Search

Multi-modal large language models (MLLMs) have achieved remarkable success in fine-grained visual understanding across a range of tasks. However, they often encounter significant challenges due to inadequate alignment for fine-grained knowledge, which restricts their ability to accurately capture local details and attain a comprehensive global perception. While recent advancements have focused on aligning object expressions with grounding information, they typically lack explicit integration of object images, which contain affluent information beyond mere texts or coordinates. To bridge this gap, we introduce a novel fine-grained visual knowledge alignment method that effectively aligns and integrates multi-scale knowledge of objects, including texts, coordinates, and images. This innovative method is underpinned by our multi-scale fine-grained enhancement data synthesis pipeline, which provides over 300K essential training data to enhance alignment and improve overall performance. Furthermore, we present TinyGroundingGPT, a series of compact models optimized for high-level alignments. With a scale of approximately 3B parameters, TinyGroundingGPT achieves outstanding results in grounding tasks while delivering performance comparable to larger MLLMs in complex visual scenarios.

Underwater object detection (UOD), aiming to identify and localise the objects in underwater images or videos, presents significant challenges due to the optical distortion, water turbidity, and changing illumination in underwater scenes. In recent years, artificial intelligence (AI) based methods, especially deep learning methods, have shown promising performance in UOD. To further facilitate future advancements, we comprehensively study AI-based UOD. In this survey, we first categorise existing algorithms into traditional machine learning-based methods and deep learning-based methods, and summarise them by considering learning strategy, experimental dataset, utilised features or frameworks, and learning stage. Next, we discuss the potential challenges and suggest possible solutions and new directions. We also perform both quantitative and qualitative evaluations of mainstream algorithms across multiple benchmark datasets by considering the diverse and biased experimental setups. Finally, we introduce two off-the-shelf detection analysis tools, Diagnosis and TIDE, which well-examine the effects of object characteristics and various types of errors on detectors. These tools help identify the strengths and weaknesses of detectors, providing insigts for further improvement. The source codes, trained models, utilised datasets, detection results, and detection analysis tools are public available at \url{https://github.com/LongChenCV/UODReview}, and will be regularly updated.

Ads supply personalization aims to balance the revenue and user engagement, two long-term objectives in social media ads, by tailoring the ad quantity and density. In the industry-scale system, the challenge for ads supply lies in modeling the counterfactual effects of a conservative supply treatment (e.g., a small density change) over an extended duration. In this paper, we present a streamlined framework for personalized ad supply. This framework optimally utilizes information from data collection policies through the doubly robust learning. Consequently, it significantly improves the accuracy of long-term treatment effect estimates. Additionally, its low-complexity design not only results in computational cost savings compared to existing methods, but also makes it scalable for billion-scale applications. Through both offline experiments and online production tests, the framework consistently demonstrated significant improvements in top-line business metrics over months. The framework has been fully deployed to live traffic in one of the world's largest social media platforms., Comment: Accepted by CIKM'24

Background: Allium vegetables (garlic and onion) are one of the flavorings in people's daily diets. Observational studies suggest that intake of allium vegetables may be correlated with a lower incidence of digestive system cancers. However, the existence of a causal relationship is still controversial due to confounding factors and reverse causation. Therefore, we explored the causal relationship between intake of allium vegetables and digestive system cancers using Mendelian randomization approach. Methods: First, we performed Mendelian randomization analyses using inverse variance weighting (IVW), weighted median, and MR-Egger approaches, and demonstrated the reliability of the results in the sensitivity step. Second, Multivariable Mendelian randomization was applied to adjust for smoking and alcohol consumption. Third, we explored the molecular mechanisms behind the positive results through network pharmacology and molecular docking methods. Results: The study suggests that increased intake of garlic reduced gastric cancer risk. However, onion intake was not statistically associated with digestive system cancer. Conclusion: Garlic may have a protective effect against gastric cancer.

