arXiv subjects

Yao Yao

Publications and source records attributed to Yao Yao.

At least 91 records · Page 5Linked to original sources

arXiv2025

Enhanced Quantum Parameter Estimation via Dynamical Modulation

In quantum theory, the inescapable interaction between a system and its surroundings would lead to a loss of coherence and leakage of information into the environment. An effective approach to retain the quantum characteristics of the system is to decouple it from the environment. However, things get complicated in quantum parameter estimation tasks, especially when the unknown parameter originates from the environment. Here, we propose a general dynamical modulation scheme that enables the enhancement of estimation precision irrespective of the origin of the parameters to be estimated. Notably, beyond the capability of dynamically decoupling the system from the environment, our proposal can select the effective frequency of the system and in turn manipulate the dynamics of the system, such as the steady-state probability and the decay rate, which are sensitive to the bath parameter. Therefore, the quantum Fisher information is dramatically increased, leading to superior estimation precision. Specifically, we elucidate the effectiveness of our proposal with prototypical examples of the Ramsey spectroscopy and quantum thermometer. Our findings offer an alternative route to enhance the precision of quantum estimation processes and may have potential applications in diverse branches of quantum metrology.

quant-ph↗

arXiv2025

Quantum Discord Witness With Uncharacterized Devices

Quantum discord represents a correlation beyond classicality that could be useful for many quantum information tasks, and therefore is viewed as a valuable quantum resource. Theoretically, whether a bipartite quantum state has a non-zero amount of quantum discord or not can be determined once its density matrix is given. Experimentally, however, it is not easy to perform a reliable tomography on the state, especially when considering the imperfection of devices and the high dimensionality of system. Here, inspired by the so-called dimension witness, we propose a new approach using uncharacterized measurements to witness quantum discord of an unknown bipartite state within arbitrary dimension system. Furthermore, $2 \times 2$ measurements are sufficient for any bipartite state of arbitrarily large dimension. For any two-qubit state, we show that the maximum of witness happens when one performs mutually orthogonal basis measurement on each qubit. Our method exhibits high robustness against device imperfections, such as error tolerance, indicating its experimental feasibility.

quant-ph↗

arXiv2025

TOPIC: A Parallel Association Paradigm for Multi-Object Tracking under Complex Motions and Diverse Scenes

Video data and algorithms have been driving advances in multi-object tracking (MOT). While existing MOT datasets focus on occlusion and appearance similarity, complex motion patterns are widespread yet overlooked. To address this issue, we introduce a new dataset called BEE24 to highlight complex motions. Identity association algorithms have long been the focus of MOT research. Existing trackers can be categorized into two association paradigms: single-feature paradigm (based on either motion or appearance feature) and serial paradigm (one feature serves as secondary while the other is primary). However, these paradigms are incapable of fully utilizing different features. In this paper, we propose a parallel paradigm and present the Two rOund Parallel matchIng meChanism (TOPIC) to implement it. The TOPIC leverages both motion and appearance features and can adaptively select the preferable one as the assignment metric based on motion level. Moreover, we provide an Attention-based Appearance Reconstruction Module (AARM) to reconstruct appearance feature embeddings, thus enhancing the representation of appearance features. Comprehensive experiments show that our approach achieves state-of-the-art performance on four public datasets and BEE24. Moreover, BEE24 challenges existing trackers to track multiple similar-appearing small objects with complex motions over long periods, which is critical in real-world applications such as beekeeping and drone swarm surveillance. Notably, our proposed parallel paradigm surpasses the performance of existing association paradigms by a large margin, e.g., reducing false negatives by 6% to 81% compared to the single-feature association paradigm. The introduced dataset and association paradigm in this work offer a fresh perspective for advancing the MOT field. The source code and dataset are available at https://github.com/holmescao/TOPICTrack.

cs.CV↗

arXiv2024

AlphaFolding: 4D Diffusion for Dynamic Protein Structure Prediction with Reference and Motion Guidance

