Searcharxiv⌕ Search

arXiv subjects

Feng Wang

Publications and source records attributed to Feng Wang.

At least 163 records · Page 9Linked to original sources
arXiv2025

Performance of Superconducting Resonators Suspended on SiN Membranes

Suspending devices on thin SiN membranes can limit their interaction with the bulk substrate and reduce parasitic capacitance to ground. While suspending devices on membranes is used in many fields including radiation detection using superconducting circuits, there has been less investigation into maximum membrane aspect ratios and achievable suspended device quality, metrics important to establish the applicable scope of the technique. Here, we investigate these metrics by fabricating superconducting coplanar waveguide resonators entirely atop thin ($\sim$110 nm) SiN membranes, where the membrane's shortest length to thickness yields an aspect ratio of approximately $7.4 \times 10^3$. We compare these membrane resonators to on-substrate resonators on the same chip, finding similar internal quality factors $\sim$$10^5$ at single photon levels. Furthermore, we confirm that these membranes do not adversely affect resonator thermalization and conduct further materials characterization. By achieving high quality superconducting circuit devices fully suspended on thin SiN membranes, our results help expand the technique's scope to potential uses including incorporating higher aspect ratio membranes for device suspension and creating larger footprint, high impedance, and high quality devices.

quant-ph↗
arXiv2025

A parallel domain decomposition method for solving elliptic equations on manifolds

We propose a new numerical domain decomposition method for solving elliptic equations on compact Riemannian manifolds. One advantage of this method is its ability to bypass the need for global triangulations or grids on the manifolds. Additionally, it features a highly parallel iterative scheme. To verify its efficacy, we conduct numerical experiments on some $4$-dimensional manifolds without and with boundary.

math.NA↗
arXiv2024

Single-image reflection removal via self-supervised diffusion models

Reflections often degrade the visual quality of images captured through transparent surfaces, and reflection removal methods suffers from the shortage of paired real-world samples.This paper proposes a hybrid approach that combines cycle-consistency with denoising diffusion probabilistic models (DDPM) to effectively remove reflections from single images without requiring paired training data. The method introduces a Reflective Removal Network (RRN) that leverages DDPMs to model the decomposition process and recover the transmission image, and a Reflective Synthesis Network (RSN) that re-synthesizes the input image using the separated components through a nonlinear attention-based mechanism. Experimental results demonstrate the effectiveness of the proposed method on the SIR$^2$, Flash-Based Reflection Removal (FRR) Dataset, and a newly introduced Museum Reflection Removal (MRR) dataset, showing superior performance compared to state-of-the-art methods.

cs.CV↗
arXiv2024

The rigidity of eigenvalues on Kähler manifolds with positive Ricci lower bound

In this work, optimal rigidity results for eigenvalues on Kähler manifolds with positive Ricci lower bound are established. More precisely, for those Kähler manifolds whose first eigenvalue agrees with the Ricci lower bound, we show that the complex projective space is the only one with the largest multiplicity of the first eigenvalue. Moreover, there is a specific gap between the largest and the second largest multiplicity. In the Kähler--Einstein case, almost rigidity results for eigenvalues are also obtained.

math.DG↗
arXiv2024

HEP-NAS: Towards Efficient Few-shot Neural Architecture Search via Hierarchical Edge Partitioning

One-shot methods have significantly advanced the field of neural architecture search (NAS) by adopting weight-sharing strategy to reduce search costs. However, the accuracy of performance estimation can be compromised by co-adaptation. Few-shot methods divide the entire supernet into individual sub-supernets by splitting edge by edge to alleviate this issue, yet neglect relationships among edges and result in performance degradation on huge search space. In this paper, we introduce HEP-NAS, a hierarchy-wise partition algorithm designed to further enhance accuracy. To begin with, HEP-NAS treats edges sharing the same end node as a hierarchy, permuting and splitting edges within the same hierarchy to directly search for the optimal operation combination for each intermediate node. This approach aligns more closely with the ultimate goal of NAS. Furthermore, HEP-NAS selects the most promising sub-supernet after each segmentation, progressively narrowing the search space in which the optimal architecture may exist. To improve performance evaluation of sub-supernets, HEP-NAS employs search space mutual distillation, stabilizing the training process and accelerating the convergence of each individual sub-supernet. Within a given budget, HEP-NAS enables the splitting of all edges and gradually searches for architectures with higher accuracy. Experimental results across various datasets and search spaces demonstrate the superiority of HEP-NAS compared to state-of-the-art methods.

