Searcharxiv⌕ Search

arXiv subjects

Guojun Liao

Publications and source records attributed to Guojun Liao.

12 recordsLinked to original sources
arXiv2026

Accelerating Returns and the Qualitative Engine for Science

Ray Kurzweil described a thesis of accelerating returns, which is the most influential narratives in discussions of technological progress. Its central claim is that advances in multiple technological fields, especially compute, artificial intelligence, brain science, and biotechnology, interact in such a way that progress becomes self-amplifying and approximately exponential. This paper gives a simple mathematical interpretation of that claim and then argues that, even if such acceleration is real, it does not by itself resolve the central problem of scientific discovery. The reason is that accelerating returns apply most naturally to executional and infrastructural capability, whereas genuine discovery often depends on a different capacity: qualitative reasoning about when a current framework is structurally inadequate and what conceptual move is needed next. Recent ARC-AGI-3 results sharpen this distinction: humans solve the benchmark at ceiling, whereas frontier AI systems remain below 1%, indicating that the gap between current AI and human flexible reasoning is still very large. At the same time, Demis Hassabis has emphasized that humans must retain their sense of meaning and what they choose to focus their lives on, a reminder that the future of AI is not only a technical forecast but also a question of what forms of human understanding are worth preserving and transmitting. This paper positions the Qualitative Engine for Science (QES) [3] as a response to that missing capacity. In this view, the Kurzweil theory helps explain why quantitative capability may accelerate, while QES addresses the central problem in scientific discovery that acceleration alone does not solve. Its value does not depend on when AGI arrives, but on the fact that the processes of scientific discovery themselves constitute a form of human wisdom worth preserving, organizing, and making accessible.

cs.AI↗
arXiv2026

A Three-Layer Framework for AI in Scientific Discovery

Current discussions of AI in scientific discovery are often dominated by two visible capabilities: search over existing knowledge and execution through optimization, simulation, and automation. Both are important, but neither fully captures the central act of discovery: the formation and evolution of models. This paper proposes a three-layer view of AI in discovery. Layer 1 is search and retrieval by large language models. Layer 2, as the main innovation of this paper, is model formation through qualitative reasoning: the capacity to recognize when a current framework is structurally inadequate and to understand the problem within a broader representational space, not through trial and error, but through structural insight into what is missing and where it can be found. Layer 3 is execution, optimization, and refinement. The main claim is that Layer 2 is both the most important and the least developed. Search without model formation remains confined to inherited frameworks, while execution without conceptual revision only amplifies an existing formulation. We illustrate Layer 2 reasoning through three case studies: S. S. Chern's intrinsic proof of the Gauss-Bonnet theorem, the resolution of the Nesterov Accelerated Gradient convergence problem via Lyapunov functions, and the autonomous disproof of the Erdos unit distance conjecture by OpenAI in 2026. Each case exhibits the same structural signature: a framework that had become inadequate, a missing conceptual object, and a resolution found in an unexpected neighboring field.

cs.AI↗
arXiv2025

VPREG: An Optimal Control Formulation for Diffeomorphic Image Registration Based on the Variational Principle Grid Generation Method

This paper introduces VPreg, a novel diffeomorphic image registration method. This work provides several improvements to our past work on mesh generation and diffeomorphic image registration. VPreg aims to achieve excellent registration accuracy while controlling the quality of the registration transformations. It ensures a positive Jacobian determinant of the spatial transformation and provides an accurate approximation of the inverse of the registration, a crucial property for many neuroimaging workflows. Unlike conventional methods, VPreg generates this inverse transformation within the group of diffeomorphisms rather than operating on the image space. The core of VPreg is a grid generation approach, referred to as \emph{Variational Principle} (VP), which constructs non-folding grids with prescribed Jacobian determinant and curl. These VP-generated grids guarantee diffeomorphic spatial transformations essential for computational anatomy and morphometry, and provide a more accurate inverse than existing methods. To assess the potential of the proposed approach, we conduct a performance analysis for 150 registrations of brain scans from the OASIS-1 dataset. Performance evaluation based on Dice scores for 35 regions of interest, along with an empirical analysis of the properties of the computed spatial transformations, demonstrates that VPreg outperforms state-of-the-art methods in terms of Dice scores, regularity properties of the computed transformation, and accuracy and consistency of the provided inverse map. We compare our results to ANTs-SyN, Freesurfer-Easyreg, and FSL-Fnirt.

cs.CV↗
arXiv2022

Recent insights on the Uniqueness Problem of Diffeomorphisms determined by Prescribed Jacobian Determinant and Curl

Variational Principle (VP) forms diffeomorphisms with prescribed Jacobian determinant (JD) and curl. Examples demonstrate that, (i) JD alone can not uniquely determine a diffeomorphism without curl; and (ii) the solutions by VP seem to satisfy properties of a Lie group. Hence, it is conjectured that a unique diffeomorphism can be assured by its JD and curl (Uniqueness Conjecture). In this paper, (1) an observation based on VP is derived that a counter example to the Conjecture, if exists, should satisfy a particular property; (2) from the observation, an experimental strategy is formulated to numerically test whether a given diffeomorphism is a valid counter example to the conjecture; (3) a proof of an intermediate step to the conjecture is provided and referred to as the semi-general case, which argues that, given two diffeomorphisms, $\pmbϕ$ and $\pmbψ$, if they are close to the identity map, $\pmb{id}$, then $\pmbϕ$ is identical $\pmbψ$.

