Searcharxiv⌕ Search

arXiv subjects

Wei Wu

Publications and source records attributed to Wei Wu.

At least 253 records · Page 14Linked to original sources
arXiv2024

AFPR-CIM: An Analog-Domain Floating-Point RRAM-based Compute-In-Memory Architecture with Dynamic Range Adaptive FP-ADC

Power consumption has become the major concern in neural network accelerators for edge devices. The novel non-volatile-memory (NVM) based computing-in-memory (CIM) architecture has shown great potential for better energy efficiency. However, most of the recent NVM-CIM solutions mainly focus on fixed-point calculation and are not applicable to floating-point (FP) processing. In this paper, we propose an analog-domain floating-point CIM architecture (AFPR-CIM) based on resistive random-access memory (RRAM). A novel adaptive dynamic-range FP-ADC is designed to convert the analog computation results into FP codes. Output current with high dynamic range is converted to a normalized voltage range for readout, to prevent precision loss at low power consumption. Moreover, a novel FP-DAC is also implemented which reconstructs FP digital codes into analog values to perform analog computation. The proposed AFPR-CIM architecture enables neural network acceleration with FP8 (E2M5) activation for better accuracy and energy efficiency. Evaluation results show that AFPR-CIM can achieve 19.89 TFLOPS/W energy efficiency and 1474.56 GOPS throughput. Compared to traditional FP8 accelerator, digital FP-CIM, and analog INT8-CIM, this work achieves 4.135x, 5.376x, and 2.841x energy efficiency enhancement, respectively.

eess.SY↗
arXiv2024

Human Aesthetic Preference-Based Large Text-to-Image Model Personalization: Kandinsky Generation as an Example

With the advancement of neural generative capabilities, the art community has actively embraced GenAI (generative artificial intelligence) for creating painterly content. Large text-to-image models can quickly generate aesthetically pleasing outcomes. However, the process can be non-deterministic and often involves tedious trial-and-error, as users struggle with formulating effective prompts to achieve their desired results. This paper introduces a prompting-free generative approach that empowers users to automatically generate personalized painterly content that incorporates their aesthetic preferences in a customized artistic style. This approach involves utilizing ``semantic injection'' to customize an artist model in a specific artistic style, and further leveraging a genetic algorithm to optimize the prompt generation process through real-time iterative human feedback. By solely relying on the user's aesthetic evaluation and preference for the artist model-generated images, this approach creates the user a personalized model that encompasses their aesthetic preferences and the customized artistic style.

cs.AI↗
arXiv2024

MiniDisc: Minimal Distillation Schedule for Language Model Compression

Recent studies have uncovered that language model distillation is less effective when facing a large capacity gap between the teacher and the student, and introduced teacher assistant-based distillation to bridge the gap. As a connection, the scale and the performance of the teacher assistant is of vital importance to bring the knowledge from the teacher to the student. However, existing teacher assistant-based methods require maximally many trials before scheduling an optimal teacher assistant. To this end, we propose a minimal distillation schedule (MiniDisc) for scheduling the optimal teacher assistant in minimally one trial. In particular, motivated by the finding that the performance of the student is positively correlated to the scale-performance tradeoff of the teacher assistant, MiniDisc is designed with a $λ$-tradeoff to measure the optimality of the teacher assistant without trial distillation to the student. MiniDisc then can schedule the optimal teacher assistant with the best $λ$-tradeoff in a sandwich framework. MiniDisc is evaluated with an extensive set of experiments on GLUE. Experimental results demonstrate the improved efficiency our MiniDisc compared to several state-of-the-art baselines. We further apply MiniDisc to a language model with billions of parameters and show its scalability.

cs.CL↗
arXiv2024

One-dimensional Dexter-type excitonic topological phase transition

Recently topogical excitons have attracted much attention. However, studies on the topological properties of excitons in one dimension are still rare. Here we have computed the Zak phase for a generic one-dimensional dimerised excitonic model. Tuning relevant hopping parameters gives rise to a rich spectrum of physics, including non-trivial topological phase in uniform chain unlike the conventional Su-Shcrieffer-Heeger model, topologically nontrivial flat bands, and exotic fractional phase. a new concept of ``composite chiral site" was developed to interpret the Zak phase of $π$ in our calculations. Our finite-chain calculations substantiate topological edge states, providing more information about their characteristics. Most importantly, in the first time, a topological phase transition assisted by the Dexter electron exchange process has been found.

cond-mat.mes-hall↗
arXiv2024

Validating quantum-supremacy experiments with exact and fast tensor network contraction