cs.LG↗
arXiv2024

Towards Flexible 3D Perception: Object-Centric Occupancy Completion Augments 3D Object Detection

While 3D object bounding box (bbox) representation has been widely used in autonomous driving perception, it lacks the ability to capture the precise details of an object's intrinsic geometry. Recently, occupancy has emerged as a promising alternative for 3D scene perception. However, constructing a high-resolution occupancy map remains infeasible for large scenes due to computational constraints. Recognizing that foreground objects only occupy a small portion of the scene, we introduce object-centric occupancy as a supplement to object bboxes. This representation not only provides intricate details for detected objects but also enables higher voxel resolution in practical applications. We advance the development of object-centric occupancy perception from both data and algorithm perspectives. On the data side, we construct the first object-centric occupancy dataset from scratch using an automated pipeline. From the algorithmic standpoint, we introduce a novel object-centric occupancy completion network equipped with an implicit shape decoder that manages dynamic-size occupancy generation. This network accurately predicts the complete object-centric occupancy volume for inaccurate object proposals by leveraging temporal information from long sequences. Our method demonstrates robust performance in completing object shapes under noisy detection and tracking conditions. Additionally, we show that our occupancy features significantly enhance the detection results of state-of-the-art 3D object detectors, especially for incomplete or distant objects in the Waymo Open Dataset.

cs.CV↗
arXiv2024

Joint Mode Selection and Beamforming Designs for Hybrid-RIS Assisted ISAC Systems

This paper considers a hybrid reconfigurable intelligent surface (RIS) assisted integrated sensing and communication (ISAC) system, where each RIS element can flexibly switch between the active and passive modes. Subject to the signal-to-interference-plus-noise ratio (SINR) constraint for each communication user (CU) and the transmit power constraints for both the base station (BS) and the active RIS elements, with the objective of maximizing the minimum beampattern gain among multiple targets, we jointly optimize the BS transmit beamforming for ISAC and the mode selection of each RIS reflecting element, as well as the RIS reflection coefficient matrix. Such formulated joint hybrid-RIS assisted ISAC design problem is a mixed-integer nonlinear program, which is decomposed into two low-dimensional subproblems being solved in an alternating manner. Specifically, by using the semidefinite relaxation (SDR) technique along with the rank-one beamforming construction process, we efficiently obtain the optimal ISAC transmit beamforming design at the BS. Via the SDR and successive convex approximation (SCA) techniques, we jointly determine the active/passive mode selection and reflection coefficient for each RIS element. Numerical results demonstrate that the proposed design solution is significantly superior to the existing baseline solutions.

cs.IT↗
arXiv2024

Non-Terrestrial Networking for 6G: Evolution, Opportunities, and Future Directions

From 5G onwards, Non-Terrestrial Networks (NTNs) have emerged as a key component of future network architectures. Leveraging Low Earth Orbit (LEO) satellite constellations, NTNs are capable of building a space Internet and present a paradigm shift in delivering mobile services to even the most remote regions on Earth. However, the extensive coverage and rapid movement of LEO satellites pose unique challenges for NTN networking, including user equipment (UE) access and inter-satellite delivery, which directly impact the quality of service (QoS) and data transmission continuity. This paper offers an in-depth review of advanced NTN management technologies in the context of 6G evolution, focusing on radio resource management, mobility management, and dynamic network slicing. Building on this foundation and considering the latest trends in NTN development, we then present some innovative perspectives to emerging challenges in satellite beamforming, handover mechanisms, and inter-satellite transmissions. Lastly, we identify open research issues and propose future directions aimed at advancing satellite Internet deployment and enhancing NTN performance.