Protein structure prediction is pivotal for understanding the structure-function relationship of proteins, advancing biological research, and facilitating pharmaceutical development and experimental design. While deep learning methods and the expanded availability of experimental 3D protein structures have accelerated structure prediction, the dynamic nature of protein structures has received limited attention. This study introduces an innovative 4D diffusion model incorporating molecular dynamics (MD) simulation data to learn dynamic protein structures. Our approach is distinguished by the following components: (1) a unified diffusion model capable of generating dynamic protein structures, including both the backbone and side chains, utilizing atomic grouping and side-chain dihedral angle predictions; (2) a reference network that enhances structural consistency by integrating the latent embeddings of the initial 3D protein structures; and (3) a motion alignment module aimed at improving temporal structural coherence across multiple time steps. To our knowledge, this is the first diffusion-based model aimed at predicting protein trajectories across multiple time steps simultaneously. Validation on benchmark datasets demonstrates that our model exhibits high accuracy in predicting dynamic 3D structures of proteins containing up to 256 amino acids over 32 time steps, effectively capturing both local flexibility in stable states and significant conformational changes. URL: https://fudan-generative-vision.github.io/AlphaFolding/#/

cs.LG↗

arXiv2024

MCMat: Multiview-Consistent and Physically Accurate PBR Material Generation

Existing 2D methods utilize UNet-based diffusion models to generate multi-view physically-based rendering (PBR) maps but struggle with multi-view inconsistency, while some 3D methods directly generate UV maps, encountering generalization issues due to the limited 3D data. To address these problems, we propose a two-stage approach, including multi-view generation and UV materials refinement. In the generation stage, we adopt a Diffusion Transformer (DiT) model to generate PBR materials, where both the specially designed multi-branch DiT and reference-based DiT blocks adopt a global attention mechanism to promote feature interaction and fusion between different views, thereby improving multi-view consistency. In addition, we adopt a PBR-based diffusion loss to ensure that the generated materials align with realistic physical principles. In the refinement stage, we propose a material-refined DiT that performs inpainting in empty areas and enhances details in UV space. Except for the normal condition, this refinement also takes the material map from the generation stage as an additional condition to reduce the learning difficulty and improve generalization. Extensive experiments show that our method achieves state-of-the-art performance in texturing 3D objects with PBR materials and provides significant advantages for graphics relighting applications. Project Page: https://lingtengqiu.github.io/2024/MCMat/

cs.CV↗

arXiv2024

A parameter-free statistical model for two-dimensional carbon nanostructures

Energy degeneracy in physical systems may be induced by symmetries of the Hamiltonian, and the resonance of degeneracy states in carbon nanostructures can effectively enhance the stability of the system. Combining the octet rule, we introduce a parameter-free statistical model to determine the physical properties by lifting the energy degeneracy in carbon nanostructures. This model offers a direct path to accurately ascertain electron density distributions in quantum systems, akin to how charge density is used in density functional theory to deduce system properties. Our methodology diverges from traditional quantum mechanics, focusing instead on this unique statistical model by minimizing bonding free energy to determine the fundamental properties of materials. Applied to carbon nanoclusters and graphynes, our model not only precisely predicts bonding energies and electron density without relying on external parameters, but also enhances the prediction of electronic structures through bond occupancy numbers, which act as effective hopping integrals. This innovation offers insights into the structural properties and quantum behavior of electrons across various dimensions.

cond-mat.mes-hall↗

arXiv2024

JEN-1 Composer: A Unified Framework for High-Fidelity Multi-Track Music Generation

With rapid advances in generative artificial intelligence, the text-to-music synthesis task has emerged as a promising direction for music generation. Nevertheless, achieving precise control over multi-track generation remains an open challenge. While existing models excel in directly generating multi-track mix, their limitations become evident when it comes to composing individual tracks and integrating them in a controllable manner. This departure from the typical workflows of professional composers hinders the ability to refine details in specific tracks. To address this gap, we propose JEN-1 Composer, a unified framework designed to efficiently model marginal, conditional, and joint distributions over multi-track music using a single model. Building upon an audio latent diffusion model, JEN-1 Composer extends the versatility of multi-track music generation. We introduce a progressive curriculum training strategy, which gradually escalates the difficulty of training tasks while ensuring the model's generalization ability and facilitating smooth transitions between different scenarios. During inference, users can iteratively generate and select music tracks, thus incrementally composing entire musical pieces in accordance with the Human-AI co-composition workflow. Our approach demonstrates state-of-the-art performance in controllable and high-fidelity multi-track music synthesis, marking a significant advancement in interactive AI-assisted music creation. Our demo pages are available at www.jenmusic.ai/research.

