arXiv subjects

Chao Li

Publications and source records attributed to Chao Li.

At least 199 records · Page 11Linked to original sources

arXiv2025

Score-based Diffusion Model for Unpaired Virtual Histology Staining

Hematoxylin and eosin (H&E) staining visualizes histology but lacks specificity for diagnostic markers. Immunohistochemistry (IHC) staining provides protein-targeted staining but is restricted by tissue availability and antibody specificity. Virtual staining, i.e., computationally translating the H&E image to its IHC counterpart while preserving the tissue structure, is promising for efficient IHC generation. Existing virtual staining methods still face key challenges: 1) effective decomposition of staining style and tissue structure, 2) controllable staining process adaptable to diverse tissue and proteins, and 3) rigorous structural consistency modelling to handle the non-pixel-aligned nature of paired H&E and IHC images. This study proposes a mutual-information (MI)-guided score-based diffusion model for unpaired virtual staining. Specifically, we design 1) a global MI-guided energy function that disentangles the tissue structure and staining characteristics across modalities, 2) a novel timestep-customized reverse diffusion process for precise control of the staining intensity and structural reconstruction, and 3) a local MI-driven contrastive learning strategy to ensure the cellular level structural consistency between H&E-IHC images. Extensive experiments demonstrate the our superiority over state-of-the-art approaches, highlighting its biomedical potential. Codes will be open-sourced upon acceptance.

eess.IV↗

arXiv2025

Morse: Dual-Sampling for Lossless Acceleration of Diffusion Models

In this paper, we present Morse, a simple dual-sampling framework for accelerating diffusion models losslessly. The key insight of Morse is to reformulate the iterative generation (from noise to data) process via taking advantage of fast jump sampling and adaptive residual feedback strategies. Specifically, Morse involves two models called Dash and Dot that interact with each other. The Dash model is just the pre-trained diffusion model of any type, but operates in a jump sampling regime, creating sufficient space for sampling efficiency improvement. The Dot model is significantly faster than the Dash model, which is learnt to generate residual feedback conditioned on the observations at the current jump sampling point on the trajectory of the Dash model, lifting the noise estimate to easily match the next-step estimate of the Dash model without jump sampling. By chaining the outputs of the Dash and Dot models run in a time-interleaved fashion, Morse exhibits the merit of flexibly attaining desired image generation performance while improving overall runtime efficiency. With our proposed weight sharing strategy between the Dash and Dot models, Morse is efficient for training and inference. Our method shows a lossless speedup of 1.78X to 3.31X on average over a wide range of sampling step budgets relative to 9 baseline diffusion models on 6 image generation tasks. Furthermore, we show that our method can be also generalized to improve the Latent Consistency Model (LCM-SDXL, which is already accelerated with consistency distillation technique) tailored for few-step text-to-image synthesis. The code and models are available at https://github.com/deep-optimization/Morse.

cs.GR↗

arXiv2025

A Kinematic Constraint on Pedestrian Walking: Power-law Scaling between Critical Angular Velocity and Speed

This paper presents a statistical analysis of speed and angular velocity obtained from pedestrian experiments across nine distinct datasets. Experimental scenarios included crossing motion, unidirectional/bidirectional flows, bidirectional/four-directional crossing flows, pedestrian-vehicle interactions, unidirectional flow in a circular corridor, and circle antipode configurations. We applied filtering methods to reduce noise and analyzed the data at different sampling frequencies. The results reveal a universal power-law scaling between critical angular velocity and speed, with a scaling exponent of approximately -0.8. This relationship defines a bounded region in the speed-angular velocity phase space, suggesting a kinematic constraint on pedestrian motion.

physics.soc-ph↗

arXiv2025

HieraEdgeNet: A Multi-Scale Edge-Enhanced Framework for Automated Pollen Recognition

