arXiv subjects

Chenyang Li

Publications and source records attributed to Chenyang Li.

At least 73 records · Page 4Linked to original sources

arXiv2024

MapExpert: Online HD Map Construction with Simple and Efficient Sparse Map Element Expert

Constructing online High-Definition (HD) maps is crucial for the static environment perception of autonomous driving systems (ADS). Existing solutions typically attempt to detect vectorized HD map elements with unified models; however, these methods often overlook the distinct characteristics of different non-cubic map elements, making accurate distinction challenging. To address these issues, we introduce an expert-based online HD map method, termed MapExpert. MapExpert utilizes sparse experts, distributed by our routers, to describe various non-cubic map elements accurately. Additionally, we propose an auxiliary balance loss function to distribute the load evenly across experts. Furthermore, we theoretically analyze the limitations of prevalent bird's-eye view (BEV) feature temporal fusion methods and introduce an efficient temporal fusion module called Learnable Weighted Moving Descentage. This module effectively integrates relevant historical information into the final BEV features. Combined with an enhanced slice head branch, the proposed MapExpert achieves state-of-the-art performance and maintains good efficiency on both nuScenes and Argoverse2 datasets.

cs.CV↗

arXiv2024

Efficacy of Temporal Interference Electrical Stimulation for Spinal Cord Injury Rehabilitation: A Case Series

Spinal cord injury (SCI) is a debilitating condition that often results in significant motor and sensory deficits, impacting the quality of life. Current rehabilitation methods, including physical therapy and electrical stimulation, offer variable outcomes and often require invasive procedures. Temporal interference (TI) stimulation has emerged as a novel, non-invasive neuromodulation technique capable of targeting deep neural structures with precision, providing a promising alternative for SCI rehabilitation. This study explores the efficacy of TI stimulation as a non-invasive approach for improving motor and sensory function in patients with incomplete SCI. Three male patients with incomplete cervical SCI (AIS D) participated in a two-week intervention consisting of 14 sessions of TI stimulation targeting their injury sites. TI stimulation was delivered using frequencies of 1000 Hz and 1040 Hz, with assessments conducted pre- and post-intervention, including motor and sensory evaluations, functional scales, and imaging studies.All participants demonstrated significant improvements in neurological function, motor strength, sensory perception, and functional independence. Neurological levels of injury shifted upward in all cases, with one patient improving from C5 to C7. Graded Redefined Assessment of Strength, Sensibility and Prehension (GRASSP) results shows additional strength, prehension and sensory outcomes obtained for the arm and hand functions of participants. Motor scores (UEMS and LEMS) increased, sensory scores for light touch and pin prick improved, and functional assessments, such as the Berg Balance Scale (BBS) and Barthel Index (BI), showed marked gains. Pain scores also decreased in two participants, highlighting additional therapeutic benefits.

q-bio.NC↗

arXiv2024

DyRoNet: Dynamic Routing and Low-Rank Adapters for Autonomous Driving Streaming Perception

The advancement of autonomous driving systems hinges on the ability to achieve low-latency and high-accuracy perception. To address this critical need, this paper introduces Dynamic Routing Network (DyRoNet), a low-rank enhanced dynamic routing framework designed for streaming perception in autonomous driving systems. DyRoNet integrates a suite of pre-trained branch networks, each meticulously fine-tuned to function under distinct environmental conditions. At its core, the framework offers a speed router module, developed to assess and route input data to the most suitable branch for processing. This approach not only addresses the inherent limitations of conventional models in adapting to diverse driving conditions but also ensures the balance between performance and efficiency. Extensive experimental evaluations demonstrate the adaptability of DyRoNet to diverse branch selection strategies, resulting in significant performance enhancements across different scenarios. This work establishes a new benchmark for streaming perception and provides valuable engineering insights for future work.