cs.CG↗
arXiv2021

Construction of Diffeomorphisms with Prescribed Jacobian Determinant and Curl

The variational principle (VP) is designed to generate non-folding grids (diffeomorphisms) with prescribed Jacobian determinant (JD) and curl. Its solution pool of the original VP is based on an additive formulation and, consequently, is not invariant in the diffeomorphic Lie algebra. The original VP works well when the prescribed pair of JD and curl is calculated from a diffeomorphism, but not necessarily when the prescribed JD and curl are not known to come from a diffeomorphism. This issue is referred as the mismatched pair problem. In spite of that, the original VP works effectively in 2D grid generations. To resolve these issues, in this paper, we describe a new version of VP (revised VP), which is based on composition of transformations and, therefore, is invariant in the Lie algebra. The revised VP seems have overcome the inaccuracy of original VP in 3D grid generations. In the following sections, the mathematical derivations are presented. It is shown that the revised VP can calculate the inverse transformation of a known diffeomorphism. Its inverse consistency and transitivity of transformations are also demonstrated numerically. Moreover, a computational strategy is formulated based on the new version of VP to handle the mismatch issue and is demonstrated with preliminary result.

math.NA↗
arXiv2019

Deformable Registration Using Average Geometric Transformations for Brain MR Images

Accurate registration of medical images is vital for doctor's diagnosis and quantitative analysis. In this paper, we propose a new deformable medical image registration method based on average geometric transformations and VoxelMorph CNN architecture. We compute the differential geometric information including Jacobian determinant(JD) and the curl vector(CV) of diffeomorphic registration field and use them as multi-channel of VoxelMorph CNN for second train. In addition, we use the average transformation to construct a standard brain MRI atlas which can be used as fixed image. We verify our method on two datasets including ADNI dataset and MRBrainS18 Challenge dataset, and obtain excellent improvement on MR image registration with average Dice scores and non-negative Jacobian locations compared with MIT's original method. The experimental results show the method can achieve better performance in brain MRI diagnosis.

cs.CV↗
arXiv2019

The Method of Multimodal MRI Brain Image Segmentation Based on Differential Geometric Features

Accurate segmentation of brain tissue in magnetic resonance images (MRI) is a diffcult task due to different types of brain abnormalities. Using information and features from multimodal MRI including T1, T1-weighted inversion recovery (T1-IR) and T2-FLAIR and differential geometric features including the Jacobian determinant(JD) and the curl vector(CV) derived from T1 modality can result in a more accurate analysis of brain images. In this paper, we use the differential geometric information including JD and CV as image characteristics to measure the differences between different MRI images, which represent local size changes and local rotations of the brain image, and we can use them as one CNN channel with other three modalities (T1-weighted, T1-IR and T2-FLAIR) to get more accurate results of brain segmentation. We test this method on two datasets including IBSR dataset and MRBrainS datasets based on the deep voxelwise residual network, namely VoxResNet, and obtain excellent improvement over single modality or three modalities and increases average DSC(Cerebrospinal Fluid (CSF), Gray Matter (GM) and White Matter (WM)) by about 1.5% on the well-known MRBrainS18 dataset and about 2.5% on the IBSR dataset. Moreover, we discuss that one modality combined with its JD or CV information can replace the segmentation effect of three modalities, which can provide medical conveniences for doctor to diagnose because only to extract T1-modality MRI image of patients. Finally, we also compare the segmentation performance of our method in two networks, VoxResNet and U-Net network. The results show VoxResNet has a better performance than U-Net network with our method in brain MRI segmentation. We believe the proposed method can advance the performance in brain segmentation and clinical diagnosis.

cs.CV↗
arXiv2018

Uniqueness of Transformation based on Jacobian Determinant and curl-Vector

Numerical examples demonstrated that a prescribed positive Jacobian determinant alone can not uniquely determine a diffeomorphism. It is conjectured that the uniqueness of a transformation can be assured by its Jacobian determinant and the curl-vector. In this work, we study the uniqueness problem analytically and propose an approach to the proof of the uniqueness of a transformation with prescribed Jacobian determinant and curl-vector.

cs.CG↗
arXiv2018

Computational Technologies for Brain Morphometry

In this paper, we described a set of computational technologies for image analysis with applications in Brain Morphometry. The proposed technologies are based on a new Variational Principle which constructs a transformation with prescribed Jacobian determinant (which models local size changes) and prescribed curl-vector (which models local rotations). The goal of this research is to convince the image research community that Jacobian determinant as well as curl-vector should be used in all steps of image analysis. Specifically, we develop an optimal control method for non-rigid registration; a new concept and construction of average transformation; and a general robust method for construction of unbiased template from a set of images. Computational examples are presented to show the effects of curl-vector and the effectiveness of optimal control methods for non-rigid registration and our method for construction of unbiased template.

cs.CG↗
arXiv2017

A Novel Deformation Method for Higher Order Mesh Generation

The development of higher order finite elements methods has become an active research area. The deformation method for mesh generation has achieved a prescribed positive Jacobian determinant constraint and it has been a useful method for mesh adaptation. In this work, the deformation method is combined with local refinement to generate higher order meshes. 2D and 3D numerical examples of element order p=3 are shown to demonstrate the effectiveness of our new algorithm.

cs.CG↗
arXiv2016

New method of averaging diffeomorphisms based on Jacobian determinant and curl vector

Averaging diffeomorphisms is a challenging problem, and it has great applications in areas like medical image atlases. The simple Euclidean average can neither guarantee the averaged transformation is a diffeomorphism, nor get reasonable result when there is a local rotation. The goal of this paper is to propose a new approach to averaging diffeomorphisms based on the Jacobian determinant and the curl vector of the diffeomorphisms. Instead of averaging the diffeomorphisms directly, we average the Jacobian determinants and the curl vectors, and then construct a diffeomorphism based on the averaged Jacobian determinant and averaged curl vector as the average of diffeomorphisms. Numerical examples with convincible results are presented to demonstrate the method.

cs.CG↗