Electronic Design Automation (EDA) plays a crucial role in classical chip design and significantly influences the development of quantum chip design. However, traditional EDA tools cannot be directly applied to quantum chip design due to vast differences compared to the classical realm. Several EDA products tailored for quantum chip design currently exist, yet they only cover partial stages of the quantum chip design process instead of offering a fully comprehensive solution. Additionally, they often encounter issues such as limited automation, steep learning curves, challenges in integrating with actual fabrication processes, and difficulties in expanding functionality. To address these issues, we developed a full-stack EDA tool specifically for quantum chip design, called EDA-Q. The design workflow incorporates functionalities present in existing quantum EDA tools while supplementing critical design stages such as device mapping and fabrication process mapping, which users expect. EDA-Q utilizes a unique architecture to achieve exceptional scalability and flexibility. The integrated design mode guarantees algorithm compatibility with different chip components, while employing a specialized interactive processing mode to offer users a straightforward and adaptable command interface. Application examples demonstrate that EDA-Q significantly reduces chip design cycles, enhances automation levels, and decreases the time required for manual intervention. Multiple rounds of testing on the designed chip have validated the effectiveness of EDA-Q in practical applications.

The performance of models is intricately linked to the abundance of training data. In Visible-Infrared person Re-IDentification (VI-ReID) tasks, collecting and annotating large-scale images of each individual under various cameras and modalities is tedious, time-expensive, costly and must comply with data protection laws, posing a severe challenge in meeting dataset requirements. Current research investigates the generation of synthetic data as an efficient and privacy-ensuring alternative to collecting real data in the field. However, a specific data synthesis technique tailored for VI-ReID models has yet to be explored. In this paper, we present a novel data generation framework, dubbed Diffusion-based VI-ReID data Expansion (DiVE), that automatically obtain massive RGB-IR paired images with identity preserving by decoupling identity and modality to improve the performance of VI-ReID models. Specifically, identity representation is acquired from a set of samples sharing the same ID, whereas the modality of images is learned by fine-tuning the Stable Diffusion (SD) on modality-specific data. DiVE extend the text-driven image synthesis to identity-preserving RGB-IR multimodal image synthesis. This approach significantly reduces data collection and annotation costs by directly incorporating synthetic data into ReID model training. Experiments have demonstrated that VI-ReID models trained on synthetic data produced by DiVE consistently exhibit notable enhancements. In particular, the state-of-the-art method, CAJ, trained with synthetic images, achieves an improvement of about 9% in mAP over the baseline on the LLCM dataset.

Existing diffusion-based video super-resolution (VSR) methods are susceptible to introducing complex degradations and noticeable artifacts into high-resolution videos due to their inherent randomness. In this paper, we propose a noise-robust real-world VSR framework by incorporating self-supervised learning and Mamba into pre-trained latent diffusion models. To ensure content consistency across adjacent frames, we enhance the diffusion model with a global spatio-temporal attention mechanism using the Video State-Space block with a 3D Selective Scan module, which reinforces coherence at an affordable computational cost. To further reduce artifacts in generated details, we introduce a self-supervised ControlNet that leverages HR features as guidance and employs contrastive learning to extract degradation-insensitive features from LR videos. Finally, a three-stage training strategy based on a mixture of HR-LR videos is proposed to stabilize VSR training. The proposed Self-supervised ControlNet with Spatio-Temporal Continuous Mamba based VSR algorithm achieves superior perceptual quality than state-of-the-arts on real-world VSR benchmark datasets, validating the effectiveness of the proposed model design and training strategies.

Large language models (LLMs) have brought about significant transformations in human society. Among the crucial computations in LLMs, the softmax unit holds great importance. Its helps the model generating a probability distribution on potential subsequent words or phrases, considering a series of input words. By utilizing this distribution, the model selects the most probable next word or phrase, based on the assigned probabilities. The softmax unit assumes a vital function in LLM training as it facilitates learning from data through the adjustment of neural network weights and biases.With the development of the size of LLMs, computing the gradient becomes expensive. However, Zero-th Order method can approximately compute the gradient with only forward passes. In this paper, we present a Zero-th Order algorithm specifically tailored for Softmax optimization. We demonstrate the convergence of our algorithm, highlighting its effectiveness in efficiently computing gradients for large-scale LLMs. By leveraging the Zeroth-Order method, our work contributes to the advancement of optimization techniques in the context of complex language models.

