arXiv subjects

Yuan Gao

Publications and source records attributed to Yuan Gao.

At least 307 records · Page 17Linked to original sources

arXiv2024

Non-Adversarial Learning: Vector-Quantized Common Latent Space for Multi-Sequence MRI

Adversarial learning helps generative models translate MRI from source to target sequence when lacking paired samples. However, implementing MRI synthesis with adversarial learning in clinical settings is challenging due to training instability and mode collapse. To address this issue, we leverage intermediate sequences to estimate the common latent space among multi-sequence MRI, enabling the reconstruction of distinct sequences from the common latent space. We propose a generative model that compresses discrete representations of each sequence to estimate the Gaussian distribution of vector-quantized common (VQC) latent space between multiple sequences. Moreover, we improve the latent space consistency with contrastive learning and increase model stability by domain augmentation. Experiments using BraTS2021 dataset show that our non-adversarial model outperforms other GAN-based methods, and VQC latent space aids our model to achieve (1) anti-interference ability, which can eliminate the effects of noise, bias fields, and artifacts, and (2) solid semantic representation ability, with the potential of one-shot segmentation. Our code is publicly available.

eess.IV↗

arXiv2024

Non-degeneracy and new type of cylindrial solutions for a critical Grushin-type problem

In this paper, we consider a critical Grushin-type problem, which is closely related to the prescribed Webster scalar curvature problems on the CR sphere with cylindrically symmetric curvature. We first prove a non-degeneracy result through local Pohozaev identities, then by using the Lyapunov-Schmidt reduction methods, we construct new type of multi-bubbling solutions with cylindrical symmetry.

math.AP↗

arXiv2024

Periodic domain inversion in single crystal barium titanate-on-insulator thin film

We report experimentally achieving first-ever electric field periodic poling of single crystal barium titanate (BTO, or BaTiO3) thin film on insulator. Owing to the outstanding optical nonlinearities of BTO, this result is a key step towards achieving quasi-phase-matching in BTO. We first grow the BTO thin film on a dysprosium scandate substrate using pulsed laser deposition with a thin layer of strontium ruthenate later serving as the bottom electrode for poling. We present characterization of the BTO thin film using x-ray diffraction and piezo-response force microscopy to clearly demonstrate single crystal, single domain growth of the film which enables the desired periodic poling. To investigate the poling quality, we apply both non-destructive piezo force response microscopy and destructive etching-assisted scanning electron microscopy and we show that high quality, uniform and intransient poling with 50 % duty cycle and periods ranging from 2 μm to 10 μm is achieved. The successful realization of periodic poling in BTO thin film unlocks the potential for highly efficient nonlinear processes under quasi-phase-matching that seemed far-fetched with prior polycrystalline BTO thin films which predominantly relied on efficiency-limited random or non-phase matching conditions and is a key step towards integration of BTO photonic devices.

physics.optics↗

arXiv2024

I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models

Text-guided image-to-video (I2V) generation aims to generate a coherent video that preserves the identity of the input image and semantically aligns with the input prompt. Existing methods typically augment pretrained text-to-video (T2V) models by either concatenating the image with noised video frames channel-wise before being fed into the model or injecting the image embedding produced by pretrained image encoders in cross-attention modules. However, the former approach often necessitates altering the fundamental weights of pretrained T2V models, thus restricting the model's compatibility within the open-source communities and disrupting the model's prior knowledge. Meanwhile, the latter typically fails to preserve the identity of the input image. We present I2V-Adapter to overcome such limitations. I2V-Adapter adeptly propagates the unnoised input image to subsequent noised frames through a cross-frame attention mechanism, maintaining the identity of the input image without any changes to the pretrained T2V model. Notably, I2V-Adapter only introduces a few trainable parameters, significantly alleviating the training cost and also ensures compatibility with existing community-driven personalized models and control tools. Moreover, we propose a novel Frame Similarity Prior to balance the motion amplitude and the stability of generated videos through two adjustable control coefficients. Our experimental results demonstrate that I2V-Adapter is capable of producing high-quality videos. This performance, coupled with its agility and adaptability, represents a substantial advancement in the field of I2V, particularly for personalized and controllable applications.

cs.CV↗

arXiv2024

Unsupervised Bayesian Generation of Synthetic CT from CBCT Using Patient-Specific Score-Based Prior

