Expertini Research Research

Browse Research Papers

23,520+ open-access research outputs.

✕ Clear
🔍 martin vechev
Showing 23520 results for "martin vechev"
AI & Data Science Preprint PDF DOI

Representation Fr\'echet Loss for Visual Generation

Jiawei Yang, Zhengyang Geng, Xuan Ju, Yonglong Tian, Yue Wang · 2026

We show that Fr\'echet Distance (FD), long considered impractical as a training objective, can in fact be effectively optimized in the representation space. Our idea is simple: decouple the population…

Read Paper →
Physics Preprint PDF DOI

Beyond the Separatrix: Analytic Continuation of Darwin Variables for Plunging Geodesics in Schwarzschild Spacetime

Francisco M. Blanco · 2026

We study geodesic motion of a test particle in Schwarzschild spacetime. Bound and scattering geodesics are commonly described using Darwin variables, which provide a convenient parametrization of the …

Read Paper →
AI & Data Science Preprint PDF DOI

3D-ReGen: A Unified 3D Geometry Regeneration Framework

Geon Yeong Park, Roman Shapovalov, Rakesh Ranjan, Jong Chul Ye, Andrea Vedaldi, Thu Nguyen-Phuoc · 2026

We consider the problem of regenerating 3D objects from 2D images and initial 3D shapes. Most 3D generators operate in a one-shot fashion, converting text or images to a 3D object with limited control…

Read Paper →
Physics Preprint PDF DOI

Discontinuous BBP transitions

Dario Bocchi, Giulio Biroli, Chiara Cammarota, Federico Ricci-Tersenghi · 2026

The Baik-Ben Arous-Peche (BBP) transition sets fundamental limits for detecting low-rank structure in noisy high-dimensional data and underlies a wide range of spectral methods in many fields from phy…

Read Paper →
Mathematics Preprint PDF DOI

Stein's square function associated with the Bochner-Riesz means on M\'etivier groups and its applications

Joydwip Singh · 2026

In this paper, we study the $L^p$-boundedness of Stein's square function $\mathfrak{S}^{\alpha}(\mathcal{L})$ associated with the sub-Laplacian $\mathcal{L}$ on M\'etivier group $G$. A key aspect of o…

Read Paper →
AI & Data Science Preprint PDF DOI

Frequency-Aware Semantic Fusion with Gated Injection for AI-generated Image Detection

Shuchang Zhou, Shangkun Wu, Jiwei Wei, Ke Liu, Ran Ran, Caiyan Qin, Yang Yang · 2026

AI-generated images are becoming increasingly realistic and diverse, posing significant challenges for generalizable detection. While Vision Foundation Models (VFMs) provide rich semantic representati…

Read Paper →
AI & Data Science Preprint PDF DOI

Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction

Mehryar Mohri, Yutao Zhong · 2026

The choice of loss function in classification involves a fundamental trade-off: smooth losses (like Cross-Entropy) enable fast optimization rates but yield slow square-root consistency bounds, while p…

Read Paper →
AI & Data Science Preprint PDF DOI

Mind the Gap: Structure-Aware Consistency in Preference Learning

Mehryar Mohri, Yutao Zhong · 2026

Preference learning has become the foundation of aligning Large Language Models (LLMs) with human intent. Popular methods, such as Direct Preference Optimization (DPO), minimize surrogate losses as pr…

Read Paper →
AI & Data Science Preprint PDF DOI

Optimized Deferral for Imbalanced Settings

Corinna Cortes, Anqi Mao, Mehryar Mohri, Yutao Zhong · 2026

Learning algorithms can be significantly improved by routing complex or uncertain inputs to specialized experts, balancing accuracy with computational cost. This approach, known as learning to defer, …

Read Paper →
Engineering Preprint PDF DOI

Bitwise Over-Parameterized Neural Polar Decoding: A Theoretical Performance Analysis

Hongzhi Zhu, Wei Xu, Xiaohu You · 2026

This paper proposes a bitwise over-parameterized neural network (ONN) decoder for polar-coded transmission and develops a tractable theoretical performance analysis framework. By modeling each synthes…

