arXiv subjects

Qing Zhong

Publications and source records attributed to Qing Zhong.

12 recordsLinked to original sources

arXiv2026

LightAVSeg: Lightweight Audio-Visual Segmentation

Audio-Visual Segmentation (AVS) targets pixel level localization of sounding emitting objects in videos. However, existing models rely on dense cross-modal attention with quadratic computational cost, limiting their suitability for resource efficient deployment. Most efficiency oriented methods focus on backbone reduction and overlook the interaction module as the primary bottleneck. This paper proposes LightAVSeg, a lightweight framework that replaces heavy attention with a decoupled design for semantic filtering and spatial grounding, resulting in interaction costs that scale linearly with spatial resolution. Furthermore, we introduce an auxiliary alignment loss to enforce semantic consistency during training with zero inference overhead. Extensive experiments demonstrate that LightAVSeg achieves a new state-of-the-art among lightweight methods: with 20.5M parameters ~1/7 of AVSegFormer), it reaches 50.4 mIoU on the MS3 benchmark and enables efficient inference on a mobile processor.

cs.CV↗

arXiv2025

MACO: A Multi-Agent LLM Framework for Automated CGRA Hardware/Software Co-Design

Designing optimal Coarse-Grained Reconfigurable Arrays (CGRAs) requires navigating a vast, interdependent hardware/software space bottlenecked by costly manual iteration. We present MACO, an open-source, multi-agent LLM framework that automates CGRA HW/SW co-design. MACO decomposes the design loop into four collaborative stages, HW/SW Co-design, Error Correction, Best-Design Selection, and Evaluation & Feedback, to iteratively optimize power, performance, and area (PPA). To accelerate convergence and efficiently traverse the design space, MACO introduces an exponentially decaying exploration strategy, EDA-guided LLM self-learning, and robust rule-based error correction. Evaluated against state-of-the-art baselines, MACO reduces power consumption by 25.9%, improves performance by 20.0%, and accelerates the search process by 5x. Finally, we validate MACO's physical design through a complete 7nm ASIC design flow.

cs.AR↗

arXiv2025

A Temporal Modeling Framework for Video Pre-Training on Video Instance Segmentation

Contemporary Video Instance Segmentation (VIS) methods typically adhere to a pre-train then fine-tune regime, where a segmentation model trained on images is fine-tuned on videos. However, the lack of temporal knowledge in the pre-trained model introduces a domain gap which may adversely affect the VIS performance. To effectively bridge this gap, we present a novel video pre-training approach to enhance VIS models, especially for videos with intricate instance relationships. Our crucial innovation focuses on reducing disparities between the pre-training and fine-tuning stages. Specifically, we first introduce consistent pseudo-video augmentations to create diverse pseudo-video samples for pre-training while maintaining the instance consistency across frames. Then, we incorporate a multi-scale temporal module to enhance the model's ability to model temporal relations through self- and cross-attention at short- and long-term temporal spans. Our approach does not set constraints on model architecture and can integrate seamlessly with various VIS methods. Experiment results on commonly adopted VIS benchmarks show that our method consistently outperforms state-of-the-art methods. Our approach achieves a notable 4.0% increase in average precision on the challenging OVIS dataset.

cs.CV↗

arXiv2025

Strategic priorities for transformative progress in advancing biology with proteomics and artificial intelligence

Artificial intelligence (AI) is transforming scientific research, including proteomics. Advances in mass spectrometry (MS)-based proteomics data quality, diversity, and scale, combined with groundbreaking AI techniques, are unlocking new challenges and opportunities in biological discovery. Here, we highlight key areas where AI is driving innovation, from data analysis to new biological insights. These include developing an AI-friendly ecosystem for proteomics data generation, sharing, and analysis; improving peptide and protein identification and quantification; characterizing protein-protein interactions and protein complexes; advancing spatial and perturbation proteomics; integrating multi-omics data; and ultimately enabling AI-empowered virtual cells.