Background: Cone-beam computed tomography (CBCT) scans, performed fractionally (e.g., daily or weekly), are widely utilized for patient alignment in the image-guided radiotherapy (IGRT) process, thereby making it a potential imaging modality for the implementation of adaptive radiotherapy (ART) protocols. Nonetheless, significant artifacts and incorrect Hounsfield unit (HU) values hinder their application in quantitative tasks such as target and organ segmentations and dose calculation. Therefore, acquiring CT-quality images from the CBCT scans is essential to implement online ART in clinical settings. Purpose: This work aims to develop an unsupervised learning method using the patient-specific diffusion model for CBCT-based synthetic CT (sCT) generation to improve the image quality of CBCT. Methods: The proposed method is in an unsupervised framework that utilizes a patient-specific score-based model as the image prior alongside a customized total variation (TV) regularization to enforce coherence across different transverse slices. The score-based model is unconditionally trained using the same patient's planning CT (pCT) images to characterize the manifold of CT-quality images and capture the unique anatomical information of the specific patient. The efficacy of the proposed method was assessed on images from anatomical sites including head and neck (H&N) cancer, pancreatic cancer, and lung cancer. The performance of the proposed CBCT correction method was evaluated using quantitative metrics including mean absolute error (MAE), peak signal-to-noise ratio (PSNR), and normalized cross-correlation (NCC). Additionally, the proposed algorithm was benchmarked against two other unsupervised diffusion model-based CBCT correction algorithms.

physics.med-ph↗

arXiv2024

Optimal $(2,δ)$ Locally Repairable Codes via Punctured Simplex Codes

Locally repairable codes (LRCs) have attracted a lot of attention due to their applications in distributed storage systems. In this paper, we provide new constructions of optimal $(2, δ)$-LRCs over $\mathbb{F}_q$ with flexible parameters. Firstly, employing techniques from finite geometry, we introduce a simple yet useful condition to ensure that a punctured simplex code becomes a $(2, δ)$-LRC. It is worth noting that this condition only imposes a requirement on the size of the puncturing set. Secondly, utilizing character sums over finite fields and Krawtchouk polynomials, we determine the parameters of more punctured simplex codes with puncturing sets of new structures. Several infinite families of LRCs with new parameters are derived. All of our new LRCs are optimal with respect to the generalized Cadambe-Mazumdar bound and some of them are also Griesmer codes or distance-optimal codes.

cs.IT↗

arXiv2024

Ultra-bright and energy-efficient quantum-dot LEDs by idealizing charge injection

Lighting and display, relying on electric and optical down-conversion emission with sluggish power efficiency, account for >15% global electricity consumption1,2. In 2014, quantum-dot (QD) LEDs (QLEDs) with near-optimal external quantum efficiency emerged3 and promised a pathway to avoid the vast down-conversion energy loss4,5. Despite a decade of progress4-22, fabrication of energy-efficient QLEDs with application-relevant brightness remains elusive. Here, the main roadblock is identified as the oxidative species adsorbed in the nanocrystalline electron-injection layer of QLEDs, which is then addressed by a simple reductive treatment to simultaneously boosts electron conductivity and hole blockage of the electron-injection layer. The resulting sub-bandgap-driven QLEDs with optimal efficiency achieve ultra-high brightness across the entire visible spectrum at least 2.6-fold higher than existing benchmarks. The brightness fully satisfies the demands of various forms of lighting and display, which surges to a remarkable level sufficient for QD laser diodes with a moderate bias (~9 V). Optimized electron injection further enables new types of QD-blend LEDs for diffuse white-light sources surpassing the 2035 R&D targets set by the U.S. Department of Energy. Our findings open a door for understanding and optimizing carrier transport in nanocrystalline semiconductors shared by various types of solution-processed optoelectronic devices.

physics.app-ph↗

arXiv2024

Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding

The vast applications of deep generative models are anchored in three core capabilities -- generating new instances, reconstructing inputs, and learning compact representations -- across various data types, such as discrete text/protein sequences and continuous images. Existing model families, like variational autoencoders (VAEs), generative adversarial networks (GANs), autoregressive models, and (latent) diffusion models, generally excel in specific capabilities and data types but fall short in others. We introduce Generalized Encoding-Decoding Diffusion Probabilistic Models (EDDPMs) which integrate the core capabilities for broad applicability and enhanced performance. EDDPMs generalize the Gaussian noising-denoising in standard diffusion by introducing parameterized encoding-decoding. Crucially, EDDPMs are compatible with the well-established diffusion model objective and training recipes, allowing effective learning of the encoder-decoder parameters jointly with diffusion. By choosing appropriate encoder/decoder (e.g., large language models), EDDPMs naturally apply to different data types. Extensive experiments on text, proteins, and images demonstrate the flexibility to handle diverse data and tasks and the strong improvement over various existing models.

cs.LG↗

arXiv2024

Probing Electronic Motion and Core Potential by Coulomb-reshaped Terahertz Radiation

