Search

Video diffusion models have exhibited tremendous progress in various video generation tasks. However, existing models struggle to capture latent physical knowledge, failing to infer physical phenomena that are challenging to articulate with natural language. Generating videos following the fundamental physical laws is still an opening challenge. To address this challenge, we propose a novel method to teach video diffusion models with latent physical phenomenon knowledge, enabling the accurate generation of physically informed phenomena. Specifically, we first pretrain Masked Autoencoders (MAE) to reconstruct the physical phenomena, resulting in output embeddings that encapsulate latent physical phenomenon knowledge. Leveraging these embeddings, we could generate the pseudo-language prompt features based on the aligned spatial relationships between CLIP vision and language encoders. Particularly, given that diffusion models typically use CLIP's language encoder for text prompt embeddings, our approach integrates the CLIP visual features informed by latent physical knowledge into a quaternion hidden space. This enables the modeling of spatial relationships to produce physical knowledge-informed pseudo-language prompts. By incorporating these prompt features and fine-tuning the video diffusion model in a parameter-efficient manner, the physical knowledge-informed videos are successfully generated. We validate our method extensively through both numerical simulations and real-world observations of physical phenomena, demonstrating its remarkable performance across diverse scenarios., Comment: 7 figures, 14 pages

The star tracker is generally affected by the atmospheric background light and the aerodynamic environment when working in near space, which results in missing stars or false stars. Moreover, high-speed maneuvering may cause star trailing, which reduces the accuracy of the star position. To address the challenges for starmap identification, a reverse attitude statistics based method is proposed to handle position noise, false stars, and missing stars. Conversely to existing methods which match before solving for attitude, this method introduces attitude solving into the matching process, and obtains the final match and the correct attitude simultaneously by frequency statistics. Firstly, based on stable angular distance features, the initial matching is obtained by utilizing spatial hash indexing. Then, the dual-vector attitude determination is introduced to calculate potential attitude. Finally, the star pairs are accurately matched by applying a frequency statistics filtering method. In addition, Bayesian optimization is employed to find optimal parameters under the impact of noises, which is able to enhance the algorithm performance further. In this work, the proposed method is validated in simulation, field test and on-orbit experiment. Compared with the state-of-the-art, the identification rate is improved by more than 14.3%, and the solving time is reduced by over 28.5%., Comment: 10 pages, 17figures, 4 tables, 4663 words, submitted to IEEE Sensors Journal

Quantum nonlocality and nonclassicality are two remarkable characteristics of quantum theory, and offer quantum advantages in some quantum information processing. Motivated by recent work on the interplay between nonclassicality quantified by average correlation [Tschaffon et al., Phys. Rev. Res. 5,023063 (2023)] and Bell nonlocality, in this paper we aim to establish the relationship between the average correlation and the violation of the three-setting linear steering inequality for two-qubit systems. Exact lower and upper bounds of average correlation versus steering are obtained, and the respective states which suffice those bounds are also characterized. For clarity of our presentation, we illustrate these results with examples from well-known classes of two-qubit states. Moreover, the dynamical behavior of these two quantifiers is carefully analyzed under the influence of local unital and nonunital noisy channels. The results suggest that average correlation is closely related to the violation of three-setting linear steering, like its relationship with Bell violation. Particularly, for a given class of states, the hierarchy of nonclassicality-steering-Bell nonlocality is demonstrated., Comment: 2

The optimal \(H_{\infty}\) control problem over an infinite time horizon, which incorporates a performance function with a discount factor \(e^{-\alpha t}\) (\(\alpha > 0\)), is important in various fields. Solving this optimal \(H_{\infty}\) control problem is equivalent to addressing a discounted Hamilton-Jacobi-Isaacs (HJI) partial differential equation. In this paper, we first provide a precise estimate for the discount factor \(\alpha\) that ensures the existence of a nonnegative stabilizing solution to the HJI equation. This stabilizing solution corresponds to the stable manifold of the characteristic system of the HJI equation, which is a contact Hamiltonian system due to the presence of the discount factor. Secondly, we demonstrate that approximating the optimal controller in a natural manner results in a closed-loop system with a finite \(L_2\)-gain that is nearly less than the gain of the original system. Thirdly, based on the theoretical results obtained, we propose a deep learning algorithm to approximate the optimal controller using the stable manifold of the contact Hamiltonian system associated with the HJI equation. Finally, we apply our method to the \(H_{\infty}\) control of the Allen-Cahn equation to illustrate its effectiveness.

