arXiv subjects

Biao Yang

Publications and source records attributed to Biao Yang.

At least 37 records · Page 2Linked to original sources

arXiv2025

AttentionDrag: Exploiting Latent Correlation Knowledge in Pre-trained Diffusion Models for Image Editing

Traditional point-based image editing methods rely on iterative latent optimization or geometric transformations, which are either inefficient in their processing or fail to capture the semantic relationships within the image. These methods often overlook the powerful yet underutilized image editing capabilities inherent in pre-trained diffusion models. In this work, we propose a novel one-step point-based image editing method, named AttentionDrag, which leverages the inherent latent knowledge and feature correlations within pre-trained diffusion models for image editing tasks. This framework enables semantic consistency and high-quality manipulation without the need for extensive re-optimization or retraining. Specifically, we reutilize the latent correlations knowledge learned by the self-attention mechanism in the U-Net module during the DDIM inversion process to automatically identify and adjust relevant image regions, ensuring semantic validity and consistency. Additionally, AttentionDrag adaptively generates masks to guide the editing process, enabling precise and context-aware modifications with friendly interaction. Our results demonstrate a performance that surpasses most state-of-the-art methods with significantly faster speeds, showing a more efficient and semantically coherent solution for point-based image editing tasks.

cs.CV↗

arXiv2025

Photonic chiral bulk transports manipulated by boundary freedom in three-dimensional meta-crystals

In topological physics, one of the most intriguing phenomena is the presence of topological boundary states, accurately predicted by the well-established bulk-edge correspondence. For example, in three-dimensional Weyl semimetals, Fermi arcs emerge to connect projected Weyl points on the surface due to inheriting the bulk-edge correspondence from the integer quantum Hall effect. However, limited attention has been paid to exploring the reverse mechanism in topological crystals. In this study, we propose that boundaries can serve as an alternative degree of freedom to manipulate topological bulk transports. We analytically and experimentally validate our concept using a finite-thickness photonic meta-crystal that supports bulk nodal lines, with its zeroth modes exhibiting opposite chiral bulk transports under different boundary conditions. Notably, the mirror symmetry remains preserved across both configurations. These findings are applicable to other topological systems, providing new insights into systems with varied boundary conditions and offering the potential for the design of more compact and spatially efficient topological photonic devices.

cond-mat.mes-hall↗

arXiv2025

OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning

Scoring the Optical Character Recognition (OCR) capabilities of Large Multimodal Models (LMMs) has witnessed growing interest. Existing benchmarks have highlighted the impressive performance of LMMs in text recognition; however, their abilities in certain challenging tasks, such as text localization, handwritten content extraction, and logical reasoning, remain underexplored. To bridge this gap, we introduce OCRBench v2, a large-scale bilingual text-centric benchmark with currently the most comprehensive set of tasks (4x more tasks than the previous multi-scene benchmark OCRBench), the widest coverage of scenarios (31 diverse scenarios), and thorough evaluation metrics, with 10,000 human-verified question-answering pairs and a high proportion of difficult samples. Moreover, we construct a private test set with 1,500 manually annotated images. The consistent evaluation trends observed across both public and private test sets validate the OCRBench v2's reliability. After carefully benchmarking state-of-the-art LMMs, we find that most LMMs score below 50 (100 in total) and suffer from five-type limitations, including less frequently encountered text recognition, fine-grained perception, layout perception, complex element parsing, and logical reasoning. The project website is at: https://99franklin.github.io/ocrbench_v2/

cs.CV↗

arXiv2025

A 2D Semantic-Aware Position Encoding for Vision Transformers

Vision transformers have demonstrated significant advantages in computer vision tasks due to their ability to capture long-range dependencies and contextual relationships through self-attention. However, existing position encoding techniques, which are largely borrowed from natural language processing, fail to effectively capture semantic-aware positional relationships between image patches. Traditional approaches like absolute position encoding and relative position encoding primarily focus on 1D linear position relationship, often neglecting the semantic similarity between distant yet contextually related patches. These limitations hinder model generalization, translation equivariance, and the ability to effectively handle repetitive or structured patterns in images. In this paper, we propose 2-Dimensional Semantic-Aware Position Encoding ($\text{SaPE}^2$), a novel position encoding method with semantic awareness that dynamically adapts position representations by leveraging local content instead of fixed linear position relationship or spatial coordinates. Our method enhances the model's ability to generalize across varying image resolutions and scales, improves translation equivariance, and better aggregates features for visually similar but spatially distant patches. By integrating $\text{SaPE}^2$ into vision transformers, we bridge the gap between position encoding and perceptual similarity, thereby improving performance on computer vision tasks.