The nature of electronic motion and structural information of atoms and molecules is encoded into strong-field induced radiations ranging from terahertz (THz) to extreme ultraviolet wavelength. The dependence of THz yields in bi-chromatic laser fields on ellipticity and interpulse phase delay were experimentally measured, and the trajectory calculations establish the link between the THz emission and the motion of the photoelectron wave packet. The interaction between the photoelectron and parent core transforms from soft collision to recollision as the laser field tuned from elliptical to linear polarization, which can be reflected in THz emission. The soft collision is found to be more effective in reconstructing electron dynamics through THz polarization, which enables to construct the effective core potential of the generating medium with the Coulomb-reshaped THz radiation in an elliptically polarized laser field. Our work allows designing innovative all-optical THz measurements of electronic and structural dynamics.

physics.atom-ph↗

arXiv2024

ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models

High-resolution Large Multimodal Models (LMMs) encounter the challenges of excessive visual tokens and quadratic visual complexity. Current high-resolution LMMs address the quadratic complexity while still generating excessive visual tokens. However, the redundancy in visual tokens is the key problem as it leads to more substantial compute. To mitigate this issue, we propose ConvLLaVA, which employs ConvNeXt, a hierarchical backbone, as the visual encoder of LMM to replace Vision Transformer (ViT). ConvLLaVA compresses high-resolution images into information-rich visual features, effectively preventing the generation of excessive visual tokens. To enhance the capabilities of ConvLLaVA, we propose two critical optimizations. Since the low-resolution pretrained ConvNeXt underperforms when directly applied on high resolution, we update it to bridge the gap. Moreover, since ConvNeXt's original compression ratio is inadequate for much higher resolution inputs, we train a successive stage to further compress the visual tokens, thereby reducing redundancy. These optimizations enable ConvLLaVA to support inputs of 1536x1536 resolution generating only 576 visual tokens, capable of handling images of arbitrary aspect ratios. Experimental results demonstrate that our method achieves competitive performance with state-of-the-art models on mainstream benchmarks. The ConvLLaVA model series are publicly available at https://github.com/alibaba/conv-llava.

cs.CV↗

arXiv2024

Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost

We aim at exploiting additional auxiliary labels from an independent (auxiliary) task to boost the primary task performance which we focus on, while preserving a single task inference cost of the primary task. While most existing auxiliary learning methods are optimization-based relying on loss weights/gradients manipulation, our method is architecture-based with a flexible asymmetric structure for the primary and auxiliary tasks, which produces different networks for training and inference. Specifically, starting from two single task networks/branches (each representing a task), we propose a novel method with evolving networks where only primary-to-auxiliary links exist as the cross-task connections after convergence. These connections can be removed during the primary task inference, resulting in a single-task inference cost. We achieve this by formulating a Neural Architecture Search (NAS) problem, where we initialize bi-directional connections in the search space and guide the NAS optimization converging to an architecture with only the single-side primary-to-auxiliary connections. Moreover, our method can be incorporated with optimization-based auxiliary learning approaches. Extensive experiments with six tasks on NYU v2, CityScapes, and Taskonomy datasets using VGG, ResNet, and ViT backbones validate the promising performance. The codes are available at https://github.com/ethanygao/Aux-NAS.

cs.LG↗

arXiv2024

Dual Relation Mining Network for Zero-Shot Learning

Zero-shot learning (ZSL) aims to recognize novel classes through transferring shared semantic knowledge (e.g., attributes) from seen classes to unseen classes. Recently, attention-based methods have exhibited significant progress which align visual features and attributes via a spatial attention mechanism. However, these methods only explore visual-semantic relationship in the spatial dimension, which can lead to classification ambiguity when different attributes share similar attention regions, and semantic relationship between attributes is rarely discussed. To alleviate the above problems, we propose a Dual Relation Mining Network (DRMN) to enable more effective visual-semantic interactions and learn semantic relationship among attributes for knowledge transfer. Specifically, we introduce a Dual Attention Block (DAB) for visual-semantic relationship mining, which enriches visual information by multi-level feature fusion and conducts spatial attention for visual to semantic embedding. Moreover, an attribute-guided channel attention is utilized to decouple entangled semantic features. For semantic relationship modeling, we utilize a Semantic Interaction Transformer (SIT) to enhance the generalization of attribute representations among images. Additionally, a global classification branch is introduced as a complement to human-defined semantic attributes, and we then combine the results with attribute-based classification. Extensive experiments demonstrate that the proposed DRMN leads to new state-of-the-art performances on three standard ZSL benchmarks, i.e., CUB, SUN, and AwA2.

cs.CV↗

arXiv2024

Carleman estimates for higher order partial differential operators and its applications

In this paper, we obtain a Carleman estimate for the higher order partial differential operator. In the process of establishing this estimate, we developed a new method, which is called the back-propagation method (the BPM, for short). This method can also be used to build up Carleman estimates for some other partial differential operators, and might provide assistance with corresponding numerical analyses. As an application of the above-mentioned Carleman estimate, we proved the conditional stability of a Cauchy problem for a time fractional diffusion equation.

