arXiv subjects

Yikun Liu

Publications and source records attributed to Yikun Liu.

At least 19 recordsLinked to original sources

arXiv2026

High resolution meta-stereomicroscope based on birefringent meta-optics

Achieving both high lateral and high depth resolution is a longstanding goal in stereomicroscopy. Although meta-optics have revolutionized lens design by alleviating the physical constraints of conventional optical architectures, existing metalens-assisted stereomicroscopes still suffer from field of view (FOV) mismatch between meta-optical and conventional optical components in stereomicroscopes, thereby limiting their imaging performance. Here, we show that this mismatch can be fundamentally eliminated through a fully meta-optical architecture. The integrated system enables flexible control of numerical aperture and magnification with larger depth of field (DOF) and FOV than those of the metalens-assisted stereomicroscopes. Experimentally, we achieve an integrated meta-stereomicroscope with a lateral resolution of 435 nm, surpassing the performance of previously reported stereomicroscopes. Empowered by a stereo neural network, the system enables straightforward reconstruction of high-resolution three-dimensional surface morphology with a depth resolution of 1026 nm, demonstrating the capability to simultaneously achieve high lateral and depth resolution imaging. This integrated architecture operates in both transmission and reflection modes for biomedical imaging and industrial inspection, highlighting its broad applicability for real-time observation across biomedical and industrial scenarios.

physics.optics↗

arXiv2026

Block-exoticity of reduction simple fusion systems on $S(n,p)$

In this paper, we prove that for $p\geq 13$ and $5\leq n\leq p-3$, every reduction simple fusion system on the finite $p$-group $S(n,p)$ is block-exotic. Furthermore, we establish the block-exoticity of three infinite families of reduction simple exotic fusion systems.

math.RT↗

arXiv2026

POINTS-Seeker: An Open Recipe for Multimodal Search Agents with Visual Memory Management

Large Multimodal Models (LMMs) excel at visual perception but struggle with real-time, knowledge-intensive queries due to their reliance on static parametric knowledge. While multimodal search agents offer a promising solution, developing them from vanilla LMMs presents two major challenges: the lack of open recipes to cultivate search agency from scratch, and the severe context explosion (attention dilution) that occurs during long-horizon multi-turn investigations. In this paper, we address both challenges by developing a native multimodal search agent. First, we introduce an open training recipe featuring Agentic Seeding, a formative training stage that bootstraps tool-use and planning abilities directly from a non-agentic foundation. Second, to overcome the context bottleneck, we propose V-Fold, an adaptive memory management mechanism. V-Fold retains recent interactions as high-fidelity text while folding stale historical context into the visual space via rendering, exploiting the model's cross-modal alignment to preserve raw evidence without text token redundancy. Combining these innovations, we present POINTS-Seeker-8B, which achieves state-of-the-art performance among models of comparable scale across six multimodal search benchmarks.

cs.CV↗

arXiv2026

A Sanity Check on Composed Image Retrieval

Composed Image Retrieval (CIR) aims to retrieve a target image based on a query composed of a reference image, and a relative caption that specifies the desired modification. Despite the rapid development of CIR models, their performance is not well characterized by existing benchmarks, which inherently contain indeterminate queries degrading the evaluation (i.e., multiple candidate images, rather than solely the target image, meet the query criteria), and have not considered their effectiveness in the context of the multi-round system. Motivated by this, we consider improving the evaluation procedure from two aspects: 1) we introduce FISD, a Fully-Informed Semantically-Diverse benchmark, which employs generative models to precisely control the variables of reference-target image pairs, enabling a more accurate evaluation of CIR methods across six dimensions, without query ambiguity; 2) we propose an automatic multi-round agentic evaluation framework to probe the potential of the existing models in the interactive scenarios. By observing how models adapt and refine their choices over successive rounds of queries, this framework provides a more realistic appraisal of their efficacy in practical applications. Extensive experiments and comparisons prove the value of our novel evaluation on typical CIR methods.

cs.CV↗

arXiv2026

POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs

Multimodal Large Language Models (MLLMs) have recently demonstrated remarkable capabilities in cross-modal understanding and generation. However, the rapid growth of visual token sequences--especially in long-video and streaming scenarios--poses a major challenge to their scalability and real-world deployment. Thus, we introduce POINTS-Long, a native dual-mode MLLM featuring dynamic visual token scaling inspired by the human visual system. The model supports two complementary perception modes: focus mode and standby mode, enabling users to dynamically trade off efficiency and accuracy during inference. On fine-grained visual tasks, the focus mode retains the optimal performance, while on long-form general visual understanding, the standby mode retains 97.7-99.7% of the original accuracy using only 1/40-1/10th of the visual tokens. Moreover, POINTS-Long natively supports streaming visual understanding via a dynamically detachable KV-cache design, allowing efficient maintenance of ultra-long visual memory. Our work provides new insights into the design of future MLLMs and lays the foundation for adaptive and efficient long-form visual understanding.

