed to mitigate appearance interference and capture semantic information. Furthermore, for fine representation learning, a new hierarchical modeling generator is developed to intertwine coarse object representations. Exhaustive experiments demonstrate that the proposed PRL-Track delivers exceptional performance on three authoritative UAV tracking benchmarks. Real-world tests indicate that the proposed PRL-Track realizes superior tracking performance with 42.6 frames per second on the typical UAV platform equipped with an edge smart camera. The code, model, and demo videos are available at \url{https://github.com/vision4robotics/PRL-Track}., Comment: Accepted by the 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024)

Visual object tracking has boosted extensive intelligent applications for unmanned aerial vehicles (UAVs). However, the state-of-the-art (SOTA) enhancers for nighttime UAV tracking always neglect the uneven light distribution in low-light images, inevitably leading to excessive enhancement in scenarios with complex illumination. To address these issues, this work proposes a novel enhancer, i.e., LDEnhancer, enhancing nighttime UAV tracking with light distribution suppression. Specifically, a novel image content refinement module is developed to decompose the light distribution information and image content information in the feature space, allowing for the targeted enhancement of the image content information. Then this work designs a new light distribution generation module to capture light distribution effectively. The features with light distribution information and image content information are fed into the different parameter estimation modules, respectively, for the parameter map prediction. Finally, leveraging two parameter maps, an innovative interweave iteration adjustment is proposed for the collaborative pixel-wise adjustment of low-light images. Additionally, a challenging nighttime UAV tracking dataset with uneven light distribution, namely NAT2024-2, is constructed to provide a comprehensive evaluation, which contains 40 challenging sequences with over 74K frames in total. Experimental results on the authoritative UAV benchmarks and the proposed NAT2024-2 demonstrate that LDEnhancer outperforms other SOTA low-light enhancers for nighttime UAV tracking. Furthermore, real-world tests on a typical UAV platform with an NVIDIA Orin NX confirm the practicality and efficiency of LDEnhancer. The code is available at https://github.com/vision4robotics/LDEnhancer.

We investigate spontaneous symmetry- and antisymmetry-breaking bifurcations of solitons in a nonlinear dual-core waveguide with the pure-quartic dispersion and Kerr nonlinearity. Symmetric, antisymmetric, and asymmetric pure-quartic solitons (PQSs) are found, and their stability domains are identified. The bifurcations for both the symmetric and antisymmetric PQSs are of the supercritical type (alias phase transitions of the second kind). Direct simulations of the perturbed evolution of PQSs corroborate their stability boundaries predicted by the analysis of small perturbations., Comment: 4 pages, 5 figures, to be published in Optics Letters

Entanglement entropy characterizes the correlation of multi-particles and unveils the crucial features of open quantum systems. However, the experimental realization of exploring entanglement in non-Hermitian systems remains a challenge. In parallel, quantum walks have offered the possibility of studying the underlying mechanisms of non-Hermitian physics, which includes exceptional points, the non-Hermitian skin effect, and non-Bloch phase transitions. Unfortunately, these studies have only involved and prevailingly focused on the behavior of a single particle. Here, we propose and experimentally realize quantum walks of two indistinguishable photons in engineered non-Hermitian photonic lattices. We have successfully observed the unidirectional behavior of quantum walks in the bulk far from the edges induced by the skin effect. Moreover, we experimentally reveal the suppression of entanglement that is caused by the skin effect in non-Hermitian systems. Our study may facilitate a deep understanding of entanglement in open quantum many-body systems that are far from thermal equilibrium., Comment: 26 pages, 5 figures

To reduce the reliance on high-definition (HD) maps, a growing trend in autonomous driving is leveraging on-board sensors to generate vectorized maps online. However, current methods are mostly constrained by processing only single-frame inputs, which hampers their robustness and effectiveness in complex scenarios. To overcome this problem, we propose an online map construction system that exploits the long-term temporal information to build a consistent vectorized map. First, the system efficiently fuses all historical road marking detections from an off-the-shelf network into a semantic voxel map, which is implemented using a hashing-based strategy to exploit the sparsity of road elements. Then reliable voxels are found by examining the fused information and incrementally clustered into an instance-level representation of road markings. Finally, the system incorporates domain knowledge to estimate the geometric and topological structures of roads, which can be directly consumed by the planning and control (PnC) module. Through experiments conducted in complicated urban environments, we have demonstrated that the output of our system is more consistent and accurate than the network output by a large margin and can be effectively used in a closed-loop autonomous driving system., Comment: 8 pages, 9 figures

