arXiv subjects

Tao Yu

Publications and source records attributed to Tao Yu.

At least 163 records · Page 9Linked to original sources

arXiv2024

Persistent nodal magnon-photon polariton in ferromagnetic heterostructures

Exceptional points with coalescence of eigenvalues and eigenvectors are spectral singularities in the parameter space, achieving which often needs fine-tuning of parameters in quantum systems. We predict a \textit{persistent} realization of nodal magnon-photon polariton, i.e., a polariton of long wavelength without any gap splitting in a thin ferromagnetic insulator film sandwiched by two normal metals, which persistently exists when the ferromagnet is sufficiently thick $\sim 100$~nm due to the joint effect of dissipation and dissipative coupling. We perform the model calculation \textit{beyond the perturbation theory} using a classical approach, develop a quantum scheme able to account for the Ohmic dissipation, and find ultrastrong coupling with coupling strength comparable to the bare magnon frequency. Via revealing a simple conversion relation we extend this formalism to superconductors and predict the gap opened by the ultrastrong coupling strongly depends on the direction of polariton propagation. Our findings may help search for robust non-Hermitian topological phases in magnonic and spintronic devices.

cond-mat.mes-hall↗

arXiv2024

Spin Radiation of Electrons, Excitons, and Phonons

In the celebrated Stern-Gerlach experiment an inhomogeneous static magnetic field separates a beam of charge-neutral atoms with opposite spins, thereby driving a ``spin current" normal to the propagation direction. Here we generalize it to the dynamic scenario by demonstrating a spin transfer between an AC inhomogeneous magnetic field and intraband electrons or charge-neutral excitons and phonons. We predict that parametric pumping can efficiently radiate their DC spin currents from local AC magnetic sources with van der Waals semiconductors as prototypes. This mechanism brings a unified and efficient paradigm in the spin transport of distinct mobile carriers.

cond-mat.mes-hall↗

arXiv2024

Augmented Intelligence in Smart Intersections: Local Digital Twins-Assisted Hybrid Autonomous Driving

Vehicle-road collaboration is a promising approach for enhancing the safety and efficiency of autonomous driving by extending the intelligence of onboard systems to smart roadside infrastructures. The introduction of digital twins (DTs), particularly local DTs (LDTs) at the edge, in smart mobility presents a new embodiment of augmented intelligence, which could enhance information exchange and extract human driving expertise to improve onboard intelligence. This paper presents a novel LDT-assisted hybrid autonomous driving system for improving safety and efficiency in traffic intersections. By leveraging roadside units (RSUs) equipped with sensory and computing capabilities, the proposed system continuously monitors traffic, extracts human driving knowledge, and generates intersection-specific local driving agents through an offline reinforcement learning (RL) framework. When connected and automated vehicles (CAVs) pass through RSU-equipped intersections, RSUs can provide local agents to support safe and efficient driving in local areas. Meanwhile, they provide real-time cooperative perception (CP) to broaden onboard sensory horizons. The proposed LDT-assisted hybrid system is implemented with state-of-the-art products, e.g., CAVs and RSUs, and technologies, e.g., millimeter-wave (mmWave) communications. Hardware-in-the-loop (HiL) simulations and proof-of-concept (PoC) tests validate system performance from two standpoints: (i) The peak latency for CP and local agent downloading are 8.51 ms and 146 ms, respectively, aligning with 3GPP requirements for vehicle-to-everything (V2X) and model transfer use cases. Moreover, (ii) local driving agents can improve safety measures by 10% and reduce travel time by 15% compared with conventional onboard systems. The implemented prototype also demonstrates reliable real-time performance, fulfilling the targets of the proposed system design.

eess.SY↗

arXiv2024

FOLIO: Natural Language Reasoning with First-Order Logic

Large language models (LLMs) have achieved remarkable performance on a variety of natural language understanding tasks. However, existing benchmarks are inadequate in measuring the complex logical reasoning capabilities of a model. We present FOLIO, a human-annotated, logically complex and diverse dataset for reasoning in natural language (NL), equipped with first-order logic (FOL) annotations. FOLIO consists of 1,430 examples (unique conclusions), each paired with one of 487 sets of premises used to deductively reason for the validity of each conclusion. The logical correctness of the premises and conclusions is ensured by their FOL annotations, which are automatically verified by an FOL inference engine. In addition to the main NL reasoning task, NL-FOL pairs in FOLIO constitute a new NL-FOL translation dataset. Our experiments on FOLIO systematically evaluate the FOL reasoning ability of supervised fine-tuning on medium-sized language models. For both NL reasoning and NL-FOL translation, we benchmark multiple state-of-the-art language models. Our results show that a subset of FOLIO presents a challenge for one of the most capable {Large Language Model (LLM)} publicly available, GPT-4.