Influence maximization(IM) aims to identify a set of nodes$S$to maximize the expected number of nodes influenced during the information propagation starting from$S$. Some works had extended this problem to betopic-aware, where each node is associated with a topic distribution and tends to be activated with different probabilities by different topics. However, whether it is topic-aware or not, IM problem only focuses on the active nodes and overlooks all the inactive ones. Actually, an inactive node may receive the information from their active in-neighbors and become informed. Therefore, this type of nodes should also be considered when measuring the coverage of information propagation. Inspired by this, we formulate a new problem calledtopic-aware information coverage maximization(TAICM), which aims to maximize the sum of the expected number of both active and informed nodes in topic-aware social networks. Then we devise a heuristic method to solve it. Experiments on three real-world datasets demonstrate that our method can achieve similar or higher information coverage in much less or at least acceptable time than some commonly used IM algorithms.

RGB-Infrared person re-identification (RGB-IR ReID) aims to associate people across disjoint RGB and IR camera views. Currently, state-of-the-art performance of RGB-IR ReID is not as impressive as that of conventional ReID. Much of that is due to the notorious modality bias training issue brought by the single-modality ImageNet pre-training, which might yield RGB-biased representations that severely hinder the cross-modality image retrieval. This paper makes first attempt to tackle the task from a pre-training perspective. We propose a self-supervised pre-training solution, named Modality-Aware Multiple Granularity Learning (MMGL), which directly trains models from scratch only on multi-modal ReID datasets, but achieving competitive results against ImageNet pre-training, without using any external data or sophisticated tuning tricks. First, we develop a simple-but-effective ‘permutation recovery’ pretext task that globally maps shuffled RGB-IR images into a shared latent permutation space, providing modality-invariant global representations for downstream ReID tasks. Second, we present a part-aware cycle-contrastive (PCC) learning strategy that utilizes cross-modality cycle-consistency to maximize agreement between semantically similar RGB-IR image patches. This enables contrastive learning for the unpaired multi-modal scenarios, further improving the discriminability of local features without laborious instance augmentation. Based on these designs, MMGL effectively alleviates the modality bias training problem. Extensive experiments demonstrate that it learns better representations (+8.03% Rank-1 accuracy) with faster training speed (converge only in few hours) and higher data efficiency (<5% data size) than ImageNet pre-training. The results also suggest it generalizes well to various existing models, losses and has promising transferability across datasets. The code will be released at https://github.com/hansonchen1996/MMGL.

Deep reinforcement learning (DRL) is a machine learning method based on rewards, which can be extended to solve some complex and realistic decision-making problems. Autonomous driving needs to deal with a variety of complex and changeable traffic scenarios, so the application of DRL in autonomous driving presents a broad application prospect. In this article, an end-to-end autonomous driving policy learning method based on DRL is proposed. On the basis of proximal policy optimization (PPO), we combine a curiosity-driven method called recurrent neural network (RNN) to generate an intrinsic reward signal to encounter the agent to explore its environment, which improves the efficiency of exploration. We introduce an auxiliary critic network on the original actor-critic framework and choose the lower estimate which is predicted by the dual critic network when the network update to avoid the overestimation bias. We test our method on the lane- keeping task and overtaking task in the open racing car simulator (TORCS) driving simulator and compare with other DRL methods, experimental results show that our proposed method can improve the training efficiency and control performance in driving tasks.

RGB-Infrared person re-identification (RGB-IR ReID) is a challenging cross-modality retrieval problem, which aims at matching the person-of-interest over visible and infrared camera views. Most existing works achieve performance gains through manually-designed feature selection modules, which often require significant domain knowledge and rich experience. In this paper, we study a general paradigm, termed Neural Feature Search (NFS), to automate the process of feature selection. Specifically, NFS combines a dual-level feature search space and a differentiable search strategy to jointly select identity-related cues in coarse-grained channels and fine-grained spatial pixels. This combination allows NFS to adaptively filter background noises and concentrate on informative parts of human bodies in a data-driven manner. Moreover, a cross-modality contrastive optimization scheme further guides NFS to search features that can minimize modality discrepancy whilst maximizing inter-class distance. Extensive experiments on mainstream benchmarks demonstrate that our method outperforms state-of-the-arts, especially achieving better performance on the RegDB dataset with significant improvement of 11.20% and 8.64% in Rank-1 and mAP, respectively.

Near-infrared-visual (NIR-VIS) heterogeneous face recognition (HFR) aims to match NIR face images with the corresponding VIS ones. It is a challenging task due to the sensing gaps among different modalities. Occlusions in the input face images make the task extremely complex. To tackle these problems, we present a Saliency Search Network (SSN) to extract domain-invariant identity features. We propose to automatically search the efficient parts of face images in a modality-aware manner, and remove redundant information. Moreover, the searching process is guided by an information bottleneck network, which mitigates the overfitting problems caused by small datasets. Extensive experiments on both complete and partial NIR-VIS HFR on multiple datasets demonstrate the effectiveness and robustness of the proposed method to modality discrepancy and occlusions.

