Expertini Research Research

Browse Research Papers

7,444+ open-access research outputs.

✕ Clear
🔍 adam glos
Showing 7444 results for "adam glos"
Engineering Preprint PDF DOI

RopeDreamer: A Kinematic Recurrent State Space Model for Dynamics of Flexible Deformable Linear Objects

Tim Missal, Lucas Domingues, Berk Guler, Simon Manschitz, Jan Peters, Paula Dornhofer Paro Costa · 2026

The robotic manipulation of Deformable Linear Objects (DLOs) is a fundamental challenge due to the high-dimensional, non-linear dynamics of flexible structures and the complexity of maintaining topolo…

Read Paper →
AI & Data Science Preprint PDF DOI

Differentiable latent structure discovery for interpretable forecasting in clinical time series

Ivan Lerner, Jean Feydy, Alexandre Kalimouttou, Anita Burgun, Francis Bach · 2026

Background: Timely, uncertainty-aware forecasting from irregular electronic health records (EHR) can support critical-care decisions, yet most approaches either impute to a grid or sacrifice interpret…

Read Paper →
Mathematics Preprint PDF DOI

Learning Over-Relaxation Policies for ADMM with Convergence Guarantees

Junan Lin, Paul J. Goulart, Luca Furieri · 2026

The Alternating Direction Method of Multipliers (ADMM) is a widely used method for structured convex optimization, and its practical performance depends strongly on the choice of penalty and relaxatio…

Read Paper →
Earth & Environmental Sciences Preprint PDF DOI

The tale of the 3 planets: 3D cloud feedback enhances the spectral diversity of warm Jupiters

Nishil Mehta, Vivien Parmentier, Xianyu Tan, Elspeth K. H. Lee, Tristan Guillot, Matthew M. Murphy, Thomas P. Greene, Thomas G. Beatty, Taylor J. Bell, Jonathan J. Fortney, Michael R. Line, Sagnick Mukherjee, Kazumasa Ohno, Everett Schlawin, Anastasia Triantafillides, Luis Welbanks, Lindsey S. Wiser · 2026

JWST has shown a large diversity in warm Jupiter spectra, despite only small variations in the planetary parameters. However, the main driver of this diversity remains unclear. We aim to identify the …

Read Paper →
Engineering Preprint PDF DOI

A New Location Estimator for Mixed LOS & NLOS scenarios

Gaurav Duggal, Richard M. Buehrer, Harpreet S. Dhillon, Jeffrey H. Reed · 2026

Time-of-arrival (TOA)-based localization in mixed line-of-sight (LOS) and non-line-of-sight (NLOS) environments is challenging because conventional Euclidean range models do not capture diffraction-do…

Read Paper →
Computer Science Preprint PDF DOI

Prime-Field PINI: Machine-Checked Composition Theorems for Post-Quantum NTT Masking

Ray Iskander, Khaled Kirah · 2026

This is Paper 6 of a series of formally-verified analyses of masked NTT hardware for post-quantum cryptography; Paper 1 [1] established structural dependency analysis of the QANARY platform, and Paper…

Read Paper →
Physics Preprint PDF DOI

The Equivalence Principle and Kinematical Structure in the ADM Framework

L. G. Pereira · 2026

The relation between uniformly accelerated laboratories and laboratories supported in a gravitational field lies at the conceptual core of the Equivalence Principle, yet its precise kinematical conten…

Read Paper →
AI & Data Science Preprint PDF DOI

Enhancing SignSGD: Small-Batch Convergence Analysis and a Hybrid Switching Strategy

Haoran Chen, Wentao Wang · 2026

SignSGD compresses each stochastic gradient coordinate to a single bit, offering substantial memory and communication savings, but its 1-bit quantization removes magnitude information and is known to …

Read Paper →
Engineering Preprint PDF DOI

A Miniaturized Broadband 1-Bit Coding Reconfigurable Intelligent Surface for NLOS UE Localization and Uplink Communication

Khagendra Joshi, Deepak Kumar Sahoo, Kamalesh Kumar K, Debidas Kundu, Vivek A. Bohara, Amalendu Patnaik · 2026

In this paper, a broadband 1-bit coding metasurface-based reconfigurable intelligent surface (RIS) is presented. The unit cell of the metasurface consists of a wide dipole modified with interdigital c…

Read Paper →
AI & Data Science Preprint PDF DOI

Gradient-Direction Sensitivity Reveals Linear-Centroid Coupling Hidden by Optimizer Trajectories