The quantum supremacy experiment, such as Google Sycamore [Nature \textbf{574}, 505 (2019)], poses great challenge for classical verification due to the exponentially-increasing compute cost. Using a new-generation Sunway supercomputer within $8.5$ days, we provide a direct verification by computing three million exact amplitudes for the experimentally generated bitstrings, obtaining an XEB fidelity of $0.191\%$ (the estimated value is $0.224\%$). The leap of simulation capability is built on a multiple-amplitude tensor network contraction algorithm which systematically exploits the ``classical advantage" (the inherent ``store-and-compute" operation mode of von Neumann machines) of current supercomputers, and a fused tensor network contraction algorithm which drastically increases the compute efficiency on heterogeneous architectures. Our method has a far-reaching impact in solving quantum many-body problems, statistical problems as well as combinatorial optimization problems.

quant-ph↗
arXiv2023

PT-symmetric quantum sensing: advantages and restrictions

Quantum sensing utilizing unique quantum properties of non-Hermitian systems to realize ultra-precision measurements has been attracting increasing attention. However, the debate on whether non-Hermitian systems are superior to Hermitian counterparts in sensing remains an open question. Here, we investigate the quantum information in PT-symmetric quantum sensing utilizing two experimental schemes based on the trapped-ion platform. It turns out that the existence of advantages of non-Hermitian quantum sensing heavily depends on additional information resources carried by the extra degrees of freedom introduced to construct PT-symmetric quantum sensors. Moreover, the practical application of non-Hermitian quantum sensing with superior performance is primarily restricted by the additional resource consumption accompanied by the post-selection. Our study provides theoretical references for the construction of non-Hermitian quantum sensors with superior performance and has potential applications in research fields of quantum precision measurement and quantum information processing.

quant-ph↗
arXiv2023

Evaluating Point Cloud from Moving Camera Videos: A No-Reference Metric

Point cloud is one of the most widely used digital representation formats for three-dimensional (3D) contents, the visual quality of which may suffer from noise and geometric shift distortions during the production procedure as well as compression and downsampling distortions during the transmission process. To tackle the challenge of point cloud quality assessment (PCQA), many PCQA methods have been proposed to evaluate the visual quality levels of point clouds by assessing the rendered static 2D projections. Although such projection-based PCQA methods achieve competitive performance with the assistance of mature image quality assessment (IQA) methods, they neglect that the 3D model is also perceived in a dynamic viewing manner, where the viewpoint is continually changed according to the feedback of the rendering device. Therefore, in this paper, we evaluate the point clouds from moving camera videos and explore the way of dealing with PCQA tasks via using video quality assessment (VQA) methods. First, we generate the captured videos by rotating the camera around the point clouds through several circular pathways. Then we extract both spatial and temporal quality-aware features from the selected key frames and the video clips through using trainable 2D-CNN and pre-trained 3D-CNN models respectively. Finally, the visual quality of point clouds is represented by the video quality values. The experimental results reveal that the proposed method is effective for predicting the visual quality levels of the point clouds and even competitive with full-reference (FR) PCQA methods. The ablation studies further verify the rationality of the proposed framework and confirm the contributions made by the quality-aware features extracted via the dynamic viewing manner. The code is available at https://github.com/zzc-1998/VQA_PC.

cs.CV↗
arXiv2023

Hybrid Hierarchical DRL Enabled Resource Allocation for Secure Transmission in Multi-IRS-Assisted Sensing-Enhanced Spectrum Sharing Networks

Secure communications are of paramount importance in spectrum sharing networks due to the allocation and sharing characteristics of spectrum resources. To further explore the potential of intelligent reflective surfaces (IRSs) in enhancing spectrum sharing and secure transmission performance, a multiple intelligent reflection surface (multi-IRS)-assisted sensing-enhanced wideband spectrum sharing network is investigated by considering physical layer security techniques. An intelligent resource allocation scheme based on double deep Q networks (D3QN) algorithm and soft Actor-Critic (SAC) algorithm is proposed to maximize the secure transmission rate of the secondary network by jointly optimizing IRS pairings, subchannel assignment, transmit beamforming of the secondary base station, reflection coefficients of IRSs and the sensing time. To tackle the sparse reward problem caused by a significant amount of reflection elements of multiple IRSs, the method of hierarchical reinforcement learning is exploited. An alternative optimization (AO)-based conventional mathematical scheme is introduced to verify the computational complexity advantage of our proposed intelligent scheme. Simulation results demonstrate the efficiency of our proposed intelligent scheme as well as the superiority of multi-IRS design in enhancing secrecy rate and spectrum utilization. It is shown that inappropriate deployment of IRSs can reduce the security performance with the presence of multiple eavesdroppers (Eves), and the arrangement of IRSs deserves further consideration.