Neural architecture search (NAS) advances beyond the state-of-the-art in various computer vision tasks by automating the designs of deep neural networks. In this paper, we aim to address three important questions in NAS: (1) How to measure the correlation between architectures and their performances? (2) How to evaluate the correlation between different architectures? (3) How to learn these correlations with a small number of samples? To this end, we first model these correlations from a Bayesian perspective. Specifically, by introducing a novel Gaussian Process based NAS (GP-NAS) method, the correlations are modeled by the kernel function and mean function. The kernel function is also learnable to enable adaptive modeling for complex correlations in different search spaces. Furthermore, by incorporating a mutual information based sampling method, we can theoretically ensure the high-performance architecture with only a small set of samples. After addressing these problems, training GP-NAS once enables direct performance prediction of any architecture in different scenarios and may obtain efficient networks for different deployment platforms. Extensive experiments on both image classification and face recognition tasks verify the effectiveness of our algorithm.

Feature pyramids aim to learn multi-scale representations for detecting faces over various scales. However, they often lack adequate context over different scales, especially when there are many tiny faces in the wild. In this paper, we propose an attention-guided semantically enriched feature aggregation framework to learn a feature pyramid with rich semantics at all scales for face detection. Specifically, high-level abstract features are directly integrated into low-level representations by skip connections to retain as much semantic as possible. In addition, an attention mechanism is employed as a gate to emphasize relevant features and suppress useless features during feature fusion. Inspired by human visual perception of tiny faces, we specially design a deep progressive refined loss (DPRL) to effectively facilitate feature learning. According to the above principles, we design and investigate various feature pyramid frameworks through extensive experiments. Finally, two typical structures named Centralized Attention Feature (CAF) and Distributed Attention Feature (DAF) are proposed for face detection, which are in-place and end-to-end trainable. Extensive experiments across different aggregation architectures on four challenging face detection benchmarks demonstrate the superiority of our framework over state-of-the-art methods.

Recent works have made great progress in semantic segmentation by exploiting richer context, most of which are designed from a spatial perspective. In contrast to previous works, we present the concept of class center which extracts the global context from a categorical perspective. This class-level context describes the overall representation of each class in an image. We further propose a novel module, named Attentional Class Feature (ACF) module, to calculate and adaptively combine different class centers according to each pixel. Based on the ACF module, we introduce a coarse-to-fine segmentation network, called Attentional Class Feature Network (ACFNet), which can be composed of an ACF module and any off-the-shell segmentation network (base network). In this paper, we use two types of base networks to evaluate the effectiveness of ACFNet. We achieve new state-of-the-art performance of 81.85% mIoU on Cityscapes dataset with only finely annotated data used for training.

We present a novel introspective variational autoencoder (IntroVAE) model for synthesizing high-resolution photographic images. IntroVAE is capable of self-evaluating the quality of its generated samples and improving itself accordingly. Its inference and generator models are jointly trained in an introspective way. On one hand, the generator is required to reconstruct the input images from the noisy outputs of the inference model as normal VAEs. On the other hand, the inference model is encouraged to classify between the generated and real samples while the generator tries to fool it as GANs. These two famous generative frameworks are integrated in a simple yet efficient single-stream architecture that can be trained in a single stage. IntroVAE preserves the advantages of VAEs, such as stable training and nice latent manifold. Unlike most other hybrid models of VAEs and GANs, IntroVAE requires no extra discriminators, because the inference model itself serves as a discriminator to distinguish between the generated and real samples. Experiments demonstrate that our method produces high-resolution photo-realistic images (e.g., CELEBA images at (1024^{2})), which are comparable to or better than the state-of-the-art GANs.

Cross-modal matching methods match data from different modalities according to their similarities. Most existing methods utilize label information to reduce the semantic gap between different modalities. However, it is usually time-consuming to manually label large-scale data. This paper proposes a Self-Paced Cross-Modal Subspace Matching (SCSM) method for unsupervised multimodal data. We assume that multimodal data are pair-wised and from several semantic groups, which form hard pair-wised constraints and soft semantic group constraints respectively. Then, we formulate the unsupervised cross-modal matching problem as a non-convex joint feature learning and data grouping problem. Self-paced learning, which learns samples from 'easy' to 'complex', is further introduced to refine the grouping result. Moreover, a multimodal graph is constructed to preserve the relationship of both inter- and intra-modality similarity. An alternating minimization method is employed to minimize the non-convex optimization problem, followed by the discussion on its convergence analysis and computational complexity. Experimental results on four multimodal databases show that SCSM outperforms state-of-the-art cross-modal subspace learning methods.