cs.CL↗

arXiv2024

Non-Overlapping Placement of Macro Cells based on Reinforcement Learning in Chip Design

Due to the increasing complexity of chip design, existing placement methods still have many shortcomings in dealing with macro cells coverage and optimization efficiency. Aiming at the problems of layout overlap, inferior performance, and low optimization efficiency in existing chip design methods, this paper proposes an end-to-end placement method, SRLPlacer, based on reinforcement learning. First, the placement problem is transformed into a Markov decision process by establishing the coupling relationship graph model between macro cells to learn the strategy for optimizing layouts. Secondly, the whole placement process is optimized after integrating the standard cell layout. By assessing on the public benchmark ISPD2005, the proposed SRLPlacer can effectively solve the overlap problem between macro cells while considering routing congestion and shortening the total wire length to ensure routability. Codes are available at https://github.com/zhouyusd/SRLPlacer.

cs.AR↗

arXiv2024

PNR: Physics-informed Neural Representation for high-resolution LFM reconstruction

Light field microscopy (LFM) has been widely utilized in various fields for its capability to efficiently capture high-resolution 3D scenes. Despite the rapid advancements in neural representations, there are few methods specifically tailored for microscopic scenes. Existing approaches often do not adequately address issues such as the loss of high-frequency information due to defocus and sample aberration, resulting in suboptimal performance. In addition, existing methods, including RLD, INR, and supervised U-Net, face challenges such as sensitivity to initial estimates, reliance on extensive labeled data, and low computational efficiency, all of which significantly diminish the practicality in complex biological scenarios. This paper introduces PNR (Physics-informed Neural Representation), a method for high-resolution LFM reconstruction that significantly enhances performance. Our method incorporates an unsupervised and explicit feature representation approach, resulting in a 6.1 dB improvement in PSNR than RLD. Additionally, our method employs a frequency-based training loss, enabling better recovery of high-frequency details, which leads to a reduction in LPIPS by at least half compared to SOTA methods (1.762 V.S. 3.646 of DINER). Moreover, PNR integrates a physics-informed aberration correction strategy that optimizes Zernike polynomial parameters during optimization, thereby reducing the information loss caused by aberrations and improving spatial resolution. These advancements make PNR a promising solution for long-term high-resolution biological imaging applications. Our code and dataset will be made publicly available.

eess.IV↗

arXiv2024

CSWin-UNet: Transformer UNet with Cross-Shaped Windows for Medical Image Segmentation

Deep learning, especially convolutional neural networks (CNNs) and Transformer architectures, have become the focus of extensive research in medical image segmentation, achieving impressive results. However, CNNs come with inductive biases that limit their effectiveness in more complex, varied segmentation scenarios. Conversely, while Transformer-based methods excel at capturing global and long-range semantic details, they suffer from high computational demands. In this study, we propose CSWin-UNet, a novel U-shaped segmentation method that incorporates the CSWin self-attention mechanism into the UNet to facilitate horizontal and vertical stripes self-attention. This method significantly enhances both computational efficiency and receptive field interactions. Additionally, our innovative decoder utilizes a content-aware reassembly operator that strategically reassembles features, guided by predicted kernels, for precise image resolution restoration. Our extensive empirical evaluations on diverse datasets, including synapse multi-organ CT, cardiac MRI, and skin lesions, demonstrate that CSWin-UNet maintains low model complexity while delivering high segmentation accuracy. Codes are available at https://github.com/eatbeanss/CSWin-UNet.

eess.IV↗

arXiv2024

Roadside Units Assisted Localized Automated Vehicle Maneuvering: An Offline Reinforcement Learning Approach