cs.SD↗

arXiv2024

Suppression of chemotactic singularity by buoyancy

Chemotactic singularity formation in the context of the Patlak-Keller-Segel equation is an extensively studied phenomenon. In recent years, it has been shown that the presence of fluid advection can arrest the singularity formation given that the fluid flow possesses mixing or diffusion enhancing properties and its amplitude is sufficiently strong - this effect is conjectured to hold for more general classes of nonlinear PDEs. In this paper, we consider the Patlak-Keller-Segel equation coupled with a fluid flow that obeys Darcy's law for incompressible porous media via buoyancy force. We prove that in contrast with passive advection, this active fluid coupling is capable of suppressing singularity formation at arbitrary small coupling strength: namely, the system always has globally regular solutions.

math.AP↗

arXiv2024

4D SlingBAG: spatial-temporal coupled Gaussian ball for large-scale dynamic 3D photoacoustic iterative reconstruction

Large-scale dynamic three-dimensional (3D) photoacoustic imaging (PAI) is significantly important in clinical applications. In practical implementations, large-scale 3D real-time PAI systems typically utilize sparse two-dimensional (2D) sensor arrays with certain angular deficiencies, necessitating advanced iterative reconstruction (IR) algorithms to achieve quantitative PAI and reduce reconstruction artifacts. However, for existing IR algorithms, multi-frame 3D reconstruction leads to extremely high memory consumption and prolonged computation time, with limited consideration of the spatial-temporal continuity between data frames. Here, we propose a novel method, named the 4D sliding Gaussian ball adaptive growth (4D SlingBAG) algorithm, based on the current point cloud-based IR algorithm sliding Gaussian ball adaptive growth (SlingBAG), which has minimal memory consumption among IR methods. Our 4D SlingBAG method applies spatial-temporal coupled deformation functions to each Gaussian sphere in point cloud, thus explicitly learning the deformations features of the dynamic 3D PA scene. This allows for the efficient representation of various physiological processes (such as pulsation) or external pressures (e.g., blood perfusion experiments) contributing to changes in vessel morphology and blood flow during dynamic 3D PAI, enabling highly efficient IR for dynamic 3D PAI. Simulation experiments demonstrate that 4D SlingBAG achieves high-quality dynamic 3D PA reconstruction. Compared to performing reconstructions by using SlingBAG algorithm individually for each frame, our method significantly reduces computational time and keeps a extremely low memory consumption. The project for 4D SlingBAG can be found in the following GitHub repository: \href{https://github.com/JaegerCQ/4D-SlingBAG}{https://github.com/JaegerCQ/4D-SlingBAG}.

cs.CV↗

arXiv2024

A Note on Complexity for Two Classes of Structured Non-Smooth Non-Convex Compositional Optimization

This note studies numerical methods for solving compositional optimization problems, where the inner function is smooth, and the outer function is Lipschitz continuous, non-smooth, and non-convex but exhibits one of two special structures that enable the design of efficient first-order methods. In the first structure, the outer function allows for an easily solvable proximal mapping. We demonstrate that, in this case, a smoothing compositional gradient method can find a $(δ,ε)$-stationary point--specifically defined for compositional optimization--in $O(1/(δε^2))$ iterations. In the second structure, the outer function is expressed as a difference-of-convex function, where each convex component is simple enough to allow an efficiently solvable proximal linear subproblem. In this case, we show that a prox-linear method can find a nearly $ε$-critical point in $O(1/ε^2)$ iterations.

math.OC↗

arXiv2024

Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption

Large Language Models (LLMs), epitomized by ChatGPT's release in late 2022, have revolutionized various industries with their advanced language comprehension. However, their efficiency is challenged by the Transformer architecture's struggle with handling long texts. KV Cache has emerged as a pivotal solution to this issue, converting the time complexity of token generation from quadratic to linear, albeit with increased GPU memory overhead proportional to conversation length. With the development of the LLM community and academia, various KV Cache compression methods have been proposed. In this review, we dissect the various properties of KV Cache and elaborate on various methods currently used to optimize the KV Cache space usage of LLMs. These methods span the pre-training phase, deployment phase, and inference phase, and we summarize the commonalities and differences among these methods. Additionally, we list some metrics for evaluating the long-text capabilities of large language models, from both efficiency and capability perspectives. Our review thus sheds light on the evolving landscape of LLM optimization, offering insights into future advancements in this dynamic field. Links to the papers mentioned in this review can be found in our Github Repo https://github.com/zcli-charlie/Awesome-KV-Cache.