cs.IT↗
arXiv2023

Adaptive Resource Allocation for Semantic Communication Networks

Semantic communication, recognized as a promising technology for future intelligent applications, has received widespread research attention. Despite the potential of semantic communication to enhance transmission reliability, especially in low signal-to-noise (SNR) environments, the critical issue of resource allocation and compatibility in the dynamic wireless environment remains largely unexplored. In this paper, we propose an adaptive semantic resource allocation paradigm with semantic-bit quantization (SBQ) compatibly for existing wireless communications, where the inaccurate environment perception introduced by the additional mapping relationship between semantic metrics and transmission metrics is solved. In order to investigate the performance of semantic communication networks, the quality of service for semantic communication (SC-QoS), including the semantic quantization efficiency (SQE) and transmission latency, is proposed for the first time. A problem of maximizing the overall effective SC-QoS is formulated by jointly optimizing the transmit beamforming of the base station, the bits for semantic representation, the subchannel assignment, and the bandwidth resource allocation. To address the non-convex formulated problem, an intelligent resource allocation scheme is proposed based on a hybrid deep reinforcement learning (DRL) algorithm, where the intelligent agent can perceive both semantic tasks and dynamic wireless environments. Simulation results demonstrate that our design can effectively combat semantic noise and achieve superior performance in wireless communications compared to several benchmark schemes. Furthermore, compared to mapping-guided paradigm based resource allocation schemes, our proposed adaptive scheme can achieve up to 13% performance improvement in terms of SC-QoS.

cs.IT↗
arXiv2023

Quantum metrology in the noisy intermediate-scale quantum era

Quantum metrology pursues the physical realization of higher-precision measurements to physical quantities than the classically achievable limit by exploiting quantum features, such as entanglement and squeezing, as resources. It has potential applications in developing next-generation frequency standards, magnetometers, radar, and navigation. However, the ubiquitous decoherence in the quantum world degrades the quantum resources and forces the precision back to or even worse than the classical limit, which is called the no-go theorem of noisy quantum metrology and greatly hinders its applications. Therefore, how to realize the promised performance of quantum metrology in realistic noisy situations attracts much attention in recent years. We will review the principle, categories, and applications of quantum metrology. Special attention will be paid to different quantum resources that can bring quantum superiority in enhancing sensitivity. Then, we will introduce the no-go theorem of noisy quantum metrology and its active control under different kinds of noise-induced decoherence situations.

quant-ph↗
arXiv2023

Depth-Based Statistical Inferences in the Spike Train Space

Metric-based summary statistics such as mean and covariance have been introduced in neural spike train space. They can properly describe template and variability in spike train data, but are often sensitive to outliers and expensive to compute. Recent studies also examine outlier detection and classification methods on point processes. These tools provide reasonable and efficient result, whereas the accuracy remains at a low level in certain cases. In this study, we propose to adopt a well-established notion of statistical depth to the spike train space. This framework can naturally define the median in a set of spike trains, which provides a robust description of the 'center' or 'template' of the observations. It also provides a principled method to identify 'outliers' in the data and classify data from different categories. We systematically compare the median with the state-of-the-art 'mean spike trains' in terms of robustness and efficiency. The performance of our novel outlier detection and classification tools will be compared with previous methods. The result shows the median has superior description for 'template' than the mean. Moreover, the proposed outlier detection and classification perform more accurately than previous methods. The advantages and superiority are well illustrated with simulations and real data.

stat.AP↗
arXiv2023

See SIFT in a Rain

Rain streaks bring complicated pixel intensity changes and additional gradients, greatly obstructing the extraction of image features from background. This causes serious performance degradation in feature-based applications. Thus, it is critical to remove rain streaks from a single rainy image to recover image features. Recently, many excellent image deraining methods have made remarkable progress. However, these human visual system-driven approaches mainly focus on improving image quality with pixel recovery as loss function, and neglect how to enhance image feature recovery ability. To address this issue, we propose a task-driven image deraining algorithm to strengthen image feature supply for subsequent feature-based applications. Due to the extensive use and strong practicability of Scale-Invariant Feature Transform (SIFT), we first propose two separate networks using distinct losses and modules to achieve two goals, respectively. One is difference of Gaussian (DoG) pyramid recovery network (DPRNet) for SIFT detection, and the other gradients of Gaussian images recovery network (GGIRNet) for SIFT description. Second, in the DPRNet we propose an alternative interest point loss that directly penalizes scale response extrema to recover the DoG pyramid. Third, we advance a gradient attention module in the GGIRNet to recover those gradients of Gaussian images. Finally, with the recovered DoG pyramid and gradients, we can regain SIFT key points. This divide-and-conquer scheme to set different objectives for SIFT detection and description leads to good robustness. Compared with state-of-the-art methods, experimental results demonstrate that our proposed algorithm achieves better performance in both the number of recovered SIFT key points and their accuracy.