In recent years, Solving partial differential equations has shifted the focus of traditional neural network studies from finite-dimensional Euclidean spaces to generalized functional spaces in research. A novel methodology is to learn an operator as a means of approximating the mapping between outputs. Currently, researchers have proposed a variety of operator architectures. Nevertheless, the majority of these architectures adopt an iterative update architecture, whereby a single operator is learned from the same function space. In practical physical science problems, the numerical solutions of partial differential equations are complex, and a serial single operator is unable to accurately approximate the intricate mapping between input and output. So, We propose a deep parallel operator model (DPNO) for efficiently and accurately solving partial differential equations. DPNO employs convolutional neural networks to extract local features and map data into distinct latent spaces. Designing a parallel block of double Fourier neural operators to solve the iterative error problem. DPNO approximates complex mappings between inputs and outputs by learning multiple operators in different potential spaces in parallel blocks. DPNO achieved the best performance on five of them, with an average improvement of 10.5\%, and ranked second on one dataset.

Open-vocabulary image semantic segmentation (OVS) seeks to segment images into semantic regions across an open set of categories. Existing OVS methods commonly depend on foundational vision-language models and utilize similarity computation to tackle OVS tasks. However, these approaches are predominantly tailored to natural images and struggle with the unique characteristics of remote sensing images, such as rapidly changing orientations and significant scale variations. These challenges complicate OVS tasks in earth vision, requiring specialized approaches. To tackle this dilemma, we propose the first OVS framework specifically designed for remote sensing imagery, drawing inspiration from the distinct remote sensing traits. Particularly, to address the varying orientations, we introduce a rotation-aggregative similarity computation module that generates orientation-adaptive similarity maps as initial semantic maps. These maps are subsequently refined at both spatial and categorical levels to produce more accurate semantic maps. Additionally, to manage significant scale changes, we integrate multi-scale image features into the upsampling process, resulting in the final scale-aware semantic masks. To advance OVS in earth vision and encourage reproducible research, we establish the first open-sourced OVS benchmark for remote sensing imagery, including four public remote sensing datasets. Extensive experiments on this benchmark demonstrate our proposed method achieves state-of-the-art performance. All codes and datasets are available at https://github.com/caoql98/OVRS.

Physics-Informed Neural Networks (PINNs) have become a promising research direction in the field of solving Partial Differential Equations (PDEs). Dealing with singular perturbation problems continues to be a difficult challenge in the field of PINN. The solution of singular perturbation problems often exhibits sharp boundary layers and steep gradients, and traditional PINN cannot achieve approximation of boundary layers. In this manuscript, we propose the General-Kindred Physics-Informed Neural Network (GKPINN) for solving Singular Perturbation Differential Equations (SPDEs). This approach utilizes asymptotic analysis to acquire prior knowledge of the boundary layer from the equation and establishes a novel network to assist PINN in approximating the boundary layer. It is compared with traditional PINN by solving examples of one-dimensional, two-dimensional, and time-varying SPDE equations. The research findings underscore the exceptional performance of our novel approach, GKPINN, which delivers a remarkable enhancement in reducing the $L_2$ error by two to four orders of magnitude compared to the established PINN methodology. This significant improvement is accompanied by a substantial acceleration in convergence rates, without compromising the high precision that is critical for our applications. Furthermore, GKPINN still performs well in extreme cases with perturbation parameters of ${1\times10}^{-38}$, demonstrating its excellent generalization ability.