cs.CV↗

arXiv2026

VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimization

Multimodal Large Language Models (MLLMs) have recently achieved remarkable success in visual-language understanding, demonstrating superior high-level semantic alignment within their vision encoders. An important question thus arises: Can these encoders serve as versatile vision backbones, capable of reliably performing classic vision-centric tasks as well? To address the question, we make the following contributions: (i) we identify that the vision encoders within MLLMs exhibit deficiencies in their dense feature representations, as evidenced by their suboptimal performance on dense prediction tasks (e.g., semantic segmentation, depth estimation); (ii) we propose VersaViT, a well-rounded vision transformer that instantiates a novel multi-task framework for collaborative post-training. This framework facilitates the optimization of the vision backbone via lightweight task heads with multi-granularity supervision; (iii) extensive experiments across various downstream tasks demonstrate the effectiveness of our method, yielding a versatile vision backbone suited for both language-mediated reasoning and pixel-level understanding.

cs.CV↗

arXiv2026

POINTS-GUI-G: GUI-Grounding Journey

The rapid advancement of vision-language models has catalyzed the emergence of GUI agents, which hold immense potential for automating complex tasks, from online shopping to flight booking, thereby alleviating the burden of repetitive digital workflows. As a foundational capability, GUI grounding is typically established as a prerequisite for end-to-end task execution. It enables models to precisely locate interface elements, such as text and icons, to perform accurate operations like clicking and typing. Unlike prior works that fine-tune models already possessing strong spatial awareness (e.g., Qwen3-VL), we aim to master the full technical pipeline by starting from a base model with minimal grounding ability, such as POINTS-1.5. We introduce POINTS-GUI-G-8B, which achieves state-of-the-art performance with scores of 59.9 on ScreenSpot-Pro, 66.0 on OSWorld-G, 95.7 on ScreenSpot-v2, and 49.9 on UI-Vision. Our model's success is driven by three key factors: (1) Refined Data Engineering, involving the unification of diverse open-source datasets format alongside sophisticated strategies for augmentation, filtering, and difficulty grading; (2) Improved Training Strategies, including continuous fine-tuning of the vision encoder to enhance perceptual accuracy and maintaining resolution consistency between training and inference; and (3) Reinforcement Learning (RL) with Verifiable Rewards. While RL is traditionally used to bolster reasoning, we demonstrate that it significantly improves precision in the perception-intensive GUI grounding task. Furthermore, GUI grounding provides a natural advantage for RL, as rewards are easily verifiable and highly accurate.

cs.CV↗

arXiv2025

Learning Streaming Video Representation via Multitask Training

Understanding continuous video streams plays a fundamental role in real-time applications including embodied AI and autonomous driving. Unlike offline video understanding, streaming video understanding requires the ability to process video streams frame by frame, preserve historical information, and make low-latency decisions. To address these challenges, our main contributions are three-fold. (i) We develop a novel streaming video backbone, termed as StreamFormer, by incorporating causal temporal attention into a pre-trained vision transformer. This enables efficient streaming video processing while maintaining image representation capability. (ii) To train StreamFormer, we propose to unify diverse spatial-temporal video understanding tasks within a multitask visual-language alignment framework. Hence, StreamFormer learns global semantics, temporal dynamics, and fine-grained spatial relationships simultaneously. (iii) We conduct extensive experiments on online action detection, online video instance segmentation, and video question answering. StreamFormer achieves competitive results while maintaining efficiency, demonstrating its potential for real-time applications.

cs.CV↗

arXiv2024

LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant

With the rapid advancement of multimodal information retrieval, increasingly complex retrieval tasks have emerged. Existing methods predominately rely on task-specific fine-tuning of vision-language models, often those trained with image-text contrastive learning. In this paper, we explore the possibility of re-purposing generative Large Multimodal Models (LMMs) for retrieval. This approach enables unifying all retrieval tasks under the same formulation and, more importantly, allows for extrapolation towards unseen retrieval tasks without additional training. Our contributions can be summarised in the following aspects: (i) We introduce LamRA, a versatile framework designed to empower LMMs with sophisticated retrieval and reranking capabilities. (ii) For retrieval, we adopt a two-stage training strategy comprising language-only pre-training and multimodal instruction tuning to progressively enhance LMM's retrieval performance. (iii) For reranking, we employ joint training for both pointwise and listwise reranking, offering two distinct ways to further boost the retrieval performance. (iv) Extensive experimental results underscore the efficacy of our method in handling more than ten retrieval tasks, demonstrating robust performance in both supervised and zero-shot settings, including scenarios involving previously unseen retrieval tasks.