cs.CV↗

arXiv2024

Deep Computer Vision for Solar Physics Big Data: Opportunities and Challenges

With recent missions such as advanced space-based observatories like the Solar Dynamics Observatory (SDO) and Parker Solar Probe, and ground-based telescopes like the Daniel K. Inouye Solar Telescope (DKIST), the volume, velocity, and variety of data have made solar physics enter a transformative era as solar physics big data (SPBD). With the recent advancement of deep computer vision, there are new opportunities in SPBD for tackling problems that were previously unsolvable. However, there are new challenges arising due to the inherent characteristics of SPBD and deep computer vision models. This vision paper presents an overview of the different types of SPBD, explores new opportunities in applying deep computer vision to SPBD, highlights the unique challenges, and outlines several potential future research directions.

cs.CV↗

arXiv2024

Inverting the Leverage Score Gradient: An Efficient Approximate Newton Method

Leverage scores have become essential in statistics and machine learning, aiding regression analysis, randomized matrix computations, and various other tasks. This paper delves into the inverse problem, aiming to recover the intrinsic model parameters given the leverage scores gradient. This endeavor not only enriches the theoretical understanding of models trained with leverage score techniques but also has substantial implications for data privacy and adversarial security. We specifically scrutinize the inversion of the leverage score gradient, denoted as $g(x)$. An innovative iterative algorithm is introduced for the approximate resolution of the regularized least squares problem stated as $\min_{x \in \mathbb{R}^d} 0.5 \|g(x) - c\|_2^2 + 0.5\|\mathrm{diag}(w)Ax\|_2^2$. Our algorithm employs subsampled leverage score distributions to compute an approximate Hessian in each iteration, under standard assumptions, considerably mitigating the time complexity. Given that a total of $T = \log(\| x_0 - x^* \|_2/ ε)$ iterations are required, the cost per iteration is optimized to the order of $O( (\mathrm{nnz}(A) + d^ω ) \cdot \mathrm{poly}(\log(n/δ))$, where $\mathrm{nnz}(A)$ denotes the number of non-zero entries of $A$.

cs.LG↗

arXiv2024

On Model Compression for Neural Networks: Framework, Algorithm, and Convergence Guarantee

Model compression is a crucial part of deploying neural networks (NNs), especially when the memory and storage of computing devices are limited in many applications. This paper focuses on two model compression techniques: low-rank approximation and weight pruning in neural networks, which are very popular nowadays. However, training NN with low-rank approximation and weight pruning always suffers significant accuracy loss and convergence issues. In this paper, a holistic framework is proposed for model compression from a novel perspective of nonconvex optimization by designing an appropriate objective function. Then, we introduce NN-BCD, a block coordinate descent (BCD) algorithm to solve the nonconvex optimization. One advantage of our algorithm is that an efficient iteration scheme can be derived with closed-form, which is gradient-free. Therefore, our algorithm will not suffer from vanishing/exploding gradient problems. Furthermore, with the Kurdyka-Łojasiewicz (KŁ) property of our objective function, we show that our algorithm globally converges to a critical point at the rate of O(1/k), where k denotes the number of iterations. Lastly, extensive experiments with tensor train decomposition and weight pruning demonstrate the efficiency and superior performance of the proposed framework. Our code implementation is available at https://github.com/ChenyangLi-97/NN-BCD

cs.LG↗

arXiv2024

Unsupervised Industrial Anomaly Detection via Pattern Generative and Contrastive Networks

It is hard to collect enough flaw images for training deep learning network in industrial production. Therefore, existing industrial anomaly detection methods prefer to use CNN-based unsupervised detection and localization network to achieve this task. However, these methods always fail when there are varieties happened in new signals since traditional end-to-end networks suffer barriers of fitting nonlinear model in high-dimensional space. Moreover, they have a memory library by clustering the feature of normal images essentially, which cause it is not robust to texture change. To this end, we propose the Vision Transformer based (VIT-based) unsupervised anomaly detection network. It utilizes a hierarchical task learning and human experience to enhance its interpretability. Our network consists of pattern generation and comparison networks. Pattern generation network uses two VIT-based encoder modules to extract the feature of two consecutive image patches, then uses VIT-based decoder module to learn the human designed style of these features and predict the third image patch. After this, we use the Siamese-based network to compute the similarity of the generation image patch and original image patch. Finally, we refine the anomaly localization by the bi-directional inference strategy. Comparison experiments on public dataset MVTec dataset show our method achieves 99.8% AUC, which surpasses previous state-of-the-art methods. In addition, we give a qualitative illustration on our own leather and cloth datasets. The accurate segment results strongly prove the accuracy of our method in anomaly detection.