Inverse Kinematics (IK) is to find the robot's configurations that satisfy the target pose of the end effector. In motion planning, diverse configurations were required in case a feasible trajectory was not found. Meanwhile, collision checking (CC), e.g. Oriented bounding box (OBB), Discrete Oriented Polytope (DOP), and Quickhull \cite{quickhull}, needs to be done for each configuration provided by the IK solver to ensure every goal configuration for motion planning is available. This means the classical IK solver and CC algorithm should be executed repeatedly for every configuration. Thus, the preparation time is long when the required number of goal configurations is large, e.g. motion planning in cluster environments. Moreover, structured maps, which might be difficult to obtain, were required by classical collision-checking algorithms. To sidestep such two issues, we propose a flow-based vision method that can output diverse available configurations by fusing inverse kinematics and collision checking, named Vision Inverse Kinematics solver (ViIK). Moreover, ViIK uses RGB images as the perception of environments. ViIK can output 1000 configurations within 40 ms, and the accuracy is about 3 millimeters and 1.5 degrees. The higher accuracy can be obtained by being refined by the classical IK solver within a few iterations. The self-collision rates can be lower than 2%. The collision-with-env rates can be lower than 10% in most scenes. The code is available at: https://github.com/AdamQLMeng/ViIK.

This paper considers a scenario in city navigation: an AI agent is provided with language descriptions of the goal location with respect to some well-known landmarks; By only observing the scene around, including recognizing landmarks and road network connections, the agent has to make decisions to navigate to the goal location without instructions. This problem is very challenging, because it requires agent to establish self-position and acquire spatial representation of complex urban environment, where landmarks are often invisible. In the absence of navigation instructions, such abilities are vital for the agent to make high-quality decisions in long-range city navigation. With the emergent reasoning ability of large language models (LLMs), a tempting baseline is to prompt LLMs to "react" on each observation and make decisions accordingly. However, this baseline has very poor performance that the agent often repeatedly visits same locations and make short-sighted, inconsistent decisions. To address these issues, this paper introduces a novel agentic workflow featured by its abilities to perceive, reflect and plan. Specifically, we find LLaVA-7B can be fine-tuned to perceive the direction and distance of landmarks with sufficient accuracy for city navigation. Moreover, reflection is achieved through a memory mechanism, where past experiences are stored and can be retrieved with current perception for effective decision argumentation. Planning uses reflection results to produce long-term plans, which can avoid short-sighted decisions in long-range navigation. We show the designed workflow significantly improves navigation ability of the LLM agent compared with the state-of-the-art baselines.

This paper introduces Chain-of-Sight, a vision-language bridge module that accelerates the pre-training of Multimodal Large Language Models (MLLMs). Our approach employs a sequence of visual resamplers that capture visual details at various spacial scales. This architecture not only leverages global and local visual contexts effectively, but also facilitates the flexible extension of visual tokens through a compound token scaling strategy, allowing up to a 16x increase in the token count post pre-training. Consequently, Chain-of-Sight requires significantly fewer visual tokens in the pre-training phase compared to the fine-tuning phase. This intentional reduction of visual tokens during pre-training notably accelerates the pre-training process, cutting down the wall-clock training time by ~73%. Empirical results on a series of vision-language benchmarks reveal that the pre-train acceleration through Chain-of-Sight is achieved without sacrificing performance, matching or surpassing the standard pipeline of utilizing all visual tokens throughout the entire training process. Further scaling up the number of visual tokens for pre-training leads to stronger performances, competitive to existing approaches in a series of benchmarks.

This study introduces a new approach to addressing positive and unlabeled (PU) data through the double exponential tilting model (DETM). Traditional methods often fall short because they only apply to selected completely at random (SCAR) PU data, where the labeled positive and unlabeled positive data are assumed to be from the same distribution. In contrast, our DETM's dual structure effectively accommodates the more complex and underexplored selected at random PU data, where the labeled and unlabeled positive data can be from different distributions. We rigorously establish the theoretical foundations of DETM, including identifiability, parameter estimation, and asymptotic properties. Additionally, we move forward to statistical inference by developing a goodness-of-fit test for the SCAR condition and constructing confidence intervals for the proportion of positive instances in the target domain. We leverage an approximated Bayes classifier for classification tasks, demonstrating DETM's robust performance in prediction. Through theoretical insights and practical applications, this study highlights DETM as a comprehensive framework for addressing the challenges of PU data.