cs.NI↗
arXiv2024

DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization

Device Model Generalization (DMG) is a practical yet under-investigated research topic for on-device machine learning applications. It aims to improve the generalization ability of pre-trained models when deployed on resource-constrained devices, such as improving the performance of pre-trained cloud models on smart mobiles. While quite a lot of works have investigated the data distribution shift across clouds and devices, most of them focus on model fine-tuning on personalized data for individual devices to facilitate DMG. Despite their promising, these approaches require on-device re-training, which is practically infeasible due to the overfitting problem and high time delay when performing gradient calculation on real-time data. In this paper, we argue that the computational cost brought by fine-tuning can be rather unnecessary. We consequently present a novel perspective to improving DMG without increasing computational cost, i.e., device-specific parameter generation which directly maps data distribution to parameters. Specifically, we propose an efficient Device-cloUd collaborative parametErs generaTion framework DUET. DUET is deployed on a powerful cloud server that only requires the low cost of forwarding propagation and low time delay of data transmission between the device and the cloud. By doing so, DUET can rehearse the device-specific model weight realizations conditioned on the personalized real-time data for an individual device. Importantly, our DUET elegantly connects the cloud and device as a 'duet' collaboration, frees the DMG from fine-tuning, and enables a faster and more accurate DMG paradigm. We conduct an extensive experimental study of DUET on three public datasets, and the experimental results confirm our framework's effectiveness and generalisability for different DMG tasks.

cs.DC↗
arXiv2024

CovidLLM: A Robust Large Language Model with Missing Value Adaptation and Multi-Objective Learning Strategy for Predicting Disease Severity and Clinical Outcomes in COVID-19 Patients

Coronavirus Disease 2019 (COVID-19), which emerged in 2019, has caused millions of deaths worldwide. Although effective vaccines have been developed to mitigate severe symptoms, certain populations, particularly the elderly and those with comorbidities, remain at high risk for severe outcomes and increased mortality. Consequently, early identification of the severity and clinical outcomes of the disease in these patients is vital to prevent adverse prognoses. Although traditional machine learning and deep learning models have been widely employed in this area, the potential of large language models (LLMs) remains largely unexplored. Our research focuses primarily on constructing specialized prompts and adopting multi-objective learning strategies. We started by selecting serological indicators that significantly correlate with clinical outcomes and disease severity to serve as input data for the model. Blood test samples often contain numerous missing values, and traditional models generally rely on imputation to handle these gaps in the data. In contrast, LLMs offer the advantage of robust semantic understanding. By setting prompts, we can explicitly inform the model when a feature's value is missing, without the need for imputation. For the multi-objective learning strategy, the model is designed to first predict disease severity and then predict clinical outcomes. Given that LLMs utilize both the input text and the generated tokens as input for generating the next token, the predicted severity is used as a basis for generating the clinical outcome. During the fine-tuning of the LLM, the two objectives influence and improve each other. Our experiments were implemented based on the ChatGLM model. The results demonstrate the effectiveness of LLMs in this task, suggesting promising potential for further development.