math.AP↗

arXiv2024

A Latent Factor Model for High-Dimensional Binary Data

In this study, we develop a latent factor model for analysing high-dimensional binary data. Specifically, a standard probit model is used to describe the regression relationship between the observed binary data and the continuous latent variables. Our method assumes that the dependency structure of the observed binary data can be fully captured by the continuous latent factors. To estimate the model, a moment-based estimation method is developed. The proposed method is able to deal with both discontinuity and high dimensionality. Most importantly, the asymptotic properties of the resulting estimators are rigorously established. Extensive simulation studies are presented to demonstrate the proposed methodology. A real dataset about product descriptions is analysed for illustration.

stat.ME↗

arXiv2024

Vision-Language Model-based Physical Reasoning for Robot Liquid Perception

There is a growing interest in applying large language models (LLMs) in robotic tasks, due to their remarkable reasoning ability and extensive knowledge learned from vast training corpora. Grounding LLMs in the physical world remains an open challenge as they can only process textual input. Recent advancements in large vision-language models (LVLMs) have enabled a more comprehensive understanding of the physical world by incorporating visual input, which provides richer contextual information than language alone. In this work, we proposed a novel paradigm that leveraged GPT-4V(ision), the state-of-the-art LVLM by OpenAI, to enable embodied agents to perceive liquid objects via image-based environmental feedback. Specifically, we exploited the physical understanding of GPT-4V to interpret the visual representation (e.g., time-series plot) of non-visual feedback (e.g., F/T sensor data), indirectly enabling multimodal perception beyond vision and language using images as proxies. We evaluated our method using 10 common household liquids with containers of various geometry and material. Without any training or fine-tuning, we demonstrated that our method can enable the robot to indirectly perceive the physical response of liquids and estimate their viscosity. We also showed that by jointly reasoning over the visual and physical attributes learned through interactions, our method could recognize liquid objects in the absence of strong visual cues (e.g., container labels with legible text or symbols), increasing the accuracy from 69.0% -- achieved by the best-performing vision-only variant -- to 86.0%.

cs.RO↗

arXiv2024

Anchor-based Robust Finetuning of Vision-Language Models

We aim at finetuning a vision-language model without hurting its out-of-distribution (OOD) generalization. We address two types of OOD generalization, i.e., i) domain shift such as natural to sketch images, and ii) zero-shot capability to recognize the category that was not contained in the finetune data. Arguably, the diminished OOD generalization after finetuning stems from the excessively simplified finetuning target, which only provides the class information, such as ``a photo of a [CLASS]''. This is distinct from the process in that CLIP was pretrained, where there is abundant text supervision with rich semantic information. Therefore, we propose to compensate for the finetune process using auxiliary supervision with rich semantic information, which acts as anchors to preserve the OOD generalization. Specifically, two types of anchors are elaborated in our method, including i) text-compensated anchor which uses the images from the finetune set but enriches the text supervision from a pretrained captioner, ii) image-text-pair anchor which is retrieved from the dataset similar to pretraining data of CLIP according to the downstream task, associating with the original CLIP text with rich semantics. Those anchors are utilized as auxiliary semantic information to maintain the original feature space of CLIP, thereby preserving the OOD generalization capabilities. Comprehensive experiments demonstrate that our method achieves in-distribution performance akin to conventional finetuning while attaining new state-of-the-art results on domain shift and zero-shot learning benchmarks.

cs.CV↗

arXiv2024

Bayesian Optimization Algorithms for Accelerator Physics

Accelerator physics relies on numerical algorithms to solve optimization problems in online accelerator control and tasks such as experimental design and model calibration in simulations. The effectiveness of optimization algorithms in discovering ideal solutions for complex challenges with limited resources often determines the problem complexity these methods can address. The accelerator physics community has recognized the advantages of Bayesian optimization algorithms, which leverage statistical surrogate models of objective functions to effectively address complex optimization challenges, especially in the presence of noise during accelerator operation and in resource-intensive physics simulations. In this review article, we offer a conceptual overview of applying Bayesian optimization techniques towards solving optimization problems in accelerator physics. We begin by providing a straightforward explanation of the essential components that make up Bayesian optimization techniques. We then give an overview of current and previous work applying and modifying these techniques to solve accelerator physics challenges. Finally, we explore practical implementation strategies for Bayesian optimization algorithms to maximize their performance, enabling users to effectively address complex optimization challenges in real-time beam control and accelerator design.

physics.acc-ph↗

arXiv2024

On a result by Baillon, Bruck, and Reich

It is well known that the iterates of an averaged nonexpansive mapping may only converge weakly to fixed point. A celebrated result by Baillon, Bruck, and Reich from 1978 yields strong convergence in the presence of linearity. In this paper, we extend this result to allow for flexible relaxation parameters. Examples are also provided to illustrate the results.

math.FA↗