Convolutional Neural Network (CNN) struggle to capture the multi-dimensional structural information of complex high-dimensional data, which limits their feature learning capability. This paper proposes a feature fusion method based on Topological Data Analysis (TDA) and CNN, named TDA-CNN. This method combines numerical distribution features captured by CNN with topological structure features captured by TDA to improve the feature learning and representation ability of CNN. TDA-CNN divides feature extraction into a CNN channel and a TDA channel. CNN channel extracts numerical distribution features, and the TDA channel extracts topological structure features. The two types of features are fused to form a combined feature representation, with the importance weights of each feature adaptively learned through an attention mechanism. Experimental validation on datasets such as Intel Image, Gender Images, and Chinese Calligraphy Styles by Calligraphers demonstrates that TDA-CNN improves the performance of VGG16, DenseNet121, and GoogleNet networks by 17.5%, 7.11%, and 4.45%, respectively. TDA-CNN demonstrates improved feature clustering and the ability to recognize important features. This effectively enhances the model's decision-making ability.

To enhance the robustness of the Light Gradient Boosting Machine (LightGBM) algorithm for image classification, a topological data analysis (TDA)-based robustness optimization algorithm for LightGBM, TDA-LightGBM, is proposed to address the interference of noise on image classification. Initially, the method partitions the feature engineering process into two streams: pixel feature stream and topological feature stream for feature extraction respectively. Subsequently, these pixel and topological features are amalgamated into a comprehensive feature vector, serving as the input for LightGBM in image classification tasks. This fusion of features not only encompasses traditional feature engineering methodologies but also harnesses topological structure information to more accurately encapsulate the intrinsic features of the image. The objective is to surmount challenges related to unstable feature extraction and diminished classification accuracy induced by data noise in conventional image processing. Experimental findings substantiate that TDA-LightGBM achieves a 3% accuracy improvement over LightGBM on the SOCOFing dataset across five classification tasks under noisy conditions. In noise-free scenarios, TDA-LightGBM exhibits a 0.5% accuracy enhancement over LightGBM on two classification tasks, achieving a remarkable accuracy of 99.8%. Furthermore, the method elevates the classification accuracy of the Ultrasound Breast Images for Breast Cancer dataset and the Masked CASIA WebFace dataset by 6% and 15%, respectively, surpassing LightGBM in the presence of noise. These empirical results underscore the efficacy of the TDA-LightGBM approach in fortifying the robustness of LightGBM by integrating topological features, thereby augmenting the performance of image classification tasks amidst data perturbations.

Photovoltaic (PV) power forecasting plays a crucial role in optimizing the operation and planning of PV systems, thereby enabling efficient energy management and grid integration. However, un certainties caused by fluctuating weather conditions and complex interactions between different variables pose significant challenges to accurate PV power forecasting. In this study, we propose PV-Client (Cross-variable Linear Integrated ENhanced Transformer for Photovoltaic power forecasting) to address these challenges and enhance PV power forecasting accuracy. PV-Client employs an ENhanced Transformer module to capture complex interactions of various features in PV systems, and utilizes a linear module to learn trend information in PV power. Diverging from conventional time series-based Transformer models that use cross-time Attention to learn dependencies between different time steps, the Enhanced Transformer module integrates cross-variable Attention to capture dependencies between PV power and weather factors. Furthermore, PV-Client streamlines the embedding and position encoding layers by replacing the Decoder module with a projection layer. Experimental results on three real-world PV power datasets affirm PV-Client's state-of-the-art (SOTA) performance in PV power forecasting. Specifically, PV-Client surpasses the second-best model GRU by 5.3% in MSE metrics and 0.9% in accuracy metrics at the Jingang Station. Similarly, PV-Client outperforms the second-best model SVR by 10.1% in MSE metrics and 0.2% in accuracy metrics at the Xinqingnian Station, and PV-Client exhibits superior performance compared to the second-best model SVR with enhancements of 3.4% in MSE metrics and 0.9% in accuracy metrics at the Hongxing Station.

