arXiv subjects

Shengwei Wang

Publications and source records attributed to Shengwei Wang.

9 recordsLinked to original sources

arXiv2026

An Effective Router for Vision-Language Model Selection

Vision-language models (VLMs) with varying performance and resource requirements are widely deployed, making it difficult for users to select the most appropriate one among numerous VLM candidates. Existing work reveals the performance paradox phenomenon in language models and focuses on routing methods to solve it. However, developing a router for VLM selection is still a critical yet challenging problem, which primarily faces: 1) lack of specialized data, 2) ineffective feature representation, and 3) rigid model space and costly adaptation. In this paper, we construct a multimodal dataset for VLM selection, containing the outputs of seven mainstream VLMs on 32,626 unique image-text queries. We then propose ARMS, a router for VLM selection. ARMS enhances input signals with VLM profiles, employs a simple but effective architecture to improve representations of queries and VLM capabilities. To improve ARMS' adaptation to new VLMs, we propose two extension training strategies: incremental training and independent training. Experimental results on both in-distribution and out-of-distribution test sets demonstrate the effectiveness of ARMS. In particular, using our training strategy, ARMs (only 800M in size) can adapt to a broader VLM space and defeat commercial models like GPT-4o that are hundreds of times larger in scale. Our code, models, and datasets are available in the anonymous repository.

cs.AI↗

arXiv2026

The Fourth Challenge on Image Super-Resolution ($\times$4) at NTIRE 2026: Benchmark Results and Method Overview

This paper presents the NTIRE 2026 image super-resolution ($\times$4) challenge, one of the associated competitions of the NTIRE 2026 Workshop at CVPR 2026. The challenge aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs generated through bicubic downsampling with a $\times$4 scaling factor. The objective is to develop effective super-resolution solutions and analyze recent advances in the field. To reflect the evolving objectives of image super-resolution, the challenge includes two tracks: (1) a restoration track, which emphasizes pixel-wise fidelity and ranks submissions based on PSNR; and (2) a perceptual track, which focuses on visual realism and evaluates results using a perceptual score. A total of 194 participants registered for the challenge, with 31 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, main results, and methods of participating teams. The challenge provides a unified benchmark and offers insights into current progress and future directions in image super-resolution.

cs.CV↗

arXiv2025

Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution

Diffusion models have recently shown promising results for video super-resolution (VSR). However, directly adapting generative diffusion models to VSR can result in redundancy, since low-quality videos already preserve substantial content information. Such redundancy leads to increased computational overhead and learning burden, as the model performs superfluous operations and must learn to filter out irrelevant information. To address this problem, we propose OASIS, an efficient $\textbf{o}$ne-step diffusion model with $\textbf{a}$ttention $\textbf{s}$pecialization for real-world v$\textbf{i}$deo $\textbf{s}$uper-resolution. OASIS incorporates an attention specialization routing that assigns attention heads to different patterns according to their intrinsic behaviors. This routing mitigates redundancy while effectively preserving pretrained knowledge, allowing diffusion models to better adapt to VSR and achieve stronger performance. Moreover, we propose a simple yet effective progressive training strategy, which starts with temporally consistent degradations and then shifts to inconsistent settings. This strategy facilitates learning under complex degradations. Extensive experiments demonstrate that OASIS achieves state-of-the-art performance on both synthetic and real-world datasets. OASIS also provides superior inference speed, offering a $\textbf{6.2$\times$}$ speedup over one-step diffusion baselines such as SeedVR2. The code will be available at \href{https://github.com/jp-guo/OASIS}{https://github.com/jp-guo/OASIS}.

cs.CV↗

arXiv2025

Topology Structure Optimization of Reservoirs Using GLMY Homology

Reservoir is an efficient network for time series processing. It is well known that network structure is one of the determinants of its performance. However, the topology structure of reservoirs, as well as their performance, is hard to analyzed, due to the lack of suitable mathematical tools. In this paper, we study the topology structure of reservoirs using persistent GLMY homology theory, and develop a method to improve its performance. Specifically, it is found that the reservoir performance is closely related to the one-dimensional GLMY homology groups. Then, we develop a reservoir structure optimization method by modifying the minimal representative cycles of one-dimensional GLMY homology groups. Finally, by experiments, it is validated that the performance of reservoirs is jointly influenced by the reservoir structure and the periodicity of the dataset.

cs.LG↗

arXiv2025

Dynamic Control of Third-order Nonlinear Optical Properties of Gold Nanoparticle/Liquid Crystal Composites under External Electric Fields