Automated pollen recognition is vital to paleoclimatology, biodiversity monitoring, and public health, yet conventional methods are hampered by inefficiency and subjectivity. Existing deep learning models often struggle to achieve the requisite localization accuracy for microscopic targets like pollen, which are characterized by their minute size, indistinct edges, and complex backgrounds. To overcome this limitation, we introduce HieraEdgeNet, a multi-scale edge-enhancement framework. The framework's core innovation is the introduction of three synergistic modules: the Hierarchical Edge Module (HEM), which explicitly extracts a multi-scale pyramid of edge features that corresponds to the semantic hierarchy at early network stages; the Synergistic Edge Fusion (SEF) module, for deeply fusing these edge priors with semantic information at each respective scale; and the Cross Stage Partial Omni-Kernel Module (CSPOKM), which maximally refines the most detail-rich feature layers using an Omni-Kernel operator - comprising anisotropic large-kernel convolutions and mixed-domain attention - all within a computationally efficient Cross-Stage Partial (CSP) framework. On a large-scale dataset comprising 120 pollen classes, HieraEdgeNet achieves a mean Average Precision (mAP@.5) of 0.9501, significantly outperforming state-of-the-art baseline models such as YOLOv12n and RT-DETR. Furthermore, qualitative analysis confirms that our approach generates feature representations that are more precisely focused on object boundaries. By systematically integrating edge information, HieraEdgeNet provides a robust and powerful solution for high-precision, high-efficiency automated detection of microscopic objects.

cs.CV↗

arXiv2025

Seed-Coder: Let the Code Model Curate Data for Itself

Code data in large language model (LLM) pretraining is recognized crucial not only for code-related tasks but also for enhancing general intelligence of LLMs. Current open-source LLMs often heavily rely on human effort to produce their code pretraining data, such as employing hand-crafted filtering rules tailored to individual programming languages, or using human-annotated data to train quality filters. However, these approaches are inherently limited in scalability, prone to subjective biases, and costly to extend and maintain across diverse programming languages. To address these challenges, we introduce Seed-Coder, a series of open-source LLMs comprising base, instruct and reasoning models of 8B size, minimizing human involvement in data construction. Our code pretraining data is produced by a model-centric data pipeline, which predominantly leverages LLMs for scoring and filtering code data. The instruct model is further trained via supervised fine-tuning and preference optimization, and the reasoning model leverages Long-Chain-of-Thought (LongCoT) reinforcement learning to improve multi-step code reasoning. Seed-Coder achieves state-of-the-art results among open-source models of similar size and even surpasses some much larger models, demonstrating superior performance in code generation, code completion, code editing, code reasoning, and software engineering tasks.

cs.CL↗

arXiv2025

Weiss monotonicity and capillary hypersurfaces

Previous work of the authors established the rigorous limiting behavior of minimizing capillary surfaces to minimizers of the Alt--Caffarelli functional as the capillary angle tends to zero. We prove here that in this limit, the capillary area-density converges to the Weiss energy density. We apply this to obtain angle-independent curvature estimates and regularity results for capillary minimizers.

math.AP↗

arXiv2025

Hunyuan-Game: Industrial-grade Intelligent Game Creation Model

Intelligent game creation represents a transformative advancement in game development, utilizing generative artificial intelligence to dynamically generate and enhance game content. Despite notable progress in generative models, the comprehensive synthesis of high-quality game assets, including both images and videos, remains a challenging frontier. To create high-fidelity game content that simultaneously aligns with player preferences and significantly boosts designer efficiency, we present Hunyuan-Game, an innovative project designed to revolutionize intelligent game production. Hunyuan-Game encompasses two primary branches: image generation and video generation. The image generation component is built upon a vast dataset comprising billions of game images, leading to the development of a group of customized image generation models tailored for game scenarios: (1) General Text-to-Image Generation. (2) Game Visual Effects Generation, involving text-to-effect and reference image-based game visual effect generation. (3) Transparent Image Generation for characters, scenes, and game visual effects. (4) Game Character Generation based on sketches, black-and-white images, and white models. The video generation component is built upon a comprehensive dataset of millions of game and anime videos, leading to the development of five core algorithmic models, each targeting critical pain points in game development and having robust adaptation to diverse game video scenarios: (1) Image-to-Video Generation. (2) 360 A/T Pose Avatar Video Synthesis. (3) Dynamic Illustration Generation. (4) Generative Video Super-Resolution. (5) Interactive Game Video Generation. These image and video generation models not only exhibit high-level aesthetic expression but also deeply integrate domain-specific knowledge, establishing a systematic understanding of diverse game and anime art styles.