q-bio.OT↗

arXiv2025

A technical review of multi-omics data integration methods: from classical statistical to deep generative approaches

The rapid advancement of high-throughput sequencing and other assay technologies has resulted in the generation of large and complex multi-omics datasets, offering unprecedented opportunities for advancing precision medicine strategies. However, multi-omics data integration presents significant challenges due to the high dimensionality, heterogeneity, experimental gaps, and frequency of missing values across data types. Computational methods have been developed to address these issues, employing statistical and machine learning approaches to uncover complex biological patterns and provide deeper insights into our understanding of disease mechanisms. Here, we comprehensively review state-of-the-art multi-omics data integration methods with a focus on deep generative models, particularly variational autoencoders (VAEs) that have been widely used for data imputation and augmentation, joint embedding creation, and batch effect correction. We explore the technical aspects of loss functions and regularisation techniques including adversarial training, disentanglement and contrastive learning. Moreover, we discuss recent advancements in foundation models and the integration of emerging data modalities, while describing the current limitations and outlining future directions for enhancing multi-modal methodologies in biomedical research.

q-bio.QM↗

arXiv2024

OnlineTAS: An Online Baseline for Temporal Action Segmentation

Temporal context plays a significant role in temporal action segmentation. In an offline setting, the context is typically captured by the segmentation network after observing the entire sequence. However, capturing and using such context information in an online setting remains an under-explored problem. This work presents the an online framework for temporal action segmentation. At the core of the framework is an adaptive memory designed to accommodate dynamic changes in context over time, alongside a feature augmentation module that enhances the frames with the memory. In addition, we propose a post-processing approach to mitigate the severe over-segmentation in the online setting. On three common segmentation benchmarks, our approach achieves state-of-the-art performance.

cs.CV↗

arXiv2024

Demonstration of 3 V Programmable Josephson Junction Arrays Using Non-Integer-Multiple Logic

This article demonstrates a new kind of programmable logic for the representation of an integer that can be used for the programmable Josephson voltage standard. It can enable the numbers of junctions in most bits to be variable integer values, which is different from normal binary logic or ternary logic. Consequently, missing junctions due to superconducting short circuits can be tolerated under this logic. This logic can also have nearly the same segmentation efficiency as ternary logic. The completeness of the sequences using this logic is proven by the recursive method in mathematics in this paper. After that, a new algorithm for the representation of integers is presented according to the proven process, and an analysis of the number of fault-tolerant junctions for each bit is provided. Although the first and second bits are not tolerant to missing junctions, bits beyond these can tolerate one to hundreds of missing junctions. Due to the non-fixed multiples between the bits of the sequence, this logic is called non-integer-multiple logic. Finally, the design and fabrication of a 3 V programmable Josephson junction array using this logic are described, and the measurements and analysis of the characteristic parameters are presented.

cs.ET↗

arXiv2023

CTVIS: Consistent Training for Online Video Instance Segmentation

The discrimination of instance embeddings plays a vital role in associating instances across time for online video instance segmentation (VIS). Instance embedding learning is directly supervised by the contrastive loss computed upon the contrastive items (CIs), which are sets of anchor/positive/negative embeddings. Recent online VIS methods leverage CIs sourced from one reference frame only, which we argue is insufficient for learning highly discriminative embeddings. Intuitively, a possible strategy to enhance CIs is replicating the inference phase during training. To this end, we propose a simple yet effective training strategy, called Consistent Training for Online VIS (CTVIS), which devotes to aligning the training and inference pipelines in terms of building CIs. Specifically, CTVIS constructs CIs by referring inference the momentum-averaged embedding and the memory bank storage mechanisms, and adding noise to the relevant embeddings. Such an extension allows a reliable comparison between embeddings of current instances and the stable representations of historical instances, thereby conferring an advantage in modeling VIS challenges such as occlusion, re-identification, and deformation. Empirically, CTVIS outstrips the SOTA VIS models by up to +5.0 points on three VIS benchmarks, including YTVIS19 (55.1% AP), YTVIS21 (50.1% AP) and OVIS (35.5% AP). Furthermore, we find that pseudo-videos transformed from images can train robust models surpassing fully-supervised ones.

