Research
Research
Research
Research
3,359+ open-access research outputs.
Motivated by an optimal-matching problem (Leighton-Shor) and the random-field Ising model (Aizenman-Wehr, Ding-Wirth), we consider a variational problem for graphs in $1+1$ dimension maximizing an act…
We introduce a generalized family of $\left( 2\cdot \left\lfloor \frac{k}{2} \right\rfloor-1, 2\cdot \left\lceil \frac{k}{2} \right\rceil \cdot W_{1} +\max\left\{0,2\cdot\left(\left\lceil\frac{k}{2}\r…
Open-vocabulary change detection aims to identify semantic changes in bi-temporal remote sensing images without predefined categories. Recent methods combine foundation models such as SAM, DINO and CL…
Monocular depth estimation (MDE) is a fundamental yet inherently ill-posed task. Recent vision foundation models (VFMs), particularly DINO-based transformers, have significantly improved accuracy and …
We investigate the relation between neutral atomic hydrogen (HI) and dark matter halo mass (HIHM) using observations from the Deep Investigation of Neutral Gas Origins (DINGO) pilot survey 100h data, …
We consider $A_1$-weights and prove weighted weak type $(1,1)$ estimates for oscillatory singular integrals with kernels satisfying a Dini condition.…
We provide evidence of quantum kernel advantage under noiseless simulation in binary insurance classification on MIMIC-CXR chest radiographs using quantum support vector machines (QSVM) with frozen em…
Motivated by the limited generalization of supervised image matching models to unseen image domains, we explore the zero-shot deployment of DINO features for this task. The generalist visual represent…
BCH codes form an important class of cyclic codes, which have applications in communication and data storage systems. Although the BCH bound provides a lower bound on the minimum distance of BCH codes…
PGD adversarial training, the standard robustness method, can reduce Jacobian Frobenius norm yet worsen clean-input geometry (e.g., TDI 1.336 vs. ERM 1.093). We show this is not an implementation arti…
Vision Transformers (ViTs) dominate self-supervised learning (SSL). While they have proven highly effective for large-scale pretraining, they are computationally inefficient and scale poorly with imag…
While standard flow-matching models transport noise to data uniformly, incorporating an explicit generation order - specifically, establishing coarse, low-frequency structure before fine detail - has …
Vision foundation models have shown great promise for open-set 3D object retrieval (3DOR) through efficient adaptation to multi-view images. Leveraging semantically aligned latent space, previous work…
Human perception generalizes well across different domains, but most vision models struggle beyond their training data. This gap motivates multi-dataset learning, where a single model is trained on di…
We study neutrino mass generation within the framework of non-holomorphic modular symmetry proposed by Qu and Ding. In this formalism, neutrino masses are generated via the Type-I seesaw mechanism, wh…
Traditional shadow removal networks often treat image restoration as an unconstrained mapping, lacking the physical interpretability required to balance localized texture recovery with global illumina…
Source-Free Domain Adaptation (SFDA) seeks to adapt a source model, which is pre-trained on a supervised source domain, for a target domain, with only access to unlabeled target training data. Relying…
Retrieval augmented generation (RAG) has transformed text based question answering, yet its extension to visual domains remains hindered by fundamental challenges: bridging the modality gap between im…
One of the dominant paradigms in self-supervised learning (SSL), illustrated by MoCo or DINO, aims to produce robust representations by capturing features that are insensitive to certain image transfo…
Zero-ablation -- replacing token activations with zero vectors -- is widely used to probe token function in vision transformers. Register zeroing in DINOv2+registers and DINOv3 produces large drops (u…
Free open-access publishing with Google Scholar indexing.
Submission Guide →