Read Paper →
Mathematics Preprint PDF DOI

Property $R_\infty$ for generalized Higman groups

Ignat Soroko, Nicolas Vaskou · 2026

We give a unified proof of property $R_\infty$ for the Higman groups $H_n$ ($n\ge 4$) and for their generalizations studied by Martin and Horbez--Huang. As a key step, we prove that the automorphism g…

Read Paper →
AI & Data Science Preprint PDF DOI

Estimating Decision Uncertainty from Preference Uncertainty: Application to Ground Vehicle Design

Chia-Ruei Liu, Yongjia Song, Qiong Zhang, Cameron Turner · 2026

Engineering design problems are often modeled as multi-objective optimization tasks in which a scalarized utility function selects an optimal design from the Pareto set. In practice, preferences are i…

Read Paper →
AI & Data Science Preprint PDF DOI

Generalizing the Geometry of Model Merging Through Frechet Averages

Marvin F. da Silva, Mohammed Adnan, Felix Dangel, Sageev Oore · 2026

Model merging aims to combine multiple models into one without additional training. Na\"ive parameter-space averaging can be fragile under architectural symmetries, as their geometry does not take the…

Read Paper →
AI & Data Science Preprint PDF DOI

Semi-supervised learning with max-margin graph cuts

Branislav Kveton, Michal Valko, Ali Rahimi, Ling Huang · 2026

This paper proposes a novel algorithm for semisupervised learning. This algorithm learns graph cuts that maximize the margin with respect to the labels induced by the harmonic function solution. We mo…

Read Paper →
AI & Data Science Preprint PDF DOI

FunFace: Feature Utility and Norm Estimation for Face Recognition

Ziga Babnik, Fadi Boutros, Naser Damer, Deepak Kumar Jain, Peter Peer, Vitomir Struc · 2026

Face Recognition (FR) is used in a variety of application domains, from entertainment and banking to security and surveillance. Such applications rely on the FR model to be robust and perform well in …

Read Paper →
AI & Data Science Preprint PDF DOI

Multimodal LLMs are not all you need for Pediatric Speech Language Pathology

Darren Furst, Sebastian Steindl, Ulrich Schafer · 2026

Speech Sound Disorders (SSD) affect roughly five percent of children, yet speech-language pathologists face severe staffing shortages and unmanageable caseloads. We test a hierarchical approach to SSD…

Read Paper →
Physics Preprint PDF DOI

The Fock-Darwin-Darboux system: eigenstates, information entropies and dispersion-like measures

Ignacio Baena-Jimenez, Angel Ballesteros, Ivan Gutierrez-Sagredo · 2026

The Fock-Darwin (FD) quantum system describes the motion on the plane of a charged particle under the action of an isotropic oscillator potential together with a perpendicular constant magnetic field.…

Read Paper →
Economics & Finance Preprint PDF DOI

Marshall meets Bartik: Revisiting the mysteries of the trade

Yasusada Murata, Ryo Nakajima · 2026

We identify a causal effect of top inventor inflows on the patent productivity of local inventors by combining the idea-generating process described by Marshall (1890) with the Bartik (1991) instrumen…

Read Paper →
Physics Preprint PDF DOI

Newton-Cartan limit of Klein-Gordon AQFT and the collapse of Galilean modular structure

Leonardo A. Pachon · 2026

We extend the established Galilean/relativistic structural divider in algebraic quantum field theory, namely, the absence of Reeh-Schlieder and of Tomita-Takesaki modular flow on local algebras of any…

Read Paper →
AI & Data Science Preprint PDF DOI

A Data-Centric Framework for Intraoperative Fluorescence Lifetime Imaging for Glioma Surgical Guidance

Silvia Noble Anbunesan, Mohamed Abul Hassan, Jinyi Qi, Lisanne Kraft, Han Sung Lee, Orin Bloch, Laura Marcu · 2026

Accurate intraoperative assessment of glioma infiltration is essential for maximizing tumor resection while preserving functional brain tissue. Fluorescence lifetime imaging (FLIm) offers real-time, l…

Read Paper →
Page 1 of 1176 Next →