Related papers: Analytic model for feature maps in the primary vis…
In this work, we relate the geometry of chaotic attractors of typical analytic unimodal maps to the behavior of the critical orbit. Our main result is an explicit formula relating the combinatorics of the critical orbit with the exponents…
Particle-based dynamic occupancy maps were proposed in recent years to model the obstacles in dynamic environments. Current particle-based maps describe the occupancy status in discrete grid form and suffer from the grid size problem,…
The relationship between the operator approximation property and the strong operator approximation property has deep significance in the theory of operator algebras. The original definitions of Effros and Ruan, unlike the classical…
This paper provides a fundamental characterization of the discrete ambiguity functions (AFs) of random communication waveforms under arbitrary orthonormal modulation with random constellation symbols, which serve as a key metric for…
The efficacy of Multimodal Transformers in visually-rich document understanding (VrDU) is critically constrained by two inherent limitations: the lack of explicit modeling for logical reading order and the interference of visual tokens that…
Accurate segmentation of retinal images plays a crucial role in aiding ophthalmologists in diagnosing retinopathy of prematurity (ROP) and assessing its severity. However, due to their underdeveloped, thinner vessels, manual annotation in…
Nonlinearly constrained nonconvex and nonsmooth optimization models play an increasingly important role in machine learning, statistics and data analytics. In this paper, based on the augmented Lagrangian function we introduce a flexible…
3D semantic occupancy prediction is a pivotal task in autonomous driving, providing a dense and fine-grained understanding of the surrounding environment, yet single-modality methods face trade-offs between camera semantics and LiDAR…
We present a two-stage learning framework for weakly supervised object localization (WSOL). While most previous efforts rely on high-level feature based CAMs (Class Activation Maps), this paper proposes to localize objects using the…
The magnetic line defect in the $O(N)$ model gives rise to a non-trivial one-dimensional defect conformal field theory of theoretical and experimental value. This model is considered here in $d=4-\varepsilon$ and the full spectrum of defect…
The main objects under consideration in this thesis are called maps, a certain class of graphs embedded on surfaces. Our problems have a powerful relatively recent tool in common, the so-called topological recursion (TR) introduced by…
The Segment Anything Model (SAM) has gained popularity as a versatile image segmentation method, thanks to its strong generalization capabilities across various domains. However, when applied to optic disc (OD) and optic cup (OC)…
Near-Periodic Patterns (NPP) are ubiquitous in man-made scenes and are composed of tiled motifs with appearance differences caused by lighting, defects, or design elements. A good NPP representation is useful for many applications including…
Structured reinforcement learning and stochastic optimization often involve parameters evolving on matrix Lie groups such as rotations and rigid-body transformations. We establish a representation-optimization dichotomy for…
We investigate the distributed multi-agent sharing optimization problem in a directed graph, with a composite objective function consisting of a smooth function plus a convex (possibly non-smooth) function shared by all agents. While…
Partially inspired by features of computation in visual cortex, deep neural networks compute hierarchical representations of their inputs. While these networks have been highly successful in machine learning, it remains unclear to what…
We give a brief survey on the entropy of holomorphic self maps $f$ of compact K\"ahler manifolds, and rational dominating self maps $f$ of smooth projective varieties. We emphasize the connection between the entropy and the spectral radii…
We propose a method that uses a two-species ordinary differential equation (ODE) model to characterize misfolded tau (or simply tau) protein spreading in Alzheimer's disease (AD) and calibrates it from clinical data. The unknown model…
A prevalent approach in Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViT) involves freezing the majority of the backbone parameters and solely learning low-rank adaptation weight matrices to accommodate…
We propose a new approach towards analytically solving for the dynamical content of Conformal Field Theories (CFTs) using the bootstrap philosophy. This combines the original bootstrap idea of Polyakov with the modern technology of the…