cs.CV↗

arXiv2024

Overview of AI-Debater 2023: The Challenges of Argument Generation Tasks

In this paper we present the results of the AI-Debater 2023 Challenge held by the Chinese Conference on Affect Computing (CCAC 2023), and introduce the related datasets. We organize two tracks to handle the argumentative generation tasks in different scenarios, namely, Counter-Argument Generation (Track 1) and Claim-based Argument Generation (Track 2). Each track is equipped with its distinct dataset and baseline model respectively. In total, 32 competing teams register for the challenge, from which we received 11 successful submissions. In this paper, we will present the results of the challenge and a summary of the systems, highlighting commonalities and innovations among participating systems. Datasets and baseline models of the AI-Debater 2023 Challenge have been already released and can be accessed through the official website of the challenge.

cs.CL↗

arXiv2024

Beam shaping by nonlinear moiré metasurfaces

This paper explores the interplay of momentum transfer and nonlinear optical processes through moiré phenomena. Momentum transfer plays a crucial role in the interaction between photons and matter. Here, we study stacked metasurfaces with tailored dispersion and rotated against each other with varying twisted angles. The stacking introduces interlayer interactions, which can be controlled by the relative angle between metasurfaces, significantly enriching the resulting response compared to the single layer counterpart. By focusing on second-harmonic generation (SHG) from these twisted metasurfaces, we delve into the realm of nonlinear moiré photonics. Through experimental observations, we unveil the emergence of intricate far-field SHG radiation patterns, showing their effective tuning by varying the twisted angles. These findings offer a fresh perspective to explore nonlinear wavefront shaping through moiré phenomena, opening new avenues for nonlinear information processing, optical steering, and nonlinear optical switching.

physics.optics↗

arXiv2024

Class-Aware Cartilage Segmentation for Autonomous US-CT Registration in Robotic Intercostal Ultrasound Imaging

Ultrasound imaging has been widely used in clinical examinations owing to the advantages of being portable, real-time, and radiation-free. Considering the potential of extensive deployment of autonomous examination systems in hospitals, robotic US imaging has attracted increased attention. However, due to the inter-patient variations, it is still challenging to have an optimal path for each patient, particularly for thoracic applications with limited acoustic windows, e.g., intercostal liver imaging. To address this problem, a class-aware cartilage bone segmentation network with geometry-constraint post-processing is presented to capture patient-specific rib skeletons. Then, a dense skeleton graph-based non-rigid registration is presented to map the intercostal scanning path from a generic template to individual patients. By explicitly considering the high-acoustic impedance bone structures, the transferred scanning path can be precisely located in the intercostal space, enhancing the visibility of internal organs by reducing the acoustic shadow. To evaluate the proposed approach, the final path mapping performance is validated on five distinct CTs and two volunteer US data, resulting in ten pairs of CT-US combinations. Results demonstrate that the proposed graph-based registration method can robustly and precisely map the path from CT template to individual patients (Euclidean error: $2.21\pm1.11~mm$).

cs.CV↗

arXiv2024

A Transformer variant for multi-step forecasting of water level and hydrometeorological sensitivity analysis based on explainable artificial intelligence technology

Understanding the combined influences of meteorological and hydrological factors on water level and flood events is essential, particularly in today's changing climate environments. Transformer, as one kind of the cutting-edge deep learning methods, offers an effective approach to model intricate nonlinear processes, enables the extraction of key features and water level predictions. EXplainable Artificial Intelligence (XAI) methods play important roles in enhancing the understandings of how different factors impact water level. In this study, we propose a Transformer variant by integrating sparse attention mechanism and introducing nonlinear output layer for the decoder module. The variant model is utilized for multi-step forecasting of water level, by considering meteorological and hydrological factors simultaneously. It is shown that the variant model outperforms traditional Transformer across different lead times with respect to various evaluation metrics. The sensitivity analyses based on XAI technology demonstrate the significant influence of meteorological factors on water level evolution, in which temperature is shown to be the most dominant meteorological factor. Therefore, incorporating both meteorological and hydrological factors is necessary for reliable hydrological prediction and flood prevention. In the meantime, XAI technology provides insights into certain predictions, which is beneficial for understanding the prediction results and evaluating the reasonability.