cs.CV↗

arXiv2024

Inhomogeneous illumination image enhancement under ex-tremely low visibility condition

Imaging through dense fog presents unique challenges, with essential visual information crucial for applications like object detection and recognition obscured, thereby hindering conventional image processing methods. Despite improvements through neural network-based approaches, these techniques falter under extremely low visibility conditions exacerbated by inhomogeneous illumination, which degrades deep learning performance due to inconsistent signal intensities. We introduce in this paper a novel method that adaptively filters background illumination based on Structural Differential and Integral Filtering (SDIF) to enhance only vital signal information. The grayscale banding is eliminated by incorporating a visual optimization strategy based on image gradients. Maximum Histogram Equalization (MHE) is used to achieve high contrast while maintaining fidelity to the original content. We evaluated our algorithm using data collected from both a fog chamber and outdoor environments, and performed comparative analyses with existing methods. Our findings demonstrate that our proposed method significantly enhances signal clarity under extremely low visibility conditions and out-performs existing techniques, offering substantial improvements for deep fog imaging applications.

cs.CV↗

arXiv2024

Harnessing Optical Imaging Limit through Atmospheric Scattering Media

Recording and identifying faint objects through atmospheric scattering media by an optical system are fundamentally interesting and technologically important. In this work, we introduce a comprehensive model that incorporates contributions from target characteristics, atmospheric effects, imaging system, digital processing, and visual perception to assess the ultimate perceptible limit of geometrical imaging, specifically the angular resolution at the boundary of visible distance. The model allows to reevaluate the effectiveness of conventional imaging recording, processing, and perception and to analyze the limiting factors that constrain image recognition capabilities in atmospheric media. The simulations were compared with the experimental results measured in a fog chamber and outdoor settings. The results reveal general good agreement between analysis and experimental, pointing out the way to harnessing the physical limit for optical imaging in scattering media. An immediate application of the study is the extension of the image range by an amount of 1.2 times with noise reduction via multi-frame averaging, hence greatly enhancing the capability of optical imaging in the atmosphere.

physics.optics↗

arXiv2024

Audio-Visual Segmentation via Unlabeled Frame Exploitation

Audio-visual segmentation (AVS) aims to segment the sounding objects in video frames. Although great progress has been witnessed, we experimentally reveal that current methods reach marginal performance gain within the use of the unlabeled frames, leading to the underutilization issue. To fully explore the potential of the unlabeled frames for AVS, we explicitly divide them into two categories based on their temporal characteristics, i.e., neighboring frame (NF) and distant frame (DF). NFs, temporally adjacent to the labeled frame, often contain rich motion information that assists in the accurate localization of sounding objects. Contrary to NFs, DFs have long temporal distances from the labeled frame, which share semantic-similar objects with appearance variations. Considering their unique characteristics, we propose a versatile framework that effectively leverages them to tackle AVS. Specifically, for NFs, we exploit the motion cues as the dynamic guidance to improve the objectness localization. Besides, we exploit the semantic cues in DFs by treating them as valid augmentations to the labeled frames, which are then used to enrich data diversity in a self-training manner. Extensive experimental results demonstrate the versatility and superiority of our method, unleashing the power of the abundant unlabeled frames.

cs.CV↗

arXiv2024

Zero-shot Composed Text-Image Retrieval

In this paper, we consider the problem of composed image retrieval (CIR), it aims to train a model that can fuse multi-modal information, e.g., text and images, to accurately retrieve images that match the query, extending the user's expression ability. We make the following contributions: (i) we initiate a scalable pipeline to automatically construct datasets for training CIR model, by simply exploiting a large-scale dataset of image-text pairs, e.g., a subset of LAION-5B; (ii) we introduce a transformer-based adaptive aggregation model, TransAgg, which employs a simple yet efficient fusion mechanism, to adaptively combine information from diverse modalities; (iii) we conduct extensive ablation studies to investigate the usefulness of our proposed data construction procedure, and the effectiveness of core components in TransAgg; (iv) when evaluating on the publicly available benckmarks under the zero-shot scenario, i.e., training on the automatically constructed datasets, then directly conduct inference on target downstream datasets, e.g., CIRR and FashionIQ, our proposed approach either performs on par with or significantly outperforms the existing state-of-the-art (SOTA) models. Project page: https://code-kunkun.github.io/ZS-CIR/

cs.CV↗

arXiv2023

A Deep-Learning Method Using Auto-encoder and Generative Adversarial Network for Anomaly Detection on Ancient Stone Stele Surfaces