cs.CV↗

arXiv2025

DeFeed: Secure Decentralized Cross-Contract Data Feed in Web 3.0 for Connected Autonomous Vehicles

Smart contracts have been a topic of interest in blockchain research and are a key enabling technology for Connected Autonomous Vehicles (CAVs) in the era of Web 3.0. These contracts enable trustless interactions without the need for intermediaries, as they operate based on predefined rules encoded on the blockchain. However, smart contacts face significant challenges in cross-contract communication and information sharing, making it difficult to establish seamless connectivity and collaboration among CAVs with Web 3.0. In this paper, we propose DeFeed, a novel secure protocol that incorporates various gas-saving functions for CAVs, originated from in-depth research into the interaction among smart contracts for decentralized cross-contract data feed in Web 3.0. DeFeed allows smart contracts to obtain information from other contracts efficiently in a single click, without complicated operations. We judiciously design and complete various functions with DeFeed, including a pool function and a cache function for gas optimization, a subscribe function for facilitating data access, and an update function for the future iteration of our protocol. Tailored for CAVs with Web 3.0 use cases, DeFeed enables efficient data feed between smart contracts underpinning decentralized applications and vehicle coordination. Implemented and tested on the Ethereum official test network, DeFeed demonstrates significant improvements in contract interaction efficiency, reducing computational complexity and gas costs. Our solution represents a critical step towards seamless, decentralized communication in Web 3.0 ecosystems.

cs.CR↗

arXiv2025

Adaptive Spatial Transcriptomics Interpolation via Cross-modal Cross-slice Modeling

Spatial transcriptomics (ST) is a promising technique that characterizes the spatial gene profiling patterns within the tissue context. Comprehensive ST analysis depends on consecutive slices for 3D spatial insights, whereas the missing intermediate tissue sections and high costs limit the practical feasibility of generating multi-slice ST. In this paper, we propose C2-STi, the first attempt for interpolating missing ST slices at arbitrary intermediate positions between adjacent ST slices. Despite intuitive, effective ST interpolation presents significant challenges, including 1) limited continuity across heterogeneous tissue sections, 2) complex intrinsic correlation across genes, and 3) intricate cellular structures and biological semantics within each tissue section. To mitigate these challenges, in C2-STi, we design 1) a distance-aware local structural modulation module to adaptively capture cross-slice deformations and enhance positional correlations between ST slices, 2) a pyramid gene co-expression correlation module to capture multi-scale biological associations among genes, and 3) a cross-modal alignment module that integrates the ST-paired hematoxylin and eosin (H&E)-stained images to filter and align the essential cellular features across ST and H\&E images. Extensive experiments on the public dataset demonstrate our superiority over state-of-the-art approaches on both single-slice and multi-slice ST interpolation. Codes are available at https://github.com/XiaofeiWang2018/C2-STi.

eess.IV↗

arXiv2025

Order within disorder: spectral key generation and distribution in random lasers

In secure communication, highly random entropy sources are essential for information security. Random lasers (RLs), which arise from multiple scattering in disordered structures, are potentially ideal entropy sources. Traditionally, RLs are viewed as disordered and unpredictable. However, in this work, we present novel evidence that orderly patterns exist beneath the seemingly disordered outputs of RLs. Utilizing deep learning techniques, a variety of advanced neural network models are used to analyze the spectral data in multiple dimensions. The results show that the time series of RLs spectra are unpredictable, but spectral wavelength component intensities can be recovered due to inter-modal correlations. This finding not only breaks through the traditional perception that RLs are unpredictable, but also reveals for the first time that RLs have the dual characteristics of both randomness and determinism. Based on this new characteristic, we further expand the application field of RLs and innovatively design a new type of key generation and distribution scheme. In this scheme, the disordered property of RLs is used for key generation to ensure high randomness, while their ordered property is used for key distribution to guarantee accuracy and reliability. The scheme provides a new strategy for secure communication.