Bounded by the size, weight, and power consumption (SWaP) of conventional superconducting single photon detectors (SSPD), applications of SSPDs were commonly confined in the laboratory. However, booming demands for high efficiency single photon detector incorporated with avionic platforms arise with the development of remote imaging and sensing or long-haul quantum communication without topographical constraints. We herein designed and manufactured the first drone based SSPD system with a SDE as high as 91.8%. This drone based SSPD system is established with high performance NbTiN SSPDs, self-developed miniature liquid helium dewar, and homemade integrated electric setups, which is able to be launched in complex topographical conditions. Such a drone based SSPD system may open the use of SSPDs for applications that demand high-SDE in complex environments.

Due to the dense environment, neutron stars (NSs) can serve as an ideal laboratory for studying the interactions between dark matter (DM) and ordinary matter. In the process of DM capture, deep inelastic scattering may dominate over elastic scattering, especially for the DM with a large momentum transfer. In this work, we calculate DM-nucleon deep inelastic scattering via a vector mediator and estimate its contribution to the capture rate. Using the surface temperature of the NSs, we derive the exclusion limits for the DM-nucleon scattering cross section in the mass range, $1~{\rm GeV}

Close white dwarf binaries (CWDBs) are considered to be progenitors of several exotic astronomical phenomena (e.g., type Ia supernovae, cataclysmic variables). These violent events are broadly used in studies of general relativity and cosmology. However, obtaining precise stellar parameter measurements for both components of CWDBs is a challenging task given their low luminosities, swift time variation, and complex orbits. High-resolution spectra (R$> 20 000$) are preferred but expensive, resulting in a sample size that is insufficient for robust population study. To release the full potential of the less expensive low-resolution spectroscopic surveys, and thus greatly expand the CWDB sample size, it is necessary to develop a robust pipeline for spectra decomposition and analysis. We used an artificial neural network (ANN) to build spectrum generators for DA/DB white dwarfs and main-sequence stars. The best-fit stellar parameters were obtained by finding the least $\chi^2$ solution to these feature lines and the continuum simultaneously. We demonstrate the reliability of our code with two well-studied CWDBs, WD 1534+503 and PG 1224+309. We also estimate the stellar parameters of 14 newly identified CWDB candidates, most of which are fitted with double component models for the first time. Our estimates agree with previous results for the common stars and follow the statistical distribution in the literature. The application of our code to a large volume of white dwarf binary candidates will offer important statistic samples to stellar evolution studies and future gravitational wave monitoring., Comment: 14pages, 12 figures, 2 tables.Accepted by A&A

Imagining potential outcomes of actions before execution helps agents make more informed decisions, a prospective thinking ability fundamental to human cognition. However, mainstream model-free Reinforcement Learning (RL) methods lack the ability to proactively envision future scenarios, plan, and guide strategies. These methods typically rely on trial and error to adjust policy functions, aiming to maximize cumulative rewards or long-term value, even if such high-reward decisions place the environment in extremely dangerous states. To address this, we propose the Prospective (ProSpec) RL method, which makes higher-value, lower-risk optimal decisions by imagining future n-stream trajectories. Specifically, ProSpec employs a dynamic model to predict future states (termed "imagined states") based on the current state and a series of sampled actions. Furthermore, we integrate the concept of Model Predictive Control and introduce a cycle consistency constraint that allows the agent to evaluate and select the optimal actions from these trajectories. Moreover, ProSpec employs cycle consistency to mitigate two fundamental issues in RL: augmenting state reversibility to avoid irreversible events (low risk) and augmenting actions to generate numerous virtual trajectories, thereby improving data efficiency. We validated the effectiveness of our method on the DMControl benchmarks, where our approach achieved significant performance improvements. Code will be open-sourced upon acceptance.