Accurate detection of natural deterioration and man-made damage on the surfaces of ancient stele in the first instance is essential for their preventive conservation. Existing methods for cultural heritage preservation are not able to achieve this goal perfectly due to the difficulty of balancing accuracy, efficiency, timeliness, and cost. This paper presents a deep-learning method to automatically detect above mentioned emergencies on ancient stone stele in real time, employing autoencoder (AE) and generative adversarial network (GAN). The proposed method overcomes the limitations of existing methods by requiring no extensive anomaly samples while enabling comprehensive detection of unpredictable anomalies. the method includes stages of monitoring, data acquisition, pre-processing, model structuring, and post-processing. Taking the Longmen Grottoes' stone steles as a case study, an unsupervised learning model based on AE and GAN architectures is proposed and validated with a reconstruction accuracy of 99.74\%. The method's evaluation revealed the proficient detection of seven artificially designed anomalies and demonstrated precision and reliability without false alarms. This research provides novel ideas and possibilities for the application of deep learning in the field of cultural heritage.

cs.CV↗

arXiv2023

Local-Global Transformer Enhanced Unfolding Network for Pan-sharpening

Pan-sharpening aims to increase the spatial resolution of the low-resolution multispectral (LrMS) image with the guidance of the corresponding panchromatic (PAN) image. Although deep learning (DL)-based pan-sharpening methods have achieved promising performance, most of them have a two-fold deficiency. For one thing, the universally adopted black box principle limits the model interpretability. For another thing, existing DL-based methods fail to efficiently capture local and global dependencies at the same time, inevitably limiting the overall performance. To address these mentioned issues, we first formulate the degradation process of the high-resolution multispectral (HrMS) image as a unified variational optimization problem, and alternately solve its data and prior subproblems by the designed iterative proximal gradient descent (PGD) algorithm. Moreover, we customize a Local-Global Transformer (LGT) to simultaneously model local and global dependencies, and further formulate an LGT-based prior module for image denoising. Besides the prior module, we also design a lightweight data module. Finally, by serially integrating the data and prior modules in each iterative stage, we unfold the iterative algorithm into a stage-wise unfolding network, Local-Global Transformer Enhanced Unfolding Network (LGTEUN), for the interpretable MS pan-sharpening. Comprehensive experimental results on three satellite data sets demonstrate the effectiveness and efficiency of LGTEUN compared with state-of-the-art (SOTA) methods. The source code is available at https://github.com/lms-07/LGTEUN.

cs.CV↗

arXiv2018

Imaging of objects through a thin scattering layer using a spectrally and spatially separated reference

Incoherently illuminated or luminescent objects give rise to a low-contrast speckle-like pattern when observed through a thin diffusive medium, as such a medium effectively convolves their shape with a speckle-like point spread function (PSF). This point spread function can be extracted in the presence of a reference object of known shape. Here it is shown that reference objects that are both spatially and spectrally separated from the object of interest can be used to obtain an approximation of the point spread function. The crucial observation, corroborated by analytical calculations, is that the spectrally shifted point spread function is strongly correlated to a spatially scaled one. With the approximate point spread function thus obtained, the speckle-like pattern is deconvolved to produce a clear and sharp image of the object on a speckle-like background of low intensity.

physics.optics↗

arXiv2017

3D Object Imaging through Scattering Media

Human ability to visualize an image is usually hindered by optical scattering. Recent extensive studies have promoted imaging technique through turbid materials to a reality where color image can be restored behind scattering media in real time. The big challenge now is to recover a 3D object in a large field of view with depth resolving ability. Here, we reveal a new physical relationship between speckles generated from objects at different planes. With a single given point spread function, 3D imaging through scattering media is achieved even beyond the depth of field (DOF). Experimental testing of standard scattering media shows that the original DOF can be extended up to 5 times and the physical mechanism is depicted. This extended 3D imaging is expected to have important applications in science, technology, bio-medical, security and defense.

physics.optics↗

arXiv2017

Ultrafast Optical Signal Processing with Bragg Structures

The phase, amplitude, speed, and polarization, in addition to many other properties of light, can be modulated by photonic Bragg structures. In conjunction with nonlinearity and quantum effects, a variety of ensuing micro- or nano-photonic applications can be realized. This paper reviews various optical phenomena in several exemplary 1D Bragg gratings. Important examples are resonantly absorbing photonic structures, chirped Bragg grating, and cholesteric liquid crystals; their unique operation capabilities and key issues are considered in detail. These Bragg structures are expected to be used in wide-spread applications involving light field modulations, especially in the rapidly advancing field of ultrafast optical signal processing.

physics.optics↗