Traffic intersections present significant challenges for the safe and efficient maneuvering of connected and automated vehicles (CAVs). This research proposes an innovative roadside unit (RSU)-assisted cooperative maneuvering system aimed at enhancing road safety and traveling efficiency at intersections for CAVs. We utilize RSUs for real-time traffic data acquisition and train an offline reinforcement learning (RL) algorithm based on human driving data. Evaluation results obtained from hardware-in-loop autonomous driving simulations show that our approach employing the twin delayed deep deterministic policy gradient and behavior cloning (TD3+BC), achieves performance comparable to state-of-the-art autonomous driving systems in terms of safety measures while significantly enhancing travel efficiency by up to 17.38% in intersection areas. This paper makes a pivotal contribution to the field of intelligent transportation systems, presenting a breakthrough solution for improving urban traffic flow and safety at intersections.

eess.SY↗

arXiv2024

Lemur: Harmonizing Natural Language and Code for Language Agents

We introduce Lemur and Lemur-Chat, openly accessible language models optimized for both natural language and coding capabilities to serve as the backbone of versatile language agents. The evolution from language chat models to functional language agents demands that models not only master human interaction, reasoning, and planning but also ensure grounding in the relevant environments. This calls for a harmonious blend of language and coding capabilities in the models. Lemur and Lemur-Chat are proposed to address this necessity, demonstrating balanced proficiencies in both domains, unlike existing open-source models that tend to specialize in either. Through meticulous pre-training using a code-intensive corpus and instruction fine-tuning on text and code data, our models achieve state-of-the-art averaged performance across diverse text and coding benchmarks among open-source models. Comprehensive experiments demonstrate Lemur's superiority over existing open-source models and its proficiency across various agent tasks involving human communication, tool usage, and interaction under fully- and partially- observable environments. The harmonization between natural and programming languages enables Lemur-Chat to significantly narrow the gap with proprietary models on agent abilities, providing key insights into developing advanced open-source agents adept at reasoning, planning, and operating seamlessly across environments. https://github.com/OpenLemur/Lemur

cs.CL↗

arXiv2024

Digital Twin-Empowered Routing Management for Reliable Multi-Hop Millimeter Wave V2X

Digital twin (DT) technology can replicate physical entities in cyberspace. A mobility DT digitalizes connected and autonomous vehicles (CAVs) and their surrounding traffic environment, allowing to monitor the maneuvering and distribution of CAVs in real-time, which is crucial for managing vehicle-to-everything (V2X) connectivity, especially when millimeter wave (mmWave) is adopted. MmWave V2X relies on dynamic multi-hop communications to ensure high reliability. Therefore, in this paper, the challenges of mmWave V2X are presented to motivate the utilization of DT, and then we introduce the system model for DT-based multi-hop routing management, incorporating two different routing algorithms: with and without future trajectory prediction. For proof of concept, we implement the proposed DT system using Unity-based AWSIM and evaluate the proposed algorithms via simulations. The results show that, compared to the conventional routing algorithm in vehicular ad hoc networks (VANETs), the DT-based algorithms significantly improve the reliability of mmWave V2X, and such improvements can be seen in both fully connected and mixed traffic scenarios.

cs.NI↗

arXiv2024

Spin-orbit locking of magnons with localized microwave fields

We address the photonic spin-orbit coupling known from nano-optics and plasmonics in the microwave regime. The spin $\mathbf{S}$ and momentum $\mathbf{q}$ of microwaves emitted by an excited magnetic particle are locked by $\mathbf{q}\cdot\mathbf{S}=0$ with a fixed chirality $\hat{\mathbf{n}}\cdot(\hat{\bf S}\times\hat{\bf q})=1$ when evanescent along $\hat{\mathbf{n}}\perp {\bf q}$. This field excites magnons in a nearby magnetic film in the form of directional beams that rotate with the magnetization direction. The exchange of these magnons between two distant nanomagnets leads to a highly tunable strong coupling and entangles their excited states.

cond-mat.mes-hall↗

arXiv2024

Shape-restricted transfer learning analysis for generalized linear regression model