cs.LG↗

arXiv2024

Forte: A Suite of Advanced Multireference Quantum Chemistry Methods

Forte is an open-source library specialized in multireference electronic structure theories for molecular systems and the rapid prototyping of new methods. This paper gives an overview of the capabilities of Forte, its software architecture, and examples of applications enabled by the methods it implements.

physics.chem-ph↗

arXiv2024

Resource-Efficient Real-Time Polarization Compensation for MDI-QKD with Rejected Data

Measurement-device-independent quantum key distribution (MDI-QKD) closes all the security loopholes in the detection system and is a promising solution for secret key sharing. Polarization encoding is the most common QKD encoding scheme, as it is straightforward to prepare and measure. However, implementing polarization encoding in MDI QKD imposes extra challenges, as polarization alignment must be maintained over both mutually unbiased bases and be maintained for both paths (Alice-Charlie and Bob-Charlie). Polarization alignment is usually done by interrupting the QKD process (reducing overall key generation rates) or using additional classical laser sources multiplexed with quantum channels for polarization alignment. Since low key rates and cost are the two most pressing challenges preventing wide adoption of QKD systems, using additional resources or reducing key rates runs contrary to making QKD commercially viable. Therefore, we propose and implement a novel polarization compensation scheme in the MDI-QKD system that avoids the aforementioned drawbacks by recycling part of discarded detection events. Our scheme evaluates the polarization drift in real-time based on single measurements corresponding to decoy intensities. Our fully automated experimental demonstration maintains the average polarization drift below 0.13 rad over 40 km of spooled fibre (without an insulating jacket) for at least four hours. The average quantum bit error rate is 3.8$\%$, and we achieved an average key rate of $7.45\times 10^{-6}$ bits per pulse.

quant-ph↗

arXiv2024

One Pass Streaming Algorithm for Super Long Token Attention Approximation in Sublinear Space

Attention computation takes both the time complexity of $O(n^2)$ and the space complexity of $O(n^2)$ simultaneously, which makes deploying Large Language Models (LLMs) in streaming applications that involve long contexts requiring substantial computational resources. In recent OpenAI DevDay (Nov 6, 2023), OpenAI released a new model that is able to support a 128K-long document, in our paper, we focus on the memory-efficient issue when context length $n$ is much greater than 128K ($n \gg 2^d$). Considering a single-layer self-attention with Query, Key, and Value matrices $Q, K, V \in \mathbb{R}^{n \times d}$, the polynomial method approximates the attention output $T \in \mathbb{R}^{n \times d}$. It accomplishes this by constructing $U_1, U_2 \in \mathbb{R}^{n \times t}$ to expedite attention ${\sf Attn}(Q, K, V)$ computation within $n^{1+o(1)}$ time executions. Despite this, computing the approximated attention matrix $U_1U_2^\top \in \mathbb{R}^{n \times n}$ still necessitates $O(n^2)$ space, leading to significant memory usage. In response to these challenges, we introduce a new algorithm that only reads one pass of the data in a streaming fashion. This method employs sublinear space $o(n)$ to store three sketch matrices, alleviating the need for exact $K, V$ storage. Notably, our algorithm exhibits exceptional memory-efficient performance with super-long tokens. As the token length $n$ increases, our error guarantee diminishes while the memory usage remains nearly constant. This unique attribute underscores the potential of our technique in efficiently handling LLMs in streaming applications.

cs.LG↗

arXiv2024

WordArt Designer API: User-Driven Artistic Typography Synthesis with Large Language Models on ModelScope

This paper introduces the WordArt Designer API, a novel framework for user-driven artistic typography synthesis utilizing Large Language Models (LLMs) on ModelScope. We address the challenge of simplifying artistic typography for non-professionals by offering a dynamic, adaptive, and computationally efficient alternative to traditional rigid templates. Our approach leverages the power of LLMs to understand and interpret user input, facilitating a more intuitive design process. We demonstrate through various case studies how users can articulate their aesthetic preferences and functional requirements, which the system then translates into unique and creative typographic designs. Our evaluations indicate significant improvements in user satisfaction, design flexibility, and creative expression over existing systems. The WordArt Designer API not only democratizes the art of typography but also opens up new possibilities for personalized digital communication and design.