This study investigates the dynamic control of third-order nonlinear optical absorption properties of gold nanoparticles (AuNPs) dispersed in nematic liquid crystals (LC). By leveraging the reconfigurable nature of liquid crystals under external electric fields, we demonstrate the ability to manipulate AuNP alignment, dimer formation, and subsequently the plasmon coupling effects. Planar oriented and degenerate LC cells were prepared, and their optical responses under varying electric fields were characterized using polarization microscopy, UV-VIS spectroscopy, and Z-scan techniques. In planar cells, the applied electric field reorients LC molecules and AuNPs, influencing plasmon coupling and the nonlinear absorption. Conversely, degenerate cells exhibit more complex behaviors due to multiple LC alignment directions. These findings illustrate the potential of AuNP/nematic LC systems for creating tunable photonic devices responsive to external stimuli.

cond-mat.soft↗

arXiv2024

Multi-Source Coflow Scheduling in Collaborative Edge Computing with Multihop Network

Collaborative edge computing has become a popular paradigm where edge devices collaborate by sharing resources. Data dissemination is a fundamental problem in CEC to decide what data is transmitted from which device and how. Existing works on data dissemination have not focused on coflow scheduling in CEC, which involves deciding the order of flows within and across coflows at network links. Coflow implies a set of parallel flows with a shared objective. The existing works on coflow scheduling in data centers usually assume a non-blocking switch and do not consider congestion at different links in the multi-hop path in CEC, leading to increased coflow completion time (CCT). Furthermore, existing works do not consider multiple flow sources that cannot be ignored, as data can have duplicate copies at different edge devices. This work formulates the multi-source coflow scheduling problem in CEC, which includes jointly deciding the source and flow ordering for multiple coflows to minimize the sum of CCT. This problem is shown to be NP-hard and challenging as each flow can have multiple dependent conflicts at multiple links. We propose a source and coflow-aware search and adjust (SCASA) heuristic that first provides an initial solution considering the coflow characteristics. SCASA further improves the initial solution using the source search and adjust heuristic by leveraging the knowledge of both coflows and network congestion at links. Evaluation done using simulation experiments shows that SCASA leads to up to 83% reduction in the sum of CCT compared to benchmarks without a joint solution.

cs.NI↗

arXiv2024

Bridging Data Barriers among Participants: Assessing the Potential of Geoenergy through Federated Learning

Machine learning algorithms emerge as a promising approach in energy fields, but its practical is hindered by data barriers, stemming from high collection costs and privacy concerns. This study introduces a novel federated learning (FL) framework based on XGBoost models, enabling safe collaborative modeling with accessible yet concealed data from multiple parties. Hyperparameter tuning of the models is achieved through Bayesian Optimization. To ascertain the merits of the proposed FL-XGBoost method, a comparative analysis is conducted between separate and centralized models to address a classical binary classification problem in geoenergy sector. The results reveal that the proposed FL framework strikes an optimal balance between privacy and accuracy. FL models demonstrate superior accuracy and generalization capabilities compared to separate models, particularly for participants with limited data or low correlation features and offers significant privacy benefits compared to centralized model. The aggregated optimization approach within the FL agreement proves effective in tuning hyperparameters. This study opens new avenues for assessing unconventional reservoirs through collaborative and privacy-preserving FL techniques.

cs.LG↗

arXiv2018

Accelerate CU Partition in HEVC using Large-Scale Convolutional Neural Network

High efficiency video coding (HEVC) suffers high encoding computational complexity, partly attributed to the rate-distortion optimization quad-tree search in CU partition decision. Therefore, we propose a novel two-stage CU partition decision approach in HEVC intra-mode. In the proposed approach, CNN-based algorithm is designed to decide CU partition mode precisely in three depths. In order to alleviate computational complexity further, an auxiliary earl-termination mechanism is also proposed to filter obvious homogeneous CUs out of the subsequent CNN-based algorithm. Experimental results show that the proposed approach achieves about 37% encoding time saving on average and insignificant BD-Bitrate rise compared with the original HEVC encoder.

cs.CV↗

arXiv2016

Crowdsourcing Information Extraction for Biomedical Systematic Reviews

Information extraction is a critical step in the practice of conducting biomedical systematic literature reviews. Extracted structured data can be aggregated via methods such as statistical meta-analysis. Typically highly trained domain experts extract data for systematic reviews. The high expense of conducting biomedical systematic reviews has motivated researchers to explore lower cost methods that achieve similar rigor without compromising quality. Crowdsourcing represents one such promising approach. In this work-in-progress study, we designed a crowdsourcing task for biomedical information extraction. We briefly report the iterative design process and the results of two pilot testings. We found that giving more concrete examples in the task instruction can help workers better understand the task, especially for concepts that are abstract and confusing. We found a few workers completed most of the work, and our payment level appeared more attractive to workers from low-income countries. In the future, we will further evaluate our results with reference to gold standard extractions, thus assessing the feasibility of tasking crowd workers with extracting biomedical intervention information for systematic reviews.

cs.HC↗