Transfer learning has emerged as a highly sought-after and actively pursued research area within the statistical community. The core concept of transfer learning involves leveraging insights and information from auxiliary datasets to enhance the analysis of the primary dataset of interest. In this paper, our focus is on datasets originating from distinct yet interconnected distributions. We assume that the training data conforms to a standard generalized linear model, while the testing data exhibit a connection to the training data based on a prior probability shift assumption. Ultimately, we discover that the two-sample conditional means are interrelated through an unknown, nondecreasing function. We integrate the power of generalized estimating equations with the shape-restricted score function, creating a robust framework for improved inference regarding the underlying parameters. We theoretically establish the asymptotic properties of our estimator and demonstrate, through simulation studies, that our method yields more accurate parameter estimates compared to those based solely on the testing or training data. Finally, we apply our method to a real-world example.

stat.ME↗

arXiv2024

YOLO-TLA: An Efficient and Lightweight Small Object Detection Model based on YOLOv5

Object detection, a crucial aspect of computer vision, has seen significant advancements in accuracy and robustness. Despite these advancements, practical applications still face notable challenges, primarily the inaccurate detection or missed detection of small objects. In this paper, we propose YOLO-TLA, an advanced object detection model building on YOLOv5. We first introduce an additional detection layer for small objects in the neck network pyramid architecture, thereby producing a feature map of a larger scale to discern finer features of small objects. Further, we integrate the C3CrossCovn module into the backbone network. This module uses sliding window feature extraction, which effectively minimizes both computational demand and the number of parameters, rendering the model more compact. Additionally, we have incorporated a global attention mechanism into the backbone network. This mechanism combines the channel information with global information to create a weighted feature map. This feature map is tailored to highlight the attributes of the object of interest, while effectively ignoring irrelevant details. In comparison to the baseline YOLOv5s model, our newly developed YOLO-TLA model has shown considerable improvements on the MS COCO validation dataset, with increases of 4.6% in mAP@0.5 and 4% in mAP@0.5:0.95, all while keeping the model size compact at 9.49M parameters. Further extending these improvements to the YOLOv5m model, the enhanced version exhibited a 1.7% and 1.9% increase in mAP@0.5 and mAP@0.5:0.95, respectively, with a total of 27.53M parameters. These results validate the YOLO-TLA model's efficient and effective performance in small object detection, achieving high accuracy with fewer parameters and computational demands.

cs.CV↗

arXiv2024

Automated Design and Optimization of Distributed Filtering Circuits via Reinforcement Learning

Designing distributed filter circuits (DFCs) is complex and time-consuming, involving setting and optimizing multiple hyperparameters. Traditional optimization methods, such as using the commercial finite element solver HFSS (High-Frequency Structure Simulator) to enumerate all parameter combinations with fixed steps and then simulate each combination, are not only time-consuming and labor-intensive but also rely heavily on the expertise and experience of electronics engineers, making it difficult to adapt to rapidly changing design requirements. Additionally, these commercial tools struggle with precise adjustments when parameters are sensitive to numerical changes, resulting in limited optimization effectiveness. This study proposes a novel end-to-end automated method for DFC design. The proposed method harnesses reinforcement learning (RL) algorithms, eliminating the dependence on the design experience of engineers. Thus, it significantly reduces the subjectivity and constraints associated with circuit design. The experimental findings demonstrate clear improvements in design efficiency and quality when comparing the proposed method with traditional engineer-driven methods. Furthermore, the proposed method achieves superior performance when designing complex or rapidly evolving DFCs, highlighting the substantial potential of RL in circuit design automation. In particular, compared to the existing DFC automation design method CircuitGNN, our method achieves an average performance improvement of 8.72%. Additionally, the execution efficiency of our method is 2000 times higher than CircuitGNN on the CPU and 241 times higher on the GPU.

cs.LG↗

arXiv2024

DisControlFace: Adding Disentangled Control to Diffusion Autoencoder for One-shot Explicit Facial Image Editing

In this work, we focus on exploring explicit fine-grained control of generative facial image editing, all while generating faithful facial appearances and consistent semantic details, which however, is quite challenging and has not been extensively explored, especially under an one-shot scenario. We identify the key challenge as the exploration of disentangled conditional control between high-level semantics and explicit parameters (e.g., 3DMM) in the generation process, and accordingly propose a novel diffusion-based editing framework, named DisControlFace. Specifically, we leverage a Diffusion Autoencoder (Diff-AE) as the semantic reconstruction backbone. To enable explicit face editing, we construct an Exp-FaceNet that is compatible with Diff-AE to generate spatial-wise explicit control conditions based on estimated 3DMM parameters. Different from current diffusion-based editing methods that train the whole conditional generative model from scratch, we freeze the pre-trained weights of the Diff-AE to maintain its semantically deterministic conditioning capability and accordingly propose a random semantic masking (RSM) strategy to effectively achieve an independent training of Exp-FaceNet. This setting endows the model with disentangled face control meanwhile reducing semantic information shift in editing. Our model can be trained using 2D in-the-wild portrait images without requiring 3D or video data and perform robust editing on any new facial image through a simple one-shot fine-tuning. Comprehensive experiments demonstrate that DisControlFace can generate realistic facial images with better editing accuracy and identity preservation over state-of-the-art methods. Project page: https://discontrolface.github.io/