cs.CL↗

arXiv2024

Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models

Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and Parameter-Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting LLMs to downstream tasks. ICL typically constructs a few-shot learning scenario, either manually or by setting up a Retrieval-Augmented Generation (RAG) system, helping models quickly grasp domain knowledge or question-answering patterns without changing model parameters. However, this approach involves trade-offs, such as slower inference speed and increased space occupancy. PEFT assists the model in adapting to tasks through minimal parameter modifications, but the training process still demands high hardware requirements, even with a small number of parameters involved. To address these challenges, we propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning, maintaining low inference costs. RTD constructs a reference datastore from the provided training examples and optimizes the LLM's final vocabulary distribution by flexibly selecting suitable references based on the input, resulting in more trustable responses and enabling the model to adapt to downstream tasks at a low cost. Experimental evaluations on various LLMs using different benchmarks demonstrate that RTD establishes a new paradigm for augmenting models to downstream tasks. Furthermore, our method exhibits strong orthogonality with traditional methods, allowing for concurrent usage. Our code can be found at https://github.com/ShiLuohe/ReferenceTrustableDecoding

cs.CL↗

arXiv2024

Size Growth on Short Timescales of Star-Forming Galaxies: Insights from Size Variation with Rest-Frame Wavelength with JADES

We investigate size variation with rest-frame wavelength for star-forming galaxies based on the second JWST Advanced Deep Extragalactic Survey data release. Star-forming galaxies are typically smaller at longer wavelength from UV-to-NIR at $z<3.5$, especially for more massive galaxies, indicating the inside-out assembly with in-situ star formation if ignoring dust attenuation. The size variation with wavelength shows strong dependence on stellar mass, and shows little or no dependence on redshift, specific star formation rate and galaxy environment. This suggests that the size growth of star-forming galaxies is a self-regulated process primarily governed by stellar mass. We model size as a function of both mass and redshift simultaneously, obtaining $R_{\rm e} \propto M_*^{0.23} (1+z)^{-1.04}$ at a wavelength of 0.45 ${μ\mathrm{m}}$, and $R_{\rm e} \propto M_*^{0.20} (1+z)^{-1.08}$ at 1.0 ${μ\mathrm{m}}$. Based on this size evolution and the star formation main sequence from the literature, we obtain the locus of typical size growth for individual galaxies of different masses on the mass-size plane. The moving trend of galaxies on the mass-size plane, which indicates the slopes of their locus, strongly correlates with the size ratio between 0.45 ${μ\mathrm{m}}$ and 1.0 ${μ\mathrm{m}}$, supporting the idea that the size variation with wavelength provides important information on size growth of galaxies on short timescales.

astro-ph.GA↗

arXiv2024

Sliding Gaussian ball adaptive growth (SlingBAG): point cloud-based iterative algorithm for large-scale 3D photoacoustic imaging

Large-scale 3D photoacoustic (PA) imaging has become increasingly important for both clinical and pre-clinical applications. Limited by cost and system complexity, only systems with sparsely-distributed sensors can be widely implemented, which desires advanced reconstruction algorithms to reduce artifacts. However, high computing memory and time consumption of traditional iterative reconstruction (IR) algorithms is practically unacceptable for large-scale 3D PA imaging. Here, we propose a point cloud-based IR algorithm that reduces memory consumption by several orders, wherein the 3D PA scene is modeled as a series of Gaussian-distributed spherical sources stored in form of point cloud. During the IR process, not only are properties of each Gaussian source, including its peak intensity (initial pressure value), standard deviation (size) and mean (position) continuously optimized, but also each Gaussian source itself adaptively undergoes destroying, splitting, and duplication along the gradient direction. This method, named the sliding Gaussian ball adaptive growth (SlingBAG) algorithm, enables high-quality large-scale 3D PA reconstruction with fast iteration and extremely low memory usage. We validated SlingBAG algorithm in both simulation study and in vivo animal experiments. The source code and data for SlingBAG, along with supplementary materials and demonstration videos, are now available in the following GitHub repository: https://github.com/JaegerCQ/SlingBAG.