Single-photon detectors (SPDs) are widely used in applications requiring extremely weak light detection. In the near-infrared region, SPDs based on InGaAs/InP single-photon avalanche diodes (SPADs) are the primary candidates for practical applications because of their small size, low cost and ease of operation. Driven by the escalating demands for quantum communication and lidar, the performance of InGaAs/InP SPDs has been continuously enhanced. This paper provides a comprehensive review of advances in InGaAs/InP SPDs over the past 10 years, including the investigation into SPAD structures and mechanisms, as well as emerging readout techniques for both gated and free-running mode SPDs. In addition, future prospects are also summarised., Comment: Accepted by Measurement Science and Technology

Linear-in-$k$ Rashba spin-orbit coupling is crucial for achieving topological superconductivity. The wave vector dependence of this spin-orbit coupling can vary across materials, exhibiting linear, cubic, or a combination of both forms. Notably, cubic Rashba spin-orbit coupling induces a distinct triple spin winding on the Fermi surface, differentiating it from linear Rashba spin-orbit coupling. In this Letter, we investigate the potential for two-dimensional topological superconductivity in an interacting bilayer Rashba spin-orbit coupled system with local inversion symmetry breaking. We discover an intriguing interplay between the unique spin texture induced by cubic Rashba spin-orbit coupling and odd-parity Cooper pairing mechanisms. This interplay leads to a mirror symmetry-protected topological crystalline superconductor hosting three pairs of Majorana edge modes associated with an effective helical $f$-wave Cooper pairing. The bulk topology of the helical $f$-wave superconductor is characterized by a mirror Chern number $n_M=3$, which remains stable even in the presence of coexisting linear and cubic Rashba spin-orbit couplings. Our work not only proposes an approach to engineering topological mirror superconductors but also uncovers a pathway to realizing rare helical $f$-wave pairing., Comment: Comments are welcome

The emergence of deep and large-scale spiking neural networks (SNNs) exhibiting high performance across diverse complex datasets has led to a need for compressing network models due to the presence of a significant number of redundant structural units, aiming to more effectively leverage their low-power consumption and biological interpretability advantages. Currently, most model compression techniques for SNNs are based on unstructured pruning of individual connections, which requires specific hardware support. Hence, we propose a structured pruning approach based on the activity levels of convolutional kernels named Spiking Channel Activity-based (SCA) network pruning framework. Inspired by synaptic plasticity mechanisms, our method dynamically adjusts the network's structure by pruning and regenerating convolutional kernels during training, enhancing the model's adaptation to the current target task. While maintaining model performance, this approach refines the network architecture, ultimately reducing computational load and accelerating the inference process. This indicates that structured dynamic sparse learning methods can better facilitate the application of deep SNNs in low-power and high-efficiency scenarios.

Humans learn multiple tasks in succession with minimal mutual interference, through the context gating mechanism in the prefrontal cortex (PFC). The brain-inspired models of spiking neural networks (SNN) have drawn massive attention for their energy efficiency and biological plausibility. To overcome catastrophic forgetting when learning multiple tasks in sequence, current SNN models for lifelong learning focus on memory reserving or regularization-based modification, while lacking SNN to replicate human experimental behavior. Inspired by biological context-dependent gating mechanisms found in PFC, we propose SNN with context gating trained by the local plasticity rule (CG-SNN) for lifelong learning. The iterative training between global and local plasticity for task units is designed to strengthen the connections between task neurons and hidden neurons and preserve the multi-task relevant information. The experiments show that the proposed model is effective in maintaining the past learning experience and has better task-selectivity than other methods during lifelong learning. Our results provide new insights that the CG-SNN model can extend context gating with good scalability on different SNN architectures with different spike-firing mechanisms. Thus, our models have good potential for parallel implementation on neuromorphic hardware and model human's behavior.

The deployment of large language models (LLMs) faces considerable challenges concerning resource constraints and inference efficiency. Recent research has increasingly focused on smaller, task-specific models enhanced by distilling knowledge from LLMs. However, prior studies have often overlooked the diversity and quality of knowledge, especially the untapped potential of negative knowledge. Constructing effective negative knowledge remains severely understudied. In this paper, we introduce a novel framework called quality-guided contrastive rationale distillation aimed at enhancing reasoning capabilities through contrastive knowledge learning. For positive knowledge, we enrich its diversity through temperature sampling and employ self-consistency for further denoising and refinement. For negative knowledge, we propose an innovative self-adversarial approach that generates low-quality rationales by sampling previous iterations of smaller language models, embracing the idea that one can learn from one's own weaknesses. A contrastive loss is developed to distill both positive and negative knowledge into smaller language models, where an online-updating discriminator is integrated to assess qualities of rationales and assign them appropriate weights, optimizing the training process. Through extensive experiments across multiple reasoning tasks, we demonstrate that our method consistently outperforms existing distillation techniques, yielding higher-quality rationales.