cs.CV↗

arXiv2024

Rethinking Domain Adaptation and Generalization in the Era of CLIP

In recent studies on domain adaptation, significant emphasis has been placed on the advancement of learning shared knowledge from a source domain to a target domain. Recently, the large vision-language pre-trained model, i.e., CLIP has shown strong ability on zero-shot recognition, and parameter efficient tuning can further improve its performance on specific tasks. This work demonstrates that a simple domain prior boosts CLIP's zero-shot recognition in a specific domain. Besides, CLIP's adaptation relies less on source domain data due to its diverse pre-training dataset. Furthermore, we create a benchmark for zero-shot adaptation and pseudo-labeling based self-training with CLIP. Last but not least, we propose to improve the task generalization ability of CLIP from multiple unlabeled domains, which is a more practical and unique scenario. We believe our findings motivate a rethinking of domain adaptation benchmarks and the associated role of related algorithms in the era of CLIP.

cs.CV↗

arXiv2024

Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?

Data science and engineering workflows often span multiple stages, from warehousing to orchestration, using tools like BigQuery, dbt, and Airbyte. As vision language models (VLMs) advance in multimodal understanding and code generation, VLM-based agents could potentially automate these workflows by generating SQL queries, Python code, and GUI operations. This automation can improve the productivity of experts while democratizing access to large-scale data analysis. In this paper, we introduce Spider2-V, the first multimodal agent benchmark focusing on professional data science and engineering workflows, featuring 494 real-world tasks in authentic computer environments and incorporating 20 enterprise-level professional applications. These tasks, derived from real-world use cases, evaluate the ability of a multimodal agent to perform data-related tasks by writing code and managing the GUI in enterprise data software systems. To balance realistic simulation with evaluation simplicity, we devote significant effort to developing automatic configurations for task setup and carefully crafting evaluation metrics for each task. Furthermore, we supplement multimodal agents with comprehensive documents of these enterprise data software systems. Our empirical evaluation reveals that existing state-of-the-art LLM/VLM-based agents do not reliably automate full data workflows (14.0% success). Even with step-by-step guidance, these agents still underperform in tasks that require fine-grained, knowledge-intensive GUI actions (16.2%) and involve remote cloud-hosted workspaces (10.6%). We hope that Spider2-V paves the way for autonomous multimodal agents to transform the automation of data science and engineering workflow. Our code and data are available at https://spider2-v.github.io.

cs.AI↗

arXiv2024

KnobCF: Uncertainty-aware Knob Tuning

The knob tuning aims to optimize database performance by searching for the most effective knob configuration under a certain workload. Existing works suffer two significant problems. On the one hand, there exist multiple similar even useless evaluations of knob tuning even with the diverse searching methods because of the different sensitivities of knobs on a certain workload. On the other hand, the single evaluation of knob configurations may bring overestimation or underestimation because of the query uncertainty performance. To solve the above problems, we propose a decoupled query uncertainty-aware knob classifier, called KnobCF, to enhance the knob tuning. Our method has three significant contributions: (1) We propose a novel concept of the uncertainty-aware knob configuration estimation to enhance the knob tuning process. (2) We provide an effective few-shot uncertainty knob estimator without extra time consumption in training data collection, which has a high time efficiency in practical tuning tasks. (3) Our method provides a general framework that could be easily deployed in any knob tuning task because we make no changes to the knob tuners and the database management system. Our experiments on four open-source benchmarks demonstrate that our method effectively reduces useless evaluations and improves the tuning results. Especially in TPCC, our method achieves competitive tuning results with only 60% to 70% time consumption compared to the full workload evaluations.

cs.DB↗