cs.CV↗

arXiv2024

Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation

Recent advances in latent diffusion-based generative models for portrait image animation, such as Hallo, have achieved impressive results in short-duration video synthesis. In this paper, we present updates to Hallo, introducing several design enhancements to extend its capabilities. First, we extend the method to produce long-duration videos. To address substantial challenges such as appearance drift and temporal artifacts, we investigate augmentation strategies within the image space of conditional motion frames. Specifically, we introduce a patch-drop technique augmented with Gaussian noise to enhance visual consistency and temporal coherence over long duration. Second, we achieve 4K resolution portrait video generation. To accomplish this, we implement vector quantization of latent codes and apply temporal alignment techniques to maintain coherence across the temporal dimension. By integrating a high-quality decoder, we realize visual synthesis at 4K resolution. Third, we incorporate adjustable semantic textual labels for portrait expressions as conditional inputs. This extends beyond traditional audio cues to improve controllability and increase the diversity of the generated content. To the best of our knowledge, Hallo2, proposed in this paper, is the first method to achieve 4K resolution and generate hour-long, audio-driven portrait image animations enhanced with textual prompts. We have conducted extensive experiments to evaluate our method on publicly available datasets, including HDTF, CelebV, and our introduced "Wild" dataset. The experimental results demonstrate that our approach achieves state-of-the-art performance in long-duration portrait video animation, successfully generating rich and controllable content at 4K resolution for duration extending up to tens of minutes. Project page https://fudan-generative-vision.github.io/hallo2

cs.CV↗

arXiv2024

Towards Native Generative Model for 3D Head Avatar

Creating 3D head avatars is a significant yet challenging task for many applicated scenarios. Previous studies have set out to learn 3D human head generative models using massive 2D image data. Although these models are highly generalizable for human appearance, their result models are not 360$^\circ$-renderable, and the predicted 3D geometry is unreliable. Therefore, such results cannot be used in VR, game modeling, and other scenarios that require 360$^\circ$-renderable 3D head models. An intuitive idea is that 3D head models with limited amount but high 3D accuracy are more reliable training data for a high-quality 3D generative model. In this vein, we delve into how to learn a native generative model for 360$^\circ$ full head from a limited 3D head dataset. Specifically, three major problems are studied: 1) how to effectively utilize various representations for generating the 360$^\circ$-renderable human head; 2) how to disentangle the appearance, shape, and motion of human faces to generate a 3D head model that can be edited by appearance and driven by motion; 3) and how to extend the generalization capability of the generative model to support downstream tasks. Comprehensive experiments are conducted to verify the effectiveness of the proposed model. We hope the proposed models and artist-designed dataset can inspire future research on learning native generative 3D head models from limited 3D datasets.

cs.CV↗

arXiv2024

Stability of vortex quadrupoles with odd-odd symmetry

For the 2D incompressible Euler equations, we establish global-in-time ($t \in \mathbb{R}$) stability of vortex quadrupoles satisfying odd symmetry with respect to both axes. Specifically, if the vorticity restricted to a quadrant is signed, sufficiently concentrated and close to its radial rearrangement up to a translation in $L^1$, we prove that it remains so for all times. The main difficulty is that the kinetic energy maximization problem in a quadrant -- the typical approach for establishing vortex stability -- lacks a solution, as the kinetic energy continues to increase when the vorticity escapes to infinity. We overcome this by taking dynamical information into account: finite-time desingularization result is combined with monotonicity of the first moment and a careful analysis of the interaction energies between vortices. The latter is achieved by new pointwise estimates on the Biot--Savart kernel and quantitative stability results for general interaction kernels. Moreover, with a similar strategy we obtain stability of a pair of opposite-signed Lamb dipoles moving away from each other.

math.AP↗

arXiv2024

Research on the Spatial Data Intelligent Foundation Model

This report focuses on spatial data intelligent large models, delving into the principles, methods, and cutting-edge applications of these models. It provides an in-depth discussion on the definition, development history, current status, and trends of spatial data intelligent large models, as well as the challenges they face. The report systematically elucidates the key technologies of spatial data intelligent large models and their applications in urban environments, aerospace remote sensing, geography, transportation, and other scenarios. Additionally, it summarizes the latest application cases of spatial data intelligent large models in themes such as urban development, multimodal systems, remote sensing, smart transportation, and resource environments. Finally, the report concludes with an overview and outlook on the development prospects of spatial data intelligent large models.

cs.AI↗