In ultra dense heterogeneous networks (HetNets), the interference becomes more serious since multiple small cells coexist in the coverage area of the macrocells and share the same spectrum. An efficient interference coordination method is adjusting the transmit powers of all cells in a cooperative way. However, under practical serving cell selection rules in which serving cells of users alter with the variation of cell powers, finding optimal cell powers becomes a difficult problem. In this paper, an improved modified particle swarm optimization (MPSO) is proposed to tackle this difficult problem caused by the altering of serving cell. Local search and multi-restart process are introduced to guarantee the local and then global optimality, and the convergence conditions and global optimality are proved by mathematical deduction to guide the selection of the parameters. Simulations show that the proposed algorithm can significantly improve system throughput compared with existing algorithms which do not consider the alteration of serving cells. By improving MPSO, the proposed algorithm can spend less iteration time to achieve higher system throughput, and exhibit similar performance as exhaustive search in both system throughput and the signal to interference plus noise ratio (SINR) of users.

The intensive downlink (DL) inter-cell interference created by cell range expansion (CRE) of picocells is an urgent problem needing to be solved under macro-pico heterogeneous network (HetNet) scenario. A promising approach is taking advantage of additional degree of freedom brought by carrier aggregation (CA). However, poorly arranged carrier configurations or interference coordination schemes can lead to a degradation of system overall performance. In this paper, we propose a novel dynamic interference coordination scheme based on carrier aggregation to alleviate the DL interference from macrocells to users located in the cell range expansion area. Novel carrier configuration pattern and dynamic power control scheme based on price algorithm are applied to mitigate detrimental interference to picocell-edge users and improve the availability of macrocells. Simulation results show that the proposed scheme can boost the picocell-edge throughput significantly while ameliorating the overall system throughput.

In this paper, we propose a novel opportunistic scheduling algorithm in multi-cell cooperation scenario, i.e., joint multi-user diversity (MUD) exploitation and inter-cell interference (ICI) mitigation based scheduling (MEIMS). Our algorithm jointly considers the intended channel condition of the scheduled user from its serving cell and the orthogonality between that and the corresponding interference channels to concurrently scheduled users in neighboring cells so as to exploit MUD and mitigate ICI simultaneously. The performance of our algorithm is evaluated through simulation. Results show that, our scheme can significantly enhance the received signal to interference plus noise ratio (SINR) with relatively better fairness guarantee, thus achieves the largest throughput and utility comparing to several well-known scheduling algorithms.

3GPP LTE networks can provide a higher capacity by adopting advanced physical layer techniques and serve users with different Quality of Service (QoS) requirements. However, unbalanced user distributions and strong inter-cell interference (ICI) still deteriorate network performances severely. Since fractional frequency reuse (FFR) technique is recommended to mitigate ICI, we investigate the load balancing problem in a 3GPP LTE multi-cell FFR network with heterogenous services in this paper. Firstly we formulate a multi-objective optimization problem, whose objectives are intra- and inter-cell load balancing index for users with QoS requirements and total utility function for users without QoS requirements. Then we analyze the complexity of the problem and propose a practical algorithm which includes QoS aware intra- and inter-cell handover and call admission control. Extensive simulations are conducted, the results show that our algorithm can lead to significantly better performances, i.e., a lower new call blocking rate for users with QoS requirements, a larger utility for users without QoS requirements at the cost of a bit degradation of total throughput.

In this paper, we propose a novel opportunistic scheduling algorithm, joint useful and interference channel based scheduling (JUICS), in coordinated multi-point (CoMP) transmission scenario. Our scheme jointly considers the useful channel condition of the scheduled user from its serving cell and the orthogonality between that and the corresponding interference channels to concurrently scheduled users in neighboring CoMP cells, thus to exploit multi-user diversity (MUD) and mitigate inter-cell interference (ICI) simultaneously. The performance of the proposed algorithm is evaluated through simulation in terms of the cumulative distribution performance of the received signal to interference plus noise ratio (SINR) and that of the scheduled times of all CoMP users. Results show that, with limited complexity and overhead, our scheme can significantly enhance the received SINR with relatively better fairness guarantee, thus to achieve the largest throughput and utility comparing to several well-known scheduling algorithms.