cs.CL↗
arXiv2024

M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation

There exists recent work in computer vision, named VAR, that proposes a new autoregressive paradigm for image generation. Diverging from the vanilla next-token prediction, VAR structurally reformulates the image generation into a coarse to fine next-scale prediction. In this paper, we show that this scale-wise autoregressive framework can be effectively decoupled into \textit{intra-scale modeling}, which captures local spatial dependencies within each scale, and \textit{inter-scale modeling}, which models cross-scale relationships progressively from coarse-to-fine scales. This decoupling structure allows to rebuild VAR in a more computationally efficient manner. Specifically, for intra-scale modeling -- crucial for generating high-fidelity images -- we retain the original bidirectional self-attention design to ensure comprehensive modeling; for inter-scale modeling, which semantically connects different scales but is computationally intensive, we apply linear-complexity mechanisms like Mamba to substantially reduce computational overhead. We term this new framework M-VAR. Extensive experiments demonstrate that our method outperforms existing models in both image quality and generation speed. For example, our 1.5B model, with fewer parameters and faster inference speed, outperforms the largest VAR-d30-2B. Moreover, our largest model M-VAR-d32 impressively registers 1.78 FID on ImageNet 256$\times$256 and outperforms the prior-art autoregressive models LlamaGen/VAR by 0.4/0.19 and popular diffusion models LDM/DiT by 1.82/0.49, respectively. Code is avaiable at \url{https://github.com/OliverRensu/MVAR}.

cs.CV↗
arXiv2024

An Overview on IRS-Enabled Sensing and Communications for 6G: Architectures, Fundamental Limits, and Joint Beamforming Designs

This paper presents an overview on intelligent reflecting surface (IRS)-enabled sensing and communication for the forthcoming sixth-generation (6G) wireless networks, in which IRSs are strategically deployed to proactively reconfigure wireless environments to improve both sensing and communication (S&C) performance. First, we exploit a single IRS to enable wireless sensing in the base station's (BS's) non-line-of-sight (NLoS) area. In particular, we present three IRS-enabled NLoS target sensing architectures with fully-passive, semi-passive, and active IRSs, respectively. We compare their pros and cons by analyzing the fundamental sensing performance limits for target detection and parameter estimation. Next, we consider a single IRS to facilitate integrated sensing and communication (ISAC), in which the transmit signals at the BS are used for achieving both S&C functionalities, aided by the IRS through reflective beamforming. We present joint transmit signal and receiver processing designs for realizing efficient ISAC, and jointly optimize the transmit beamforming at the BS and reflective beamforming at the IRS to balance the fundamental performance tradeoff between S&C. Furthermore, we discuss multi-IRS networked ISAC, by particularly focusing on multi-IRS-enabled multi-link ISAC, multi-region ISAC, and ISAC signal routing, respectively. Finally, we highlight various promising research topics in this area to motivate future work.

eess.SP↗
arXiv2024

Wireless Edge Content Broadcast via Integrated Terrestrial and Non-terrestrial Networks

Non-terrestrial networks (NTN) have emerged as a transformative solution to bridge the digital divide and deliver essential services to remote and underserved areas. In this context, low Earth orbit (LEO) satellite constellations offer remarkable potential for efficient cache content broadcast in remote regions, thereby extending the reach of digital services. In this paper, we introduce a novel approach to optimize wireless edge content placement using NTN. Despite wide coverage, the varying NTN transmission capabilities must be carefully aligned with each content placement to maximize broadcast efficiency. In this paper, we introduce a novel approach to optimize wireless edge content placement using NTN, positioning NTN as a complement to TN for achieving optimal content broadcasting. Specifically, we dynamically select content for placement via NTN links. This selection is based on popularity and suitability for delivery through NTN, while considering the orbital motion of LEO satellites. Our system-level case studies, based on a practical LEO constellation, demonstrate the significant improvement in placement speed compared to existing methods, which neglect network mobility. We also demonstrate that NTN links significantly outperform standalone wireless TN solutions, particularly in the early stages of content delivery. This advantage is amplified when there is a higher correlation of content popularity across geographical regions.