Spiking Neural Networks (SNNs) aim to bridge the gap between neuroscience and machine learning by emulating the structure of the human nervous system. However, like convolutional neural networks, SNNs are vulnerable to adversarial attacks. To tackle the challenge, we propose a biologically inspired methodology to enhance the robustness of SNNs, drawing insights from the visual masking effect and filtering theory. First, an end-to-end SNN-based image purification model is proposed to defend against adversarial attacks, including a noise extraction network and a non-blind denoising network. The former network extracts noise features from noisy images, while the latter component employs a residual U-Net structure to reconstruct high-quality noisy images and generate clean images. Simultaneously, a multi-level firing SNN based on Squeeze-and-Excitation Network is introduced to improve the robustness of the classifier. Crucially, the proposed image purification network serves as a pre-processing module, avoiding modifications to classifiers. Unlike adversarial training, our method is highly flexible and can be seamlessly integrated with other defense strategies. Experimental results on various datasets demonstrate that the proposed methodology outperforms state-of-the-art baselines in terms of defense effectiveness, training time, and resource consumption., Comment: 8 pages, 5 figures, ECAI2024 under review

Magnetic levitation based on the flux pinning nature of type II superconductors has the merit of self-stability, making it appealing for applications such as high speed bearings, maglev trains, space generators, etc. However, such levitation systems physically rely on the superconductor pre-capturing magnetic flux (i.e. field cooling process) before establishing the levitation state which is nonadjustable afterwards. Moreover, practical type II superconductors in the levitation system inevitably suffer from various sources of energy losses, leading to continuous levitation force decay. These intrinsic drawbacks make superconducting maglev inflexible and impractical for long term operation. Here we propose and demonstrate a new form of superconducting maglev which is tunable and with self-stability. The maglev system uses a closed-loop type II superconducting coil to lock flux of a magnet, establishing self-stable levitation between the two objects. A flux pump is used to modulate the total magnetic flux of the coil without breaking its superconductivity, thus flexibly tuning levitation force and height meanwhile maintaining self-stability. For the first time, we experimentally demonstrate a self-stable type II superconducting maglev system which is able to: counteract long term levitation force decay, adjust levitation force and equilibrium position, and establish levitation under zero field cooling condition. These breakthroughs may bridge the gap between demonstrations and practical applications of type II superconducting maglevs., Comment: 15pages,5 figures

Quantum randomness relies heavily on the accurate characterization of the generator implementation, where the device imperfection or inaccurate characterization can lead to incorrect entropy estimation and practical bias, significantly affecting the reliability of the generated randomness. Measurement-device-independent (MDI) quantum random number generation (QRNG) endeavors to produce certified randomness, utilizing uncharacterized and untrusted measurement devices that are vulnerable to numerous attack schemes targeting measurement loopholes. However, existing implementations have shown insufficient performance thus far. Here, we propose a high-speed MDI-QRNG scheme based on a robust measurement tomography approach against the imperfection of single-photon sources. Compared with the conventional approach, the decoy-state method is introduced to obtain more accurate tomography results and a tighter lower bound of randomness. Finally, by using a high-speed time-bin encoding system, we experimentally demonstrated the scheme and obtained a reliable min-entropy lower bound of $7.37 \times 10^{-2}$ bits per pulse, corresponding to a generation rate over 23 Mbps, which substantially outperforms the existing realizations and makes a record in discrete-variable semi-device-independent QRNGs., Comment: 20 pages, 9 figures, including appendixes. Accepted for publication in Quantum Science and Technology

Creating 3D textured meshes using generative artificial intelligence has garnered significant attention recently. While existing methods support text-based generative texture generation or editing on 3D meshes, they often struggle to precisely control pixels of texture images through more intuitive interaction. While 2D images can be edited generatively using drag interaction, applying this type of methods directly to 3D mesh textures still leads to issues such as the lack of local consistency among multiple views, error accumulation and long training times. To address these challenges, we propose a generative point-based 3D mesh texture editing method called DragTex. This method utilizes a diffusion model to blend locally inconsistent textures in the region near the deformed silhouette between different views, enabling locally consistent texture editing. Besides, we fine-tune a decoder to reduce reconstruction errors in the non-drag region, thereby mitigating overall error accumulation. Moreover, we train LoRA using multi-view images instead of training each view individually, which significantly shortens the training time. The experimental results show that our method effectively achieves dragging textures on 3D meshes and generates plausible textures that align with the desired intent of drag interaction.