physics.optics↗

arXiv2025

DPNet: Dynamic Pooling Network for Tiny Object Detection

In unmanned aerial systems, especially in complex environments, accurately detecting tiny objects is crucial. Resizing images is a common strategy to improve detection accuracy, particularly for small objects. However, simply enlarging images significantly increases computational costs and the number of negative samples, severely degrading detection performance and limiting its applicability. This paper proposes a Dynamic Pooling Network (DPNet) for tiny object detection to mitigate these issues. DPNet employs a flexible down-sampling strategy by introducing a factor (df) to relax the fixed downsampling process of the feature map to an adjustable one. Furthermore, we design a lightweight predictor to predict df for each input image, which is used to decrease the resolution of feature maps in the backbone. Thus, we achieve input-aware downsampling. We also design an Adaptive Normalization Module (ANM) to make a unified detector compatible with different dfs. A guidance loss supervises the predictor's training. DPNet dynamically allocates computing resources to trade off between detection accuracy and efficiency. Experiments on the TinyCOCO and TinyPerson datasets show that DPNet can save over 35% and 25% GFLOPs, respectively, while maintaining comparable detection performance. The code will be made publicly available.

cs.CV↗

arXiv2025

Nanophotonic waveguide chip-to-free-space beam scanning at 68 Million Spots/(s$\cdot$mm$^{2}$)

A seamless chip-to-world photonic interface enables wide-ranging advancements in optical ranging, display, communication, computation, imaging, and light-matter interaction. An optimal solution allows for 2D scanning of a diffraction-limited beam from anywhere on a photonic chip over a large number of beam-spots in free-space. Currently, devices with direct PIC integration rely on tiled apertures with poor mode qualities, large footprints, and complex control systems. Micro-mechanical beam scanners have good beam quality but lack direct PIC integration and are inertially-limited due to the use of bulk optical components or structures in which the optical aperture and actuator sizes are inextricably linked, resulting in trade-offs among resolution, speed, and footprint. Here, we overcome these limitations with the photonic "ski-jump": a nanoscale optical waveguide monolithically integrated atop a piezoelectrically actuated cantilever which passively curls ~90$^{\circ}$ out-of-plane in a footprint of <0.1 mm$^{2}$, emits sub-micron diffraction-limited optical modes, and exhibits kHz-rate mechanical resonances with quality factors exceeding 10,000. This enables two-dimensional beam-scanning with footprint-adjusted spot-rates of 68.6 mega-spots/(s$\cdot$mm$^{2}$) at CMOS-level voltages, which is equivalent to a 1 megapixel display at 100 Hz from a 1.5 mm$^{2}$ footprint, and exceeds the performance of state-of-the-art MEMS mirrors by >50$\times$. Using this device, we demonstrate image projection, video projection, and the initialization and readout of single photons from silicon vacancy centers in diamond waveguides. Based on current performance, we identify pathways for achieving >1 giga-spots at kHz-rates in a ~1 cm$^{2}$ area to provide a seamless, scalable optical pipeline between integrated photonic processors and the free-space world.

physics.optics↗

arXiv2025

Group Relative Knowledge Distillation: Learning from Teacher's Relational Inductive Bias

Knowledge distillation typically transfers knowledge from a teacher model to a student model by minimizing differences between their output distributions. However, existing distillation approaches largely focus on mimicking absolute probabilities and neglect the valuable relational inductive biases embedded in the teacher's relative predictions, leading to exposure bias. In this paper, we propose Group Relative Knowledge Distillation (GRKD), a novel framework that distills teacher knowledge by learning the relative ranking among classes, rather than directly fitting the absolute distribution. Specifically, we introduce a group relative loss that encourages the student model to preserve the pairwise preference orderings provided by the teacher's outputs. Extensive experiments on classification benchmarks demonstrate that GRKD achieves superior generalization compared to existing methods, especially in tasks requiring fine-grained class differentiation. Our method provides a new perspective on exploiting teacher knowledge, focusing on relational structure rather than absolute likelihood.