Time series forecasting (TSF) plays a crucial role in various applications, including medical monitoring and crop growth. Despite the advancements in deep learning methods for TSF, their capacity to predict long-term series remains constrained. This limitation arises from the failure to account for both intra- and inter-variable variations meanwhile. To mitigate this challenge, we introduce the Fi$^2$VBlock, which leverages a \textbf{F}requency domain perspective to capture \textbf{i}ntra- and \textbf{i}nter-variable \textbf{V}ariations. After transforming into the frequency domain via the Frequency Transform Module, the Frequency Cross Attention between the real and imaginary parts is designed to obtain enhanced frequency representations and capture intra-variable variations. Furthermore, Inception blocks are employed to integrate information, thus capturing correlations across different variables. Our backbone network, Fi$^2$VTS, employs a residual architecture by concatenating multiple Fi$^2$VBlocks, thereby preventing degradation issues. Theoretically, we demonstrate that Fi$^2$VTS achieves a substantial reduction in both time and memory complexity, decreasing from $\mathcal{O}(L^2)$ to $\mathcal{O}(L)$ per Fi$^2$VBlock computation. Empirical evaluations reveal that Fi$^2$VTS outperforms other baselines on two benchmark datasets. The implementation code is accessible at \url{https://github.com/HITshenrj/Fi2VTS}., Comment: There was an error in the experimental results; we mistakenly took the result of our method on the ETTh2 dataset as the result of our method on the ETTh1 dataset

We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute. These models are designed to perform a wide range of tasks efficiently, accurately, and responsibly. This report describes the model architecture, the data used to train the model, the training process, how the models are optimized for inference, and the evaluation results. We highlight our focus on Responsible AI and how the principles are applied throughout the model development.

The most advanced diffusion models have recently adopted increasingly deep stacked networks (e.g., U-Net or Transformer) to promote the generative emergence capabilities of vision generation models similar to large language models (LLMs). However, progressively deeper stacked networks will intuitively cause numerical propagation errors and reduce noisy prediction capabilities on generative data, which hinders massively deep scalable training of vision generation models. In this paper, we first uncover the nature that neural networks being able to effectively perform generative denoising lies in the fact that the intrinsic residual unit has consistent dynamic property with the input signal's reverse diffusion process, thus supporting excellent generative abilities. Afterwards, we stand on the shoulders of two common types of deep stacked networks to propose a unified and massively scalable Neural Residual Diffusion Models framework (Neural-RDM for short), which is a simple yet meaningful change to the common architecture of deep generative networks by introducing a series of learnable gated residual parameters that conform to the generative dynamics. Experimental results on various generative tasks show that the proposed neural residual models obtain state-of-the-art scores on image's and video's generative benchmarks. Rigorous theoretical proofs and extensive experiments also demonstrate the advantages of this simple gated residual mechanism consistent with dynamic modeling in improving the fidelity and consistency of generated content and supporting large-scale scalable training. Code is available at https://github.com/Anonymous/Neural-RDM.

Vortex states of photons, electrons, and other particles are freely propagating wave packets with helicoidal wave fronts winding around the axis of a phase vortex. A particle prepared in a vortex state possesses a non-zero orbital angular momentum projection on the propagation direction, a quantum number that has never been exploited in experimental particle and nuclear physics. Low-energy vortex photons, electrons, neutrons, and helium atoms have been demonstrated in experiment and found numerous applications, and there exist proposals of boosting them to higher energies. However, the verification that a high energy particle is indeed in a vortex state will be a major challenge, since the low energy techniques become impractical for highly energetic particles. Here, we propose a new diagnostic method based of the so-called superkick effect, which can unambiguously detect the presence of a phase vortex. A proof-of-principle experiment with vortex electrons can be done with the existing technology and will, at the same time, constitute the first observation of the superkick effect., Comment: 6 pages + supplemental material, 3 figures

Ongoing advances in microbiome profiling have allowed unprecedented insights into the molecular activities of microbial communities. This has fueled a strong scientific interest in understanding the critical role the microbiome plays in governing human health, by identifying microbial features associated with clinical outcomes of interest. Several aspects of microbiome data limit the applicability of existing variable selection approaches. In particular, microbiome data are high-dimensional, extremely sparse, and compositional. Importantly, many of the observed features, although categorized as different taxa, may play related functional roles. To address these challenges, we propose a novel compositional regression approach that leverages the data-adaptive clustering and variable selection properties of the spiked Dirichlet process to identify taxa that exhibit similar functional roles. Our proposed method, Bayesian Regression with Agglomerated Compositional Effects using a dirichLET process (BRACElet), enables the identification of a sparse set of features with shared impacts on the outcome, facilitating dimension reduction and model interpretation. We demonstrate that BRACElet outperforms existing approaches for microbiome variable selection through simulation studies and an application elucidating the impact of oral microbiome composition on insulin resistance.