Large-scale Vision-Language Models (VLMs) have demonstrated exceptional performance in natural vision tasks, motivating researchers across domains to explore domain-specific VLMs. However, the construction of powerful domain-specific VLMs demands vast amounts of annotated data, substantial electrical energy, and computing resources, primarily accessible to industry, yet hindering VLM research in academia. To address this challenge and foster sustainable and equitable VLM research, we present the Generalized Domain Prompt Learning (GDPL) framework. GDPL facilitates the transfer of VLMs' robust recognition capabilities from natural vision to specialized domains, without the need for extensive data or resources. By leveraging small-scale domain-specific foundation models and minimal prompt samples, GDPL empowers the language branch with domain knowledge through quaternion networks, uncovering cross-modal relationships between domain-specific vision features and natural vision-based contextual embeddings. Simultaneously, GDPL guides the vision branch into specific domains through hierarchical propagation of generated vision prompt features, grounded in well-matched vision-language relations. Furthermore, to fully harness the domain adaptation potential of VLMs, we introduce a novel low-rank adaptation approach. Extensive experiments across diverse domains like remote sensing, medical imaging, geology, Synthetic Aperture Radar, and fluid dynamics, validate the efficacy of GDPL, demonstrating its ability to achieve state-of-the-art domain recognition performance in a prompt learning paradigm. Our framework paves the way for sustainable and inclusive VLM research, transcending the barriers between academia and industry.

In this paper, we examine the homotopy classes of positive loops in ${\rm Sp}(2n)$. We demonstrate that two positive loops are homotopic if and only if they are homotopic through positive loops. As consequences, we can extend several results of McDuff \cite{McD} and Chance \cite{Cha} to higher dimensional symplectic manifolds without dimensional restrictions., Comment: 55 pages, 18 figures, minor changes

Normalizing flow is a generative modeling approach with efficient sampling. However, Flow-based models suffer two issues: 1) If the target distribution is manifold, due to the unmatch between the dimensions of the latent target distribution and the data distribution, flow-based models might perform badly. 2) Discrete data might make flow-based models collapse into a degenerate mixture of point masses. To sidestep such two issues, we propose PaddingFlow, a novel dequantization method, which improves normalizing flows with padding-dimensional noise. To implement PaddingFlow, only the dimension of normalizing flows needs to be modified. Thus, our method is easy to implement and computationally cheap. Moreover, the padding-dimensional noise is only added to the padding dimension, which means PaddingFlow can dequantize without changing data distributions. Implementing existing dequantization methods needs to change data distributions, which might degrade performance. We validate our method on the main benchmarks of unconditional density estimation, including five tabular datasets and four image datasets for Variational Autoencoder (VAE) models, and the Inverse Kinematics (IK) experiments which are conditional density estimation. The results show that PaddingFlow can perform better in all experiments in this paper, which means PaddingFlow is widely suitable for various tasks. The code is available at: https://github.com/AdamQLMeng/PaddingFlow.

Protecting individual privacy is crucial when releasing sensitive data for public use. While data de-identification helps, it is not enough. This paper addresses parameter estimation in scenarios where data are perturbed using the Post-Randomization Method (PRAM) to enhance privacy. Existing methods for parameter estimation under PRAM data suffer from limitations like being parameter-specific, model-dependent, and lacking efficiency guarantees. We propose a novel, efficient method that overcomes these limitations. Our method is applicable to general parameters defined through estimating equations and makes no assumptions about the underlying data model. We further prove that the proposed estimator achieves the semiparametric efficiency bound, making it optimal in terms of asymptotic variance.

Robotic behavior synthesis, the problem of understanding multimodal inputs and generating precise physical control for robots, is an important part of Embodied AI. Despite successes in applying multimodal large language models for high-level understanding, it remains challenging to translate these conceptual understandings into detailed robotic actions while achieving generalization across various scenarios. In this paper, we propose a tree-structured multimodal code generation framework for generalized robotic behavior synthesis, termed RoboCodeX. RoboCodeX decomposes high-level human instructions into multiple object-centric manipulation units consisting of physical preferences such as affordance and safety constraints, and applies code generation to introduce generalization ability across various robotics platforms. To further enhance the capability to map conceptual and perceptual understanding into control commands, a specialized multimodal reasoning dataset is collected for pre-training and an iterative self-updating methodology is introduced for supervised fine-tuning. Extensive experiments demonstrate that RoboCodeX achieves state-of-the-art performance in both simulators and real robots on four different kinds of manipulation tasks and one navigation task.