cs.LG↗

arXiv2025

Hierarchical Attention Generates Better Proofs

Large language models (LLMs) have shown promise in formal theorem proving, but their token-level processing often fails to capture the inherent hierarchical nature of mathematical proofs. We introduce \textbf{Hierarchical Attention}, a regularization method that aligns LLMs' attention mechanisms with mathematical reasoning structures. Our approach establishes a five-level hierarchy from foundational elements to high-level concepts, ensuring structured information flow in proof generation. Experiments demonstrate that our method improves proof success rates by 2.05\% on miniF2F and 1.69\% on ProofNet while reducing proof complexity by 23.81\% and 16.50\% respectively. The code is available at https://github.com/Car-pe/HAGBP.

cs.LG↗

arXiv2025

Imaging for All-Day Wearable Smart Glasses

In recent years smart glasses technology has rapidly advanced, opening up entirely new areas for mobile computing. We expect future smart glasses will need to be all-day wearable, adopting a small form factor to meet the requirements of volume, weight, fashionability and social acceptability, which puts significant constraints on the space of possible solutions. Additional challenges arise due to the fact that smart glasses are worn in arbitrary environments while their wearer moves and performs everyday activities. In this paper, we systematically analyze the space of imaging from smart glasses and derive several fundamental limits that govern this imaging domain. We discuss the impact of these limits on achievable image quality and camera module size -- comparing in particular to related devices such as mobile phones. We then propose a novel distributed imaging approach that allows to minimize the size of the individual camera modules when compared to a standard monolithic camera design. Finally, we demonstrate the properties of this novel approach in a series of experiments using synthetic data as well as images captured with two different prototype implementations.

cs.CV↗

arXiv2025

Significant tuning of dispersive mode coupling in doubly clamped MEMS beam resonators using thermally induced buckling effect

Dispersive mode coupling is a promising mechanism for the development of advanced micro/nanoelectromechanical devices. However, strong coupling strength remains a key challenge limiting the practical applications of dispersive mode coupling effect. Here, we experimentally demonstrate the significant tuning of the mode coupling coefficient of two flexural vibrational modes in a doubly-clamped MEMS beam resonator using thermally-induced buckling effect, which enables variable coupling strengths to be implemented for practical applications. Furthermore, a theoretical model is developed to describe the mode coupling coefficient, showing that the tunability is owing to the breakdown of the symmetric shape of the MEMS beam caused by buckling. Moreover, the theoretical model defines a simple relation between the coupling coefficient and the nonlinearity of the two coupled modes. These results provide valuable insight into physical mechanisms underlying dispersive mode coupling effect, as well as pave the way for the development of advanced MEMS devices with application-specified mode coupling strength.

physics.app-ph↗

arXiv2025

Content-Distortion High-Order Interaction for Blind Image Quality Assessment

The content and distortion are widely recognized as the two primary factors affecting the visual quality of an image. While existing No-Reference Image Quality Assessment (NR-IQA) methods have modeled these factors, they fail to capture the complex interactions between content and distortions. This shortfall impairs their ability to accurately perceive quality. To confront this, we analyze the key properties required for interaction modeling and propose a robust NR-IQA approach termed CoDI-IQA (Content-Distortion high-order Interaction for NR-IQA), which aggregates local distortion and global content features within a hierarchical interaction framework. Specifically, a Progressive Perception Interaction Module (PPIM) is proposed to explicitly simulate how content and distortions independently and jointly influence image quality. By integrating internal interaction, coarse interaction, and fine interaction, it achieves high-order interaction modeling that allows the model to properly represent the underlying interaction patterns. To ensure sufficient interaction, multiple PPIMs are employed to hierarchically fuse multi-level content and distortion features at different granularities. We also tailor a training strategy suited for CoDI-IQA to maintain interaction stability. Extensive experiments demonstrate that the proposed method notably outperforms the state-of-the-art methods in terms of prediction accuracy, data efficiency, and generalization ability.

cs.CV↗

arXiv2025

Improved regularity for minimizing capillary hypersurfaces

We give improved estimates for the size of the singular set of minimizing capillary hypersurfaces: the singular set is always of codimension at least $4$, and this estimate improves if the capillary angle is close to $0$, $\fracπ{2}$, or $π$. For capillary angles that are close to $0$ or $π$, our analysis is based on a rigorous connection between the capillary problem and the one-phase Bernoulli problem.

math.DG↗