cs.CV↗

arXiv2019

One Dimensional Nearly Free Electron States in Borophene

Two-dimensional boron (borophene) is featured by its structural polymorphs and distinct in-plane anisotropy, opening opportunities to achieve tailored electronic properties by intermixing different phases. Here, using scanning tunneling spectroscopy combined with first-principles calculations, delocalized one-dimensional nearly free electron states (NFE) in the (2,3) or \b{eta}12 borophene sheet on the Ag(111) surface were observed. The NFE states emerge from a line defect in the borophene, manifested as a structural unit of the (2,2) or \c{hi}3 sheet, which creates an in-plane potential well that shifts the states toward the Fermi level. The NFE states are held in the 2D plane of borophene, rather than in the vacuum region as observed in other nanostructures. Furthermore the borophene can provide a rare prototype to further study novel NFE behaviors, which may have potential applications on transport or field emission nanodevices based on boron.

cond-mat.mtrl-sci↗

arXiv2017

Strain-Induced Band Engineering in Monolayer Stanene on Sb(111)

Two-dimensional (2D) allotrope of tin with low buckled honeycomb structure, named as stanene, is proposed to be an ideal 2D topological insulator with a nontrivial gap larger than 0.1 eV. Theoretical works also pointed out the topological property of stanene occurs by strain tuning. In this letter, we report the successful realization of high quality, monolayer stanene film as well as monolayer stanene nanoribbons on Sb(111) surface by molecular beam epitaxy, providing an ideal platform to the study of stanene. More importantly, we observed a continuous evolution of the electronic bands of stanene across a nanoribbon, which are related to the strain field gradient in stanene. Our work experimentally confirmed that strain is an effective method for band engineering in stanene, which is important for fundamental research and application of stanene.

cond-mat.mtrl-sci↗

arXiv2017

Synthesis of Borophene Nanoribbons on Ag(110) Surface

We present the successful synthesis of single-atom-thick borophene nanoribbons (BNRs) by self-assembly of boron on Ag(110) surface. The scanning tunneling microscopy (STM) studies reveal high quality BNRs: all the ribbons are along the [-110] direction of Ag(110), and can run across the steps on the surface. The width of ribbons is distributed in a narrow range around 10.3 nm. High resolution STM images revealed four ordered surface structures in BNRs. Combined with DFT calculations, we found that all the four structures of boron nanoribbons consist of the boron chains with different width, separated by hexagonal hole arrays. The successful synthesis of BNRs enriches the low dimensional allotrope of boron and may promote further applications of borophene

cond-mat.mtrl-sci↗

arXiv2015

Experimental Realization of Two-Dimensional Boron Sheets

Boron is the fifth element in the periodic table and possesses rich chemistry second only to carbon. A striking feature of boron is that B12 icosahedral cages occur as the building blocks in bulk boron and many boron compounds. This is in contrast to its neighboring element, carbon, which prefers 2D layered structure (graphite) in its bulk form. On the other hand, boron clusters of medium size have been predicted to be planar or quasi-planar, such as B12+ , B13+, B19-, B36, and so on. This is also in contrast to carbon clusters which exhibit various cage structures (fullerenes). Therefore, boron and carbon can be viewed as a set of complementary chemical systems in their bulk and cluster structures. Now, with the boom of graphene, an intriguing question is that whether boron can also form a monoatomic-layer 2D sheet structure? Here, we report the first successful experimental realization of 2D boron sheets. We have revealed two types of boron sheet structures, corresponding to a triangular boron lattice with different arrangements of the hexagonal holes. Moreover, our boron sheets were found to be relatively stable against oxidization, and interacts only weekly with the substrate. The realization of such a long expected 2D boron sheet could open a door toward boron electronics, in analogous to the carbon electronics based on graphene.

cond-mat.mes-hall↗