cs.CV↗

arXiv2024

Non-equilibrium carrier dynamics and band structure of graphene on 2D tin

Intercalation of epitaxial graphene on SiC(0001) with Sn results in a well-ordered Sn $(1\times1)$ structure on the SiC surface with quasi-freestanding graphene on top. While the electronic properties of the individual layers have been studied in the past, emerging phenomena arising from possible inter-layer interactions between the 2D\,Sn layer and graphene remain unexplored. We use time- and angle-resolved photoemission spectroscopy to reveal a surprisingly short-lived non-equilibrium carrier distribution inside the Dirac cone of Sn-intercalated graphene. Further, we find that the graphene $π$-band exhibits a transient increase in binding energy that we attribute to charging of the graphene layer with holes. We interpret our results with support from density functional theory calculations of the graphene - 2D\,Sn heterostructure that reveal a substantial hybridization between the graphene $π$-bands and Sn states, providing a channel for efficient ultrafast charge transfer between the layers. Our results on the graphene - 2D\,Sn model system are expected to trigger similar investigations on related heterostructures obtained by intercalation of epitaxial graphene. Regarding the huge choice of materials that have been successfully intercalated in the past, we believe that the interlayer interactions revealed in the present work only represent the tip of the iceberg with many fascinating emerging phenomena to be discovered in the near future.

cond-mat.mes-hall↗

arXiv2024

AFIDAF: Alternating Fourier and Image Domain Adaptive Filters as an Efficient Alternative to Attention in ViTs

We propose and demonstrate an alternating Fourier and image domain filtering approach for feature extraction as an efficient alternative to build a vision backbone without using the computationally intensive attention. The performance among the lightweight models reaches the state-of-the-art level on ImageNet-1K classification, and improves downstream tasks on object detection and segmentation consistently as well. Our approach also serves as a new tool to compress vision transformers (ViTs).

cs.CV↗

arXiv2024

Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models

Large Multimodal Models (LMMs) have shown promise in vision-language tasks but struggle with high-resolution input and detailed scene understanding. Addressing these challenges, we introduce Monkey to enhance LMM capabilities. Firstly, Monkey processes input images by dividing them into uniform patches, each matching the size (e.g., 448x448) used in the original training of the well-trained vision encoder. Equipped with individual adapter for each patch, Monkey can handle higher resolutions up to 1344x896 pixels, enabling the detailed capture of complex visual information. Secondly, it employs a multi-level description generation method, enriching the context for scene-object associations. This two-part strategy ensures more effective learning from generated data: the higher resolution allows for a more detailed capture of visuals, which in turn enhances the effectiveness of comprehensive descriptions. Extensive ablative results validate the effectiveness of our designs. Additionally, experiments on 18 datasets further demonstrate that Monkey surpasses existing LMMs in many tasks like Image Captioning and various Visual Question Answering formats. Specially, in qualitative tests focused on dense text question answering, Monkey has exhibited encouraging results compared with GPT4V. Code is available at https://github.com/Yuliang-Liu/Monkey.

cs.CV↗

arXiv2024

OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models

Large models have recently played a dominant role in natural language processing and multimodal vision-language learning. However, their effectiveness in text-related visual tasks remains relatively unexplored. In this paper, we conducted a comprehensive evaluation of Large Multimodal Models, such as GPT4V and Gemini, in various text-related visual tasks including Text Recognition, Scene Text-Centric Visual Question Answering (VQA), Document-Oriented VQA, Key Information Extraction (KIE), and Handwritten Mathematical Expression Recognition (HMER). To facilitate the assessment of Optical Character Recognition (OCR) capabilities in Large Multimodal Models, we propose OCRBench, a comprehensive evaluation benchmark. OCRBench contains 29 datasets, making it the most comprehensive OCR evaluation benchmark available. Furthermore, our study reveals both the strengths and weaknesses of these models, particularly in handling multilingual text, handwritten text, non-semantic text, and mathematical expression recognition. Most importantly, the baseline results presented in this study could provide a foundational framework for the conception and assessment of innovative strategies targeted at enhancing zero-shot multimodal techniques. The evaluation pipeline and benchmark are available at https://github.com/Yuliang-Liu/MultimodalOCR.

cs.CV↗

arXiv2024

Exploring the Capabilities of Large Multimodal Models on Dense Text

While large multi-modal models (LMM) have shown notable progress in multi-modal tasks, their capabilities in tasks involving dense textual content remains to be fully explored. Dense text, which carries important information, is often found in documents, tables, and product descriptions. Understanding dense text enables us to obtain more accurate information, assisting in making better decisions. To further explore the capabilities of LMM in complex text tasks, we propose the DT-VQA dataset, with 170k question-answer pairs. In this paper, we conduct a comprehensive evaluation of GPT4V, Gemini, and various open-source LMMs on our dataset, revealing their strengths and weaknesses. Furthermore, we evaluate the effectiveness of two strategies for LMM: prompt engineering and downstream fine-tuning. We find that even with automatically labeled training datasets, significant improvements in model performance can be achieved. We hope that this research will promote the study of LMM in dense text tasks. Code will be released at https://github.com/Yuliang-Liu/MultimodalOCR.