The presence of distribution shifts poses a significant challenge for deploying modern machine learning models in real-world applications. This work focuses on the target shift problem in a regression setting (Zhang et al., 2013; Nguyen et al., 2016). More specifically, the target variable y (also known as the response variable), which is continuous, has different marginal distributions in the training source and testing domain, while the conditional distribution of features x given y remains the same. While most literature focuses on classification tasks with finite target space, the regression problem has an infinite dimensional target space, which makes many of the existing methods inapplicable. In this work, we show that the continuous target shift problem can be addressed by estimating the importance weight function from an ill-posed integral equation. We propose a nonparametric regularized approach named ReTaSA to solve the ill-posed integral equation and provide theoretical justification for the estimated importance weight function. The effectiveness of the proposed method has been demonstrated with extensive numerical studies on synthetic and real-world datasets., Comment: Accepted by ICLR 2024

Flow image super-resolution (FISR) aims at recovering high-resolution turbulent velocity fields from low-resolution flow images. Existing FISR methods mainly process the flow images in natural image patterns, while the critical and distinct flow visual properties are rarely considered. This negligence would cause the significant domain gap between flow and natural images to severely hamper the accurate perception of flow turbulence, thereby undermining super-resolution performance. To tackle this dilemma, we comprehensively consider the flow visual properties, including the unique flow imaging principle and morphological information, and propose the first flow visual property-informed FISR algorithm. Particularly, different from natural images that are constructed by independent RGB channels in the light field, flow images build on the orthogonal UVW velocities in the flow field. To empower the FISR network with an awareness of the flow imaging principle, we propose quaternion spatial modeling to model this orthogonal spatial relationship for improved FISR. Moreover, due to viscosity and surface tension characteristics, fluids often exhibit a droplet-like morphology in flow images. Inspired by this morphological property, we design the dynamic flow convolution to effectively mine the morphological information to enhance FISR. Extensive experiments on the newly acquired flow image datasets demonstrate the state-of-the-art performance of our method. Code and data will be made available.

The interrupted-sampling repeater jamming (ISRJ) is coherent and has the characteristic of suppression and deception to degrade the radar detection capabilities. The study focuses on anti-ISRJ techniques in the waveform domain, primarily capitalizing on waveform design and and anti-jamming signal processing methods in the waveform domain. By exploring the relationship between waveform-domain adaptive matched filtering (WD-AMF) output and waveform-domain signals, we demonstrate that ISRJ can be effectively suppressed when the transmitted waveform exhibits waveform-domain complementarity. We introduce a phase-coded (PC) waveform set with waveform-domain complementarity and propose a method for generating such waveform sets of arbitrary code lengths. The performance of WD-AMF are further developed due to the designed waveforms, and simulations affirm the superior adaptive anti-jamming capabilities of the designed waveforms compared to traditional ones. Remarkably, this improved performance is achieved without the need for prior knowledge of ISRJ interference parameters at either the transmitter or receiver stages.

The classical path planners, such as sampling-based path planners, can provide probabilistic completeness guarantees in the sense that the probability that the planner fails to return a solution if one exists, decays to zero as the number of samples approaches infinity. However, finding a near-optimal feasible solution in a given period is challenging in many applications such as the autonomous vehicle. To achieve an end-to-end near-optimal path planner, we first divide the path planning problem into two subproblems, which are path space segmentation and waypoints generation in the given path's space. We further propose a two-stage neural network named Path Planning Network (PPNet) each stage solves one of the subproblems abovementioned. Moreover, we propose a novel efficient data generation method for path planning named EDaGe-PP. EDaGe-PP can generate data with continuous-curvature paths with analytical expression while satisfying the clearance requirement. The results show the total computation time of generating random 2D path planning data is less than 1/33 and the success rate of PPNet trained by the dataset that is generated by EDaGe-PP is about 2 times compared to other methods. We validate PPNet against state-of-the-art path planning methods. The results show that PPNet can find a near-optimal solution in 15.3ms, which is much shorter than the state-of-the-art path planners.

Neural Radiance Field (NeRF) has been proposed as an innovative advancement in 3D reconstruction techniques. However, little research has been conducted on the issues of information confidentiality and security to NeRF, such as steganography. Existing NeRF steganography solutions have shortcomings in low steganography quality, model weight damage, and limited amount of steganographic information. This paper proposes Noise-NeRF, a novel NeRF steganography method employing Adaptive Pixel Selection strategy and Pixel Perturbation strategy to improve the quality and efficiency of steganography via trainable noise. Extensive experiments validate the state-of-the-art performances of Noise-NeRF on both steganography quality and rendering quality, as well as effectiveness in super-resolution image steganography.