The emergence of novel the dummy data injection attack (DDIA) poses a severe threat to the secure and stable operation of power systems. These attacks are particularly perilous due to the minimal Euclidean spatial separation between the injected malicious data and legitimate data, rendering their precise detection challenging using conventional distance-based methods. Furthermore, existing research predominantly focuses on various machine learning techniques, often analyzing the temporal data sequences post-attack or relying solely on Euclidean spatial characteristics. Unfortunately, this approach tends to overlook the inherent topological correlations within the non-Euclidean spatial attributes of power grid data, consequently leading to diminished accuracy in attack localization. To address this issue, this study takes a comprehensive approach. Initially, it examines the underlying principles of these new DDIAs on power systems. Here, an intricate mathematical model of the DDIA is designed, accounting for incomplete topological knowledge and alternating current (AC) state estimation from an attacker's perspective. Subsequently, by integrating a priori knowledge of grid topology and considering the temporal correlations within measurement data and the topology-dependent attributes of the power grid, this study introduces temporal and spatial attention matrices. These matrices adaptively capture the spatio-temporal correlations within the attacks. Leveraging gated stacked causal convolution and graph wavelet sparse convolution, the study jointly extracts spatio-temporal DDIA features. Finally, the research proposes a DDIA localization method based on spatio-temporal graph neural networks. The accuracy and effectiveness of the DDIA model are rigorously demonstrated through comprehensive analytical cases., Comment: Accepted by Applied Energy

Multi-modal large language models have demonstrated impressive performance across various tasks in different modalities. However, existing multi-modal models primarily emphasize capturing global information within each modality while neglecting the importance of perceiving local information across modalities. Consequently, these models lack the ability to effectively understand the fine-grained details of input data, limiting their performance in tasks that require a more nuanced understanding. To address this limitation, there is a compelling need to develop models that enable fine-grained understanding across multiple modalities, thereby enhancing their applicability to a wide range of tasks. In this paper, we propose GroundingGPT, a language enhanced multi-modal grounding model. Beyond capturing global information like other multi-modal models, our proposed model excels at tasks demanding a detailed understanding of local information within the input. It demonstrates precise identification and localization of specific regions in images or moments in videos. To achieve this objective, we design a diversified dataset construction pipeline, resulting in a multi-modal, multi-granularity dataset for model training. The code, dataset, and demo of our model can be found at https: //github.com/lzw-lzw/GroundingGPT.

Spiking neural networks (SNNs) serve as one type of efficient model to process spatio-temporal patterns in time series, such as the Address-Event Representation data collected from Dynamic Vision Sensor (DVS). Although convolutional SNNs have achieved remarkable performance on these AER datasets, benefiting from the predominant spatial feature extraction ability of convolutional structure, they ignore temporal features related to sequential time points. In this paper, we develop a recurrent spiking neural network (RSNN) model embedded with an advanced spiking convolutional block attention module (SCBAM) component to combine both spatial and temporal features of spatio-temporal patterns. It invokes the history information in spatial and temporal channels adaptively through SCBAM, which brings the advantages of efficient memory calling and history redundancy elimination. The performance of our model was evaluated in DVS128-Gesture dataset and other time-series datasets. The experimental results show that the proposed SRNN-SCBAM model makes better use of the history information in spatial and temporal dimensions with less memory space, and achieves higher accuracy compared to other models.

Driven by the term "the arrow of time" as a general topic, the article develops a musical discussion by referring to the etymological origin of the term: philosophy (epistemology) and physics (thermodynamics). In particular, the article explores two specific conditions: distinguishability and unique orientability, from which the article derives respective musical propositions and case studies. For the distinguishability condition, the article focuses on the "recurrence" in music and tries to interpret Bach's Christmas Oratorio from the perspective of "birth/resurrection". For the unique orientability condition, the article discusses the process of delaying the climax, thereby proposing "AB-AAB left-replication" model, implying an organicist view by treating the temporal structure of music (e.g. form) as the product of a dynamic process: organic growth.

In recent years, analog circuits have received extensive attention and are widely used in many emerging applications. The high demand for analog circuits necessitates shorter circuit design cycles. To achieve the desired performance and specifications, various geometrical symmetry constraints must be carefully considered during the analog layout process. However, the manual labeling of these constraints by experienced analog engineers is a laborious and time-consuming process. To handle the costly runtime issue, we propose a graph-based learning framework to automatically extract symmetric constraints in analog circuit layout. The proposed framework leverages the connection characteristics of circuits and the devices' information to learn the general rules of symmetric constraints, which effectively facilitates the extraction of device-level constraints on circuit netlists. The experimental results demonstrate that compared to state-of-the-art symmetric constraint detection approaches, our framework achieves higher accuracy and F1-score., Comment: 11 pages,10 figures, 6 tables, 1 algorithm