cs.CL↗

arXiv2024

TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document

We present TextMonkey, a large multimodal model (LMM) tailored for text-centric tasks. Our approach introduces enhancement across several dimensions: By adopting Shifted Window Attention with zero-initialization, we achieve cross-window connectivity at higher input resolutions and stabilize early training; We hypothesize that images may contain redundant tokens, and by using similarity to filter out significant tokens, we can not only streamline the token length but also enhance the model's performance. Moreover, by expanding our model's capabilities to encompass text spotting and grounding, and incorporating positional information into responses, we enhance interpretability. It also learns to perform screenshot tasks through finetuning. Evaluation on 12 benchmarks shows notable improvements: 5.2% in Scene Text-Centric tasks (including STVQA, TextVQA, and OCRVQA), 6.9% in Document-Oriented tasks (such as DocVQA, InfoVQA, ChartVQA, DeepForm, Kleister Charity, and WikiTableQuestions), and 2.8% in Key Information Extraction tasks (comprising FUNSD, SROIE, and POIE). It outperforms in scene text spotting with a 10.9\% increase and sets a new standard on OCRBench, a comprehensive benchmark consisting of 29 OCR-related assessments, with a score of 561, surpassing previous open-sourced large multimodal models for document understanding. Code will be released at https://github.com/Yuliang-Liu/Monkey.

cs.CV↗

arXiv2024

Sequential Visual and Semantic Consistency for Semi-supervised Text Recognition

Scene text recognition (STR) is a challenging task that requires large-scale annotated data for training. However, collecting and labeling real text images is expensive and time-consuming, which limits the availability of real data. Therefore, most existing STR methods resort to synthetic data, which may introduce domain discrepancy and degrade the performance of STR models. To alleviate this problem, recent semi-supervised STR methods exploit unlabeled real data by enforcing character-level consistency regularization between weakly and strongly augmented views of the same image. However, these methods neglect word-level consistency, which is crucial for sequence recognition tasks. This paper proposes a novel semi-supervised learning method for STR that incorporates word-level consistency regularization from both visual and semantic aspects. Specifically, we devise a shortest path alignment module to align the sequential visual features of different views and minimize their distance. Moreover, we adopt a reinforcement learning framework to optimize the semantic similarity of the predicted strings in the embedding space. We conduct extensive experiments on several standard and challenging STR benchmarks and demonstrate the superiority of our proposed method over existing semi-supervised STR methods.

cs.CV↗

arXiv2024

Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition

Scene text recognition is a rapidly developing field that faces numerous challenges due to the complexity and diversity of scene text, including complex backgrounds, diverse fonts, flexible arrangements, and accidental occlusions. In this paper, we propose a novel approach called Class-Aware Mask-guided feature refinement (CAM) to address these challenges. Our approach introduces canonical class-aware glyph masks generated from a standard font to effectively suppress background and text style noise, thereby enhancing feature discrimination. Additionally, we design a feature alignment and fusion module to incorporate the canonical mask guidance for further feature refinement for text recognition. By enhancing the alignment between the canonical mask feature and the text feature, the module ensures more effective fusion, ultimately leading to improved recognition performance. We first evaluate CAM on six standard text recognition benchmarks to demonstrate its effectiveness. Furthermore, CAM exhibits superiority over the state-of-the-art method by an average performance gain of 4.1% across six more challenging datasets, despite utilizing a smaller model size. Our study highlights the importance of incorporating canonical mask guidance and aligned feature refinement techniques for robust scene text recognition. The code is available at https://github.com/MelosY/CAM.

cs.CV↗

arXiv2024

Enhanced Robustness via Loss Engineering in Detuned Non-Hermitian Scattering Systems