cs.CV↗

arXiv2023

Tracking with Human-Intent Reasoning

Advances in perception modeling have significantly improved the performance of object tracking. However, the current methods for specifying the target object in the initial frame are either by 1) using a box or mask template, or by 2) providing an explicit language description. These manners are cumbersome and do not allow the tracker to have self-reasoning ability. Therefore, this work proposes a new tracking task -- Instruction Tracking, which involves providing implicit tracking instructions that require the trackers to perform tracking automatically in video frames. To achieve this, we investigate the integration of knowledge and reasoning capabilities from a Large Vision-Language Model (LVLM) for object tracking. Specifically, we propose a tracker called TrackGPT, which is capable of performing complex reasoning-based tracking. TrackGPT first uses LVLM to understand tracking instructions and condense the cues of what target to track into referring embeddings. The perception component then generates the tracking results based on the embeddings. To evaluate the performance of TrackGPT, we construct an instruction tracking benchmark called InsTrack, which contains over one thousand instruction-video pairs for instruction tuning and evaluation. Experiments show that TrackGPT achieves competitive performance on referring video object segmentation benchmarks, such as getting a new state-of the-art performance of 66.5 $\mathcal{J}\&\mathcal{F}$ on Refer-DAVIS. It also demonstrates a superior performance of instruction tracking under new evaluation protocols. The code and models are available at \href{https://github.com/jiawen-zhu/TrackGPT}{https://github.com/jiawen-zhu/TrackGPT}.

cs.CV↗

arXiv2023

Frozen natural orbitals for the state-averaged driven similarity renormalization group

We present a reduced-cost implementation of the state-averaged driven similarity renormalization group (SA-DSRG) based on the frozen natural orbital (FNO) approach. The natural orbitals (NOs) are obtained by diagonalizing the one-body reduced density matrix from SA-DSRG second-order perturbation theory (SA-DSRG-PT2). Subsequently, the virtual NOs with occupation numbers (ONs) smaller than a user-defined threshold are excluded from the high-level electron correlation treatment beyond SA-DSRG-PT2. An additive second-order correction is applied to the SA-DSRG Hamiltonian to reintroduce the correlation effect from the discarded orbitals. The FNO SA-DSRG method is benchmarked on 35 small organic molecules in the QUEST database. When keeping 98-99% of the cumulative ONs, the mean absolute error in the vertical transition energies due to FNO is less than 0.01 eV. Using the same FNO threshold, we observe a speedup of 9 times the conventional SA-DSRG implementation for nickel carbonyl with a quadruple-$ζ$ basis set. The FNO approach enables third-order SA-DSRG perturbation theory computations on chloroiron corrole [FeCl(C$_{19}$H$_{11}$N$_4$)] with more than 1000 basis functions.

physics.chem-ph↗

arXiv2023

WordArt Designer: User-Driven Artistic Typography Synthesis using Large Language Models

This paper introduces WordArt Designer, a user-driven framework for artistic typography synthesis, relying on the Large Language Model (LLM). The system incorporates four key modules: the LLM Engine, SemTypo, StyTypo, and TexTypo modules. 1) The LLM Engine, empowered by the LLM (e.g., GPT-3.5), interprets user inputs and generates actionable prompts for the other modules, thereby transforming abstract concepts into tangible designs. 2) The SemTypo module optimizes font designs using semantic concepts, striking a balance between artistic transformation and readability. 3) Building on the semantic layout provided by the SemTypo module, the StyTypo module creates smooth, refined images. 4) The TexTypo module further enhances the design's aesthetics through texture rendering, enabling the generation of inventive textured fonts. Notably, WordArt Designer highlights the fusion of generative AI with artistic typography. Experience its capabilities on ModelScope: https://www.modelscope.cn/studios/WordArt/WordArt.

cs.CL↗