In this paper, we study the discovery potential of a Vector-Like $B$ quark (VLB) via the process $pp \to B(\to bZ)j\to b(Z \to \nu_l\bar{\nu_l})j$ at the Large Hadron Collider (LHC) with $\sqrt{s}=14$ TeV. In the framework of a simplified model, we perform a scan over its parameter space and test its viability following a Monte Carlo analysis developed to include all production and decay dynamics. We use cut-and-count combined with Extreme Gradient Boosting (XGBoost) methods to classify the signal and background events in order to improve the efficiency of signal identification and background rejection. We find that this approach can reduce background events significantly while the signal retention rate is much higher than that of traditional methods, thereby improving the VLB discovery potential. We then calculate the exclusion and discovery capabilities for VLBs and find that the advantages of the cut-and-count plus XGBoost method especially lie in the high-mass region, i.e., $m_B > 1500 \text{ GeV}$. We finally obtain the following LHC results in terms of the coupling and chiral structure of a singlet heavy VLB interactions: (i) for $g^{\ast}$=0.2 and $R_L=0$ with 3000 fb$^{-1}$, the $B$ quark mass can be be excluded (discovered) up to 3000 GeV (2500 GeV); (ii) for $g^{\ast}$=0.2 and $R_L=0.5$ with 3000 fb$^{-1}$, the exclusion (discovery) region can reach up to 4750 GeV (4250 GeV)., Comment: 26 pages, 7 figures, 5 tables

Independent component analysis (ICA) is a fundamental problem in the field of signal processing, and numerous algorithms have been developed to address this issue. The core principle of these algorithms is to find a transformation matrix that maximizes the non-Gaussianity of the separated signals. Most algorithms typically assume that the source signals are mutually independent (orthogonal to each other), thereby imposing an orthogonal constraint on the transformation matrix. However, this assumption is not always valid in practical scenarios, where the orthogonal constraint can lead to inaccurate results. Recently, tensor-based algorithms have attracted much attention due to their ability to reduce computational complexity and enhance separation performance. In these algorithms, ICA is reformulated as an eigenpair problem of a statistical tensor. Importantly, the eigenpairs of a tensor are not inherently orthogonal, making tensor-based algorithms more suitable for nonorthogonal cases. Despite this advantage, finding exact solutions to the tensor's eigenpair problem remains a challenging task. In this paper, we introduce a non-zero volume constraint and a Riemannian gradient-based algorithm to solve the tensor's eigenpair problem. The proposed algorithm can find exact solutions under nonorthogonal conditions, making it more effective for separating nonorthogonal sources. Additionally, existing tensor-based algorithms typically rely on third-order statistics and are limited to real-valued data. To overcome this limitation, we extend tensor-based algorithms to the complex domain by constructing a fourth-order statistical tensor. Experiments conducted on both synthetic and real-world datasets demonstrate the effectiveness of the proposed algorithm., Comment: 23 pages, 6 figures

Excavators are crucial for diverse tasks such as construction and mining, while autonomous excavator systems enhance safety and efficiency, address labor shortages, and improve human working conditions. Different from the existing modularized approaches, this paper introduces ExACT, an end-to-end autonomous excavator system that processes raw LiDAR, camera data, and joint positions to control excavator valves directly. Utilizing the Action Chunking with Transformers (ACT) architecture, ExACT employs imitation learning to take observations from multi-modal sensors as inputs and generate actionable sequences. In our experiment, we build a simulator based on the captured real-world data to model the relations between excavator valve states and joint velocities. With a few human-operated demonstration data trajectories, ExACT demonstrates the capability of completing different excavation tasks, including reaching, digging and dumping through imitation learning in validations with the simulator. To the best of our knowledge, ExACT represents the first instance towards building an end-to-end autonomous excavator system via imitation learning methods with a minimal set of human demonstrations. The video about this work can be accessed at https://youtu.be/NmzR_Rf-aEk., Comment: ICRA Workshop 2024: 3rd Workshop on Future of Construction: Lifelong Learning Robots in Changing Construction Sites