Non-Hermitian optics has revealed a series of counterintuitive phenomena with profound implications for sensing, lasing, and light manipulation. While the non-Hermiticity of Hamitonians is well-recognized, recent advancements in non-Hermitian physics have broadened to include scattering matrices, uncovering phenomena such as simultaneous lasing and coherent perfect absorption (CPA), reflectionless scattering modes (RSMs), and coherent chaos control. Despite these developments, the investigation has predominantly focused on static and symmetric configurations, leaving the dynamic properties of non-Hermitian scattering in detuned systems largely unexplored. Bridging this gap, we extend certain stationary non-Hermitian scattering phenomena to detuned systems. We delve into the interplay between bi-directional RSMs and RSM exceptional points (EPs), and elucidate the global existence conditions for RSMs under detuning. Moreover, we introduces a novel category of EPs, characterized by the coalescence of transmission peaks, emerging independent with the presence of Hamiltonian EPs. The transmission EPs (TEPs) exhibit flat-top lineshape and can be extended to a square-shaped spectrum when detuning is involved, accompanied by a distinctive phase transition. Significantly, we demonstrate the applications of the TEPs in a one-dimensional coupled cavity system, engineered to enhance sensing robustness against environmental instabilities such as laser frequency drifts, which can exceed 10 MHz. This capability represents a substantial improvement over traditional sensing methods and an important improvement of fragile EP sensors. Our findings not only contribute to the broader understanding of non-Hermitian scattering phenomena but also paves the way for future advancements in non-Hermitian sensing technologies.

physics.optics↗

arXiv2023

Variation of Tensor Force due to Nuclear Medium Effect

The enhancement of $J^π(T)$=3$^{+}$(0) state with isospin $T=0$ excited by the tensor force in the free $^{6}$Li nucleus has been observed, for the first time, relative to a shrinkable excitation in the $^{6}$Li cluster component inside its host nucleus. Comparatively, the excitation of $J^π(T)$=0$^{+}$(1) state with isospin $T=1$ for these two $^{6}$Li formations take on an approximately equal excitation strength. The mechanism of such tensor force effect was proposed due to the intensive nuclear medium role on isospin $T$=0 state.

nucl-ex↗

arXiv2023

Aspect of Clusters Correlation at Light Nuclei Excited State

The correlation of $αα$ was probed via measuring the transverse momentum $p_{T}$ and width $δp_{T}$ of one $α$, for the first time, which represents the spatial and dynamical essentialities of the initial coupling state in $^{8}$Be nucleus. The weighted interaction vertex of 3$α$ reflected by the magnitudes of their relative momentums and relative emission angles proves the isosceles triangle configuration for 3$α$ at the high excited energy analogous Hoyle states.

nucl-ex↗

arXiv2023

Multi-alpha Boson Gas state in Fusion Evaporation Reaction and Three-body Force

The experimental evidence for the $α$ Boson gas state in the $^{11}$C+$^{12}$C$\rightarrow$$^{23}$Mg$^{\ast}$ fusion evaporation reaction is presented. By measuring the $α$ emission spectrum with multiplicity 2 and 3, we provide insight into the existence of a three-body force among $α$ particles. The observed spectrum exhibited distinct tails corresponding to $α$ particles emitted in pairs and triplets consistent well with the model-calculations of AV18-UX and chiral effective field theory of NV2-3-la*, indicating the formation of $α$ clusters with three-body force in the Boson gas state.

nucl-ex↗

arXiv2023

Unveiling Real Triple Degeneracies in Crystals: Exploring Link and Compound Structures

With their non-Abelian topological charges, real multi-bandgap systems challenge the conventional topological phase classifications. As the minimal sector of multi-bandgap systems, real triple degeneracies (RTPs), which serve as real 'Weyl points', lay the foundation for the research on real topological phases. However, experimental demonstration of physical systems with global band configurations consisting of multiple RTPs in crystals has not been reported. Here we present experimental evidence of RTPs in photonic meta-crystals, characterizing them using the Euler number, and establishing their connection with both Abelian and non-Abelian charges. By considering RTPs as the basic elements, we further propose the concept of a topological compound, akin to a chemical compound, where we find that certain phases are not topologically allowed. The topological classification of RTPs in crystals demonstrated in our work plays a similar role as the 'no-go' theorem in Weyl systems.

cond-mat.mes-hall↗

arXiv2023

Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks on Label-Free Data

In this paper, we propose a feature affinity (FA) assisted knowledge distillation (KD) method to improve quantization-aware training of deep neural networks (DNN). The FA loss on intermediate feature maps of DNNs plays the role of teaching middle steps of a solution to a student instead of only giving final answers in the conventional KD where the loss acts on the network logits at the output level. Combining logit loss and FA loss, we found that the quantized student network receives stronger supervision than from the labeled ground-truth data. The resulting FAQD is capable of compressing model on label-free data, which brings immediate practical benefits as pre-trained teacher models are readily available and unlabeled data are abundant. In contrast, data labeling is often laborious and expensive. Finally, we propose a fast feature affinity (FFA) loss that accurately approximates FA loss with a lower order of computational complexity, which helps speed up training for high resolution image input.

cs.LG↗