eess.IV↗
arXiv2023

GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence

Conditional story generation is significant in human-machine interaction, particularly in producing stories with complex plots. While Large language models (LLMs) perform well on multiple NLP tasks, including story generation, it is challenging to generate stories with both complex and creative plots. Existing methods often rely on detailed prompts to guide LLMs to meet target conditions, which inadvertently restrict the creative potential of the generated stories. We argue that leveraging information from exemplary human-written stories facilitates generating more diverse plotlines. Delving deeper into story details helps build complex and credible plots. In this paper, we propose a retrieval-au\textbf{G}mented sto\textbf{R}y generation framework with a f\textbf{O}rest of e\textbf{V}id\textbf{E}nce (GROVE) to enhance stories' complexity. We build a retrieval repository for target conditions to produce few-shot examples to prompt LLMs. Additionally, we design an ``asking-why'' prompting scheme that extracts a forest of evidence, providing compensation for the ambiguities that may occur in the generated story. This iterative process uncovers underlying story backgrounds. Finally, we select the most fitting chains of evidence from the evidence forest and integrate them into the generated story, thereby enhancing the narrative's complexity and credibility. Experimental results and numerous examples verify the effectiveness of our method.

cs.CL↗
arXiv2023

Fractional partial differential variational inequality

In this present paper, we introduce and study a dynamical systems involving fractional derivative operator and nonlocal condition, which is constituted of a fractional evolution equation and a time-dependent variational inequality, and is named as fractional partial differential variational inequality (FPDVI, for short). By employing the estimates involving the one-and two-parameter Mittag-Leffler functions, fixed-point theory for set-value mappings, and non-compactness measure theory, we develop a general framework to establish the existence of smooth solutions to (FPDVI).

math.GM↗
arXiv2023

Tunable quantum dots in monolithic Fabry-Perot microcavities for high-performance single-photon sources

Cavity-enhanced single quantum dots (QDs) are the main approach towards ultra-high-performance solid-state quantum light sources for scalable photonic quantum technologies. Nevertheless, harnessing the Purcell effect requires precise spectral and spatial alignment of the QDs' emission with the cavity mode, which is challenging for most cavities. Here we have successfully integrated miniaturized Fabry-Perot microcavities with a piezoelectric actuator, and demonstrated a bright single photon source derived from a deterministically coupled QD within this microcavity. Leveraging the cavity-membrane structures, we have achieved large spectral-tunability via strain tuning. On resonance, we have obtained a high Purcell factor of approximately 9. The source delivers single photons with simultaneous high extraction efficiency of 0.58, high purity of 0.956(2) and high indistinguishability of 0.922(4). Together with a small footprint, our scheme facilitates the scalable integration of indistinguishable quantum light sources on-chip, and therefore removes a major barrier to the solid-state quantum information platforms based on QDs.

physics.optics↗
arXiv2023

Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning

Dancing to music is one of human's innate abilities since ancient times. In machine learning research, however, synthesizing dance movements from music is a challenging problem. Recently, researchers synthesize human motion sequences through autoregressive models like recurrent neural network (RNN). Such an approach often generates short sequences due to an accumulation of prediction errors that are fed back into the neural network. This problem becomes even more severe in the long motion sequence generation. Besides, the consistency between dance and music in terms of style, rhythm and beat is yet to be taken into account during modeling. In this paper, we formalize the music-conditioned dance generation as a sequence-to-sequence learning problem and devise a novel seq2seq architecture to efficiently process long sequences of music features and capture the fine-grained correspondence between music and dance. Furthermore, we propose a novel curriculum learning strategy to alleviate error accumulation of autoregressive models in long motion sequence generation, which gently changes the training process from a fully guided teacher-forcing scheme using the previous ground-truth movements, towards a less guided autoregressive scheme mostly using the generated movements instead. Extensive experiments show that our approach significantly outperforms the existing state-of-the-arts on automatic metrics and human evaluation. We also make a demo video to demonstrate the superior performance of our proposed approach at https://www.youtube.com/watch?v=lmE20MEheZ8.

cs.CV↗
arXiv2023

Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion

Transformer-based pre-trained models like BERT have achieved great progress on Semantic Sentence Matching. Meanwhile, dependency prior knowledge has also shown general benefits in multiple NLP tasks. However, how to efficiently integrate dependency prior structure into pre-trained models to better model complex semantic matching relations is still unsettled. In this paper, we propose the \textbf{D}ependency-Enhanced \textbf{A}daptive \textbf{F}usion \textbf{A}ttention (\textbf{DAFA}), which explicitly introduces dependency structure into pre-trained models and adaptively fuses it with semantic information. Specifically, \textbf{\emph{(i)}} DAFA first proposes a structure-sensitive paradigm to construct a dependency matrix for calibrating attention weights. It adopts an adaptive fusion module to integrate the obtained dependency information and the original semantic signals. Moreover, DAFA reconstructs the attention calculation flow and provides better interpretability. By applying it on BERT, our method achieves state-of-the-art or competitive performance on 10 public datasets, demonstrating the benefits of adaptively fusing dependency structure in semantic matching task.

cs.CL↗