Full fine-tuning is a popular approach to adapt Transformer-based pre-trained large language models to a specific downstream task. However, the substantial requirements for computational power and storage have discouraged its widespread use. Moreover, increasing evidence of catastrophic forgetting and overparameterization in the Transformer architecture has motivated researchers to seek more efficient fine-tuning (PEFT) methods. Commonly known parameter-efficient fine-tuning methods like LoRA and BitFit are typically applied across all layers of the model. We propose a PEFT method, called Stratified Progressive Adaptation Fine-tuning (SPAFIT), based on the localization of different types of linguistic knowledge to specific layers of the model. Our experiments, conducted on nine tasks from the GLUE benchmark, show that our proposed SPAFIT method outperforms other PEFT methods while fine-tuning only a fraction of the parameters adjusted by other methods.

Sampling-based motion planning (SBMP) algorithms are renowned for their robust global search capabilities. However, the inherent randomness in their sampling mechanisms often result in inconsistent path quality and limited search efficiency. In response to these challenges, this work proposes a novel deep learning-based motion planning framework, named Transformer-Enhanced Motion Planner (TEMP), which synergizes an Environmental Information Semantic Encoder (EISE) with a Motion Planning Transformer (MPT). EISE converts environmental data into semantic environmental information (SEI), providing MPT with an enriched environmental comprehension. MPT leverages an attention mechanism to dynamically recalibrate its focus on SEI, task objectives, and historical planning data, refining the sampling node generation. To demonstrate the capabilities of TEMP, we train our model using a dataset comprised of planning results produced by the RRT*. EISE and MPT are collaboratively trained, enabling EISE to autonomously learn and extract patterns from environmental data, thereby forming semantic representations that MPT could more effectively interpret and utilize for motion planning. Subsequently, we conducted a systematic evaluation of TEMP's efficacy across diverse task dimensions, which demonstrates that TEMP achieves exceptional performance metrics and a heightened degree of generalizability compared to state-of-the-art SBMPs., Comment: This work has been submitted to the IEEE for possible publication

We have developed the world's first canopy height map of the distribution area of world-level giant trees. This mapping is crucial for discovering more individual and community world-level giant trees, and for analyzing and quantifying the effectiveness of biodiversity conservation measures in the Yarlung Tsangpo Grand Canyon (YTGC) National Nature Reserve. We proposed a method to map the canopy height of the primeval forest within the world-level giant tree distribution area by using a spaceborne LiDAR fusion satellite imagery (Global Ecosystem Dynamics Investigation (GEDI), ICESat-2, and Sentinel-2) driven deep learning modeling. And we customized a pyramid receptive fields depth separable CNN (PRFXception). PRFXception, a CNN architecture specifically customized for mapping primeval forest canopy height to infer the canopy height at the footprint level of GEDI and ICESat-2 from Sentinel-2 optical imagery with a 10-meter spatial resolution. We conducted a field survey of 227 permanent plots using a stratified sampling method and measured several giant trees using UAV-LS. The predicted canopy height was compared with ICESat-2 and GEDI validation data (RMSE =7.56 m, MAE=6.07 m, ME=-0.98 m, R^2=0.58 m), UAV-LS point clouds (RMSE =5.75 m, MAE =3.72 m, ME = 0.82 m, R^2= 0.65 m), and ground survey data (RMSE = 6.75 m, MAE = 5.56 m, ME= 2.14 m, R^2=0.60 m). We mapped the potential distribution map of world-level giant trees and discovered two previously undetected giant tree communities with an 89% probability of having trees 80-100 m tall, potentially taller than Asia's tallest tree. This paper provides scientific evidence confirming southeastern Tibet--northwestern Yunnan as the fourth global distribution center of world-level giant trees initiatives and promoting the inclusion of the YTGC giant tree distribution area within the scope of China's national park conservation.