The exponential growth of large language models (LLMs) has opened up numerous possibilities for multimodal AGI systems. However, the progress in vision and vision-language foundation models, which are also critical elements of multi-modal AGI, has not kept pace with LLMs. In this work, we design a large-scale vision-language foundation model (InternVL), which scales up the vision foundation model to 6 billion parameters and progressively aligns it with the LLM, using web-scale image-text data from various sources. This model can be broadly applied to and achieve state-of-the-art performance on 32 generic visual-linguistic benchmarks including visual perception tasks such as image-level or pixel-level recognition, vision-language tasks such as zero-shot image/video classification, zero-shot image/video-text retrieval, and link with LLMs to create multi-modal dialogue systems. It has powerful visual capabilities and can be a good alternative to the ViT-22B. We hope that our research could contribute to the development of multi-modal large models. Code and models are available at https://github.com/OpenGVLab/InternVL., Comment: 25 pages, 5 figures, 28 tables

Prompt learning has emerged as an effective and data-efficient technique in large Vision-Language Models (VLMs). However, when adapting VLMs to specialized domains such as remote sensing and medical imaging, domain prompt learning remains underexplored. While large-scale domain-specific foundation models can help tackle this challenge, their concentration on a single vision level makes it challenging to prompt both vision and language modalities. To overcome this, we propose to leverage domain-specific knowledge from domain-specific foundation models to transfer the robust recognition ability of VLMs from generalized to specialized domains, using quaternion networks. Specifically, the proposed method involves using domain-specific vision features from domain-specific foundation models to guide the transformation of generalized contextual embeddings from the language branch into a specialized space within the quaternion networks. Moreover, we present a hierarchical approach that generates vision prompt features by analyzing intermodal relationships between hierarchical language prompt features and domain-specific vision features. In this way, quaternion networks can effectively mine the intermodal relationships in the specific domain, facilitating domain-specific vision-language contrastive learning. Extensive experiments on domain-specific datasets show that our proposed method achieves new state-of-the-art results in prompt learning.

Time series forecasting (TSF) holds significant importance in modern society, spanning numerous domains. Previous representation learning-based TSF algorithms typically embrace a contrastive learning paradigm featuring segregated trend-periodicity representations. Yet, these methodologies disregard the inherent high-impact noise embedded within time series data, resulting in representation inaccuracies and seriously demoting the forecasting performance. To address this issue, we propose CLeaRForecast, a novel contrastive learning framework to learn high-purity time series representations with proposed sample, feature, and architecture purifying methods. More specifically, to avoid more noise adding caused by the transformations of original samples (series), transformations are respectively applied for trendy and periodic parts to provide better positive samples with obviously less noise. Moreover, we introduce a channel independent training manner to mitigate noise originating from unrelated variables in the multivariate series. By employing a streamlined deep-learning backbone and a comprehensive global contrastive loss function, we prevent noise introduction due to redundant or uneven learning of periodicity and trend. Experimental results show the superior performance of CLeaRForecast in various downstream TSF tasks.

Automatic Modulation Classification (AMC) plays a vital role in time series analysis, such as signal classification and identification within wireless communications. Deep learning-based AMC models have demonstrated significant potential in this domain. However, current AMC models inadequately consider the disparities in handling signals under conditions of low and high Signal-to-Noise Ratio (SNR), resulting in an unevenness in their performance. In this study, we propose MoE-AMC, a novel Mixture-of-Experts (MoE) based model specifically crafted to address AMC in a well-balanced manner across varying SNR conditions. Utilizing the MoE framework, MoE-AMC seamlessly combines the strengths of LSRM (a Transformer-based model) for handling low SNR signals and HSRM (a ResNet-based model) for high SNR signals. This integration empowers MoE-AMC to achieve leading performance in modulation classification, showcasing its efficacy in capturing distinctive signal features under diverse SNR scenarios. We conducted experiments using the RML2018.01a dataset, where MoE-AMC achieved an average classification accuracy of 71.76% across different SNR levels, surpassing the performance of previous SOTA models by nearly 10%. This study represents a pioneering application of MoE techniques in the realm of AMC, offering a promising avenue for elevating signal classification accuracy within wireless communication systems.