Mobile health has emerged as a major success for tracking individual health status, due to the popularity and power of smartphones and wearable devices. This has also brought great challenges in handling heterogeneous, multi-resolution data which arise ubiquitously in mobile health due to irregular multivariate measurements collected from individuals. In this paper, we propose an individualized dynamic latent factor model for irregular multi-resolution time series data to interpolate unsampled measurements of time series with low resolution. One major advantage of the proposed method is the capability to integrate multiple irregular time series and multiple subjects by mapping the multi-resolution data to the latent space. In addition, the proposed individualized dynamic latent factor model is applicable to capturing heterogeneous longitudinal information through individualized dynamic latent factors. Our theory provides a bound on the integrated interpolation error and the convergence rate for B-spline approximation methods. Both the simulation studies and the application to smartwatch data demonstrate the superior performance of the proposed method compared to existing methods., Comment: 43 pages, 3 figures

Free-running InGaAs/InP single-photon detectors (SPDs) based on negative-feedback avalanche diodes (NFADs) are the key components for applications requiring asynchronous single-photon detection in the near-infrared region. From the perspective of practical applications, the features of SPDs in terms of high photon detection efficiency (PDE), low noise, large sensitive area, and compactness are highly desired for system integration and performance enhancement. Here, we present the implementation of a compact four-channel multimode fiber coupling free-running InGaAs/InP SPD, with the best overall performance to date. On the one hand, we design and fabricate structure-optimized InGaAs/InP NFAD devices with 25 $\mu$m diameter active area and integrated thin film resistors to enhance the maximum achievable PDE. On the other hand, we apply a compact thermoacoustic cryocooler to regulate the operating temperature of NFADs within a large range, and design a dedicated readout circuit with minimized parasitic parameters and tunable settings of hold-off time to suppress the afterpulsing effect. The SPD is then characterized to achieve remarkable overall performance simultaneously at 1550 nm, i.e., 40% PDE, 2.3 kcps dark count rate, 8% afterpulse probability and 49 ps timing jitter (full width at half maximum) under the conditions of 5.9 V excess bias voltage, 10 $\mu$s hold-off time and 213 K operation temperature. Such performance and the results of the long-term stability tests indicate that the SPD could be a favorable solution for practical applications., Comment: 7 pages, 7 figures. Accepted for publication in the IEEE Journal of Selected Topics in Quantum Electronics

Individualized treatment rules (ITRs) have been widely applied in many fields such as precision medicine and personalized marketing. Beyond the extensive studies on ITR for binary or multiple treatments, there is considerable interest in applying combination treatments. This paper introduces a novel ITR estimation method for combination treatments incorporating interaction effects among treatments. Specifically, we propose the generalized $\psi$-loss as a non-convex surrogate in the residual weighted learning framework, offering desirable statistical and computational properties. Statistically, the minimizer of the proposed surrogate loss is Fisher-consistent with the optimal decision rules, incorporating interaction effects at any intensity level - a significant improvement over existing methods. Computationally, the proposed method applies the difference-of-convex algorithm for efficient computation. Through simulation studies and real-world data applications, we demonstrate the superior performance of the proposed method in recommending combination treatments.

Spiking neural networks (SNNs) have manifested remarkable advantages in power consumption and event-driven property during the inference process. To take full advantage of low power consumption and improve the efficiency of these models further, the pruning methods have been explored to find sparse SNNs without redundancy connections after training. However, parameter redundancy still hinders the efficiency of SNNs during training. In the human brain, the rewiring process of neural networks is highly dynamic, while synaptic connections maintain relatively sparse during brain development. Inspired by this, here we propose an efficient evolutionary structure learning (ESL) framework for SNNs, named ESL-SNNs, to implement the sparse SNN training from scratch. The pruning and regeneration of synaptic connections in SNNs evolve dynamically during learning, yet keep the structural sparsity at a certain level. As a result, the ESL-SNNs can search for optimal sparse connectivity by exploring all possible parameters across time. Our experiments show that the proposed ESL-SNNs framework is able to learn SNNs with sparse structures effectively while reducing the limited accuracy. The ESL-SNNs achieve merely 0.28% accuracy loss with 10% connection density on the DVS-Cifar10 dataset. Our work presents a brand-new approach for sparse training of SNNs from scratch with biologically plausible evolutionary mechanisms, closing the gap in the expressibility between sparse training and dense training. Hence, it has great potential for SNN lightweight training and inference with low power consumption and small memory usage.