Yongzhong Xu · 2026

We show that replacing the rolling SVD of AdamW updates with a rolling SVD of loss gradients changes the diagnostic by 1-2 orders of magnitude. Performing SVD on the loss gradient instead of the AdamW…

Read Paper →
Computer Science Preprint PDF DOI

Machine-Checked Cardinality Bounds for Masked Barrett Reduction: A 1-Bit Side-Channel Leakage Barrier in Post-Quantum Cryptographic Hardware

Ray Iskander, Khaled Kirah · 2026

Barrett reduction is the nonlinear core of every practical NTT-based post-quantum cryptography implementation. Existing composition frameworks (ISW, t-SNI, PINI, DOM) address Boolean masking over GF(2…

Read Paper →
Engineering Preprint PDF DOI

GS-DOT: Gaussian splatting-based image reconstruction for diffuse optical tomography

Jingjing Jiang · 2026

This work presents GS-DOT, a novel image reconstruction framework based on Gaussian Splatting (GS) for diffuse optical tomography (DOT). Inspired by GS for rendering applications, absorption coefficie…

Read Paper →
AI & Data Science Preprint PDF DOI

On-Device Vision Training, Deployment, and Inference on a Thumb-Sized Microcontroller

Jeremy Ellis · 2026

This paper presents a complete, end-to-end on-device vision machine learning pipeline, comprising data acquisition, two-layer CNN training with Adam optimization, and real-time inference, executing en…

Read Paper →
Computer Science Preprint PDF DOI

Entrywise Low-Rank Approximation and Matrix $p \rightarrow q$ Norms via Global Correlation Rounding

Prashanti Anderson, Ainesh Bakshi, Samuel B. Hopkins · 2026

Given a matrix $A$, the goal of the entrywise low-rank approximation problem is to find $\operatorname{argmin} \|A-B\|_p$ over all rank-$k$ matrices $B$, where $\| \cdot \|_p$ is the entrywise $\ell_p…

Read Paper →
Engineering Preprint PDF DOI

Time-Frequency Pilot Sequence Design and LoS Delay-Doppler Estimation

Aadarsh Devanand, Praful D. Mankar · 2026

We present a novel framework for line-of-sight (LoS) delay-Doppler (DD) estimation in dense scattering propagation environments. We present two time-frequency (TF) domain pilot sequences inspired by t…

Read Paper →
AI & Data Science Preprint PDF DOI

Hidden Failure Modes of Gradient Modification under Adam in Continual Learning, and Adaptive Decoupled Moment Routing as a Repair

Yuelin Hu, Zhenbo Yu, Zhengxue Cheng, Wei Liu, Li Song · 2026

Many continual-learning methods modify gradients upstream (e.g., projection, penalty rescaling, replay mixing) while treating Adam as a neutral backend. We show this composition has a hidden failure m…

Read Paper →
AI & Data Science Preprint PDF DOI

Selective Contrastive Learning For Gloss Free Sign Language Translation

Changhao Lai, Rui Zhao, Xuewen Zhong, Jinsong Su, Yidong Chen · 2026

Sign language translation (SLT) converts continuous sign videos into spoken-language text, yet it remains challenging due to the intrinsic modality mismatch between visual signs and written text, part…

Read Paper →
AI & Data Science Preprint PDF DOI

Incentivizing Neuro-symbolic Language-based Reasoning in VLMs via Reinforcement Learning

Karthic Palaniappan · 2026

There are 7,407 languages in the world. But, what about the languages that are not there in the world? Are humans so narrow minded that we don't care about the languages aliens communicate in? Aliens …

Read Paper →
AI & Data Science Preprint PDF DOI

Soft Anisotropic Diagrams for Differentiable Image Representation

Laki Iinbor, Zhiyang Dou, Wojciech Matusik · 2026

We introduce Soft Anisotropic Diagrams (SAD), an explicit and differentiable image representation parameterized by a set of adaptive sites in the image plane. In SAD, each site specifies an anisotropi…

Read Paper →
AI & Data Science Preprint PDF DOI

Revealing Geography-Driven Signals in Zone-Level Claim Frequency Models: An Empirical Study using Environmental and Visual Predictors

Sherly Alfonso-Sanchez, Cristian Bravo, Kristina G. Stankova · 2026

Geographic context is often consider relevant to motor insurance risk, yet public actuarial datasets provide limited location identifiers, constraining how this information can be incorporated and eva…

Read Paper →
Page 1 of 373 Next →