eess.SY↗
arXiv2024

SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference

Recent advances in contrastive language-image pretraining (CLIP) have demonstrated strong capabilities in zero-shot classification by aligning visual representations with target text embeddings in an image level. However, in dense prediction tasks, CLIP often struggles to localize visual features within an image and fails to give accurate pixel-level predictions, which prevents it from functioning as a generalized visual foundation model. In this work, we aim to enhance CLIP's potential for semantic segmentation with minimal modifications to its pretrained models. By rethinking self-attention, we surprisingly find that CLIP can adapt to dense prediction tasks by simply introducing a novel Correlative Self-Attention (CSA) mechanism. Specifically, we replace the traditional self-attention block of CLIP vision encoder's last layer by our CSA module and reuse its pretrained projection matrices of query, key, and value, leading to a training-free adaptation approach for CLIP's zero-shot semantic segmentation. Extensive experiments show the advantage of CSA: we obtain a 38.2% average zero-shot mIoU across eight semantic segmentation benchmarks highlighted in this paper, significantly outperforming the existing SoTA's 33.9% and the vanilla CLIP's 14.1%.

cs.CV↗
arXiv2024

Semi-supervised Chinese Poem-to-Painting Generation via Cycle-consistent Adversarial Networks

Classical Chinese poetry and painting represent the epitome of artistic expression, but the abstract and symbolic nature of their relationship poses a significant challenge for computational translation. Most existing methods rely on large-scale paired datasets, which are scarce in this domain. In this work, we propose a semi-supervised approach using cycle-consistent adversarial networks to leverage the limited paired data and large unpaired corpus of poems and paintings. The key insight is to learn bidirectional mappings that enforce semantic alignment between the visual and textual modalities. We introduce novel evaluation metrics to assess the quality, diversity, and consistency of the generated poems and paintings. Extensive experiments are conducted on a new Chinese Painting Description Dataset (CPDD). The proposed model outperforms previous methods, showing promise in capturing the symbolic essence of artistic expression. Codes are available online \url{https://github.com/Mnster00/poemtopainting}.

cs.CV↗
arXiv2024

PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead

Large language models (LLMs) enhanced with retrieval-augmented generation (RAG) have introduced a new paradigm for web search. However, the limited context awareness of LLMs degrades their performance on RAG tasks. Existing methods to enhance context awareness are often inefficient, incurring time or memory overhead during inference, and many are tailored to specific position embeddings. In this paper, we propose Position-Embedding-Agnostic attention Re-weighting (PEAR), which enhances the context awareness of LLMs with zero inference overhead. Specifically, on a proxy task focused on context copying, we first detect heads which suppress the models' context awareness thereby diminishing RAG performance. To weaken the impact of these heads, we re-weight their outputs with learnable coefficients. The LLM (with frozen parameters) is optimized by adjusting these coefficients to minimize loss on the proxy task. As a result, the coefficients are optimized to values less than one, thereby reducing their tendency to suppress RAG performance. During inference, the optimized coefficients are fixed to re-weight these heads, regardless of the specific task at hand. Our proposed PEAR offers two major advantages over previous approaches: (1) It introduces zero additional inference overhead in terms of memory usage or inference time, while outperforming competitive baselines in accuracy and efficiency across various RAG tasks. (2) It is independent of position embedding algorithms, ensuring broader applicability.

cs.CL↗
arXiv2024

jina-embeddings-v3: Multilingual Embeddings With Task LoRA

We introduce jina-embeddings-v3, a novel text embedding model with 570 million parameters, achieves state-of-the-art performance on multilingual data and long-context retrieval tasks, supporting context lengths of up to 8192 tokens. The model includes a set of task-specific Low-Rank Adaptation (LoRA) adapters to generate high-quality embeddings for query-document retrieval, clustering, classification, and text matching. Evaluation on the MTEB benchmark shows that jina-embeddings-v3 outperforms the latest proprietary embeddings from OpenAI and Cohere on English tasks, while achieving superior performance compared to multilingual-e5-large-instruct across all multilingual tasks. With a default output dimension of 1024, users can flexibly reduce the embedding dimensions to as low as 32 without compromising performance, enabled by Matryoshka Representation Learning.

cs.CL↗