Expertini Research Research

Browse Research Papers

142,544+ open-access research outputs.

✕ Clear
🔍 carl doersch
Showing 142544 results for "carl doersch"
Computer Science Preprint PDF DOI

Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection

Prashant Kulkarni · 2026

Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack pa…

Read Paper →
AI & Data Science Preprint PDF DOI

Do Sparse Autoencoders Capture Concept Manifolds?

Usha Bhalla, Thomas Fel, Can Rager, Sheridan Feucht, Tal Haklay, Daniel Wurgaft, Siddharth Boppana, Matthew Kowal, Vasudev Shyam, Jack Merullo, Atticus Geiger, Ekdeep Singh Lubana · 2026

Sparse autoencoders (SAEs) are widely used to extract interpretable features from neural network representations, often under the implicit assumption that concepts correspond to independent linear dir…

Read Paper →
AI & Data Science Preprint PDF DOI

Neural Aided Kalman Filtering for UAV State Estimation in Degraded Sensing Environments

Akhil Gupta, Erhan Guven · 2026

Accurate state estimation of nonlinear dynamical systems is fundamental to modern aerospace operations across air, sea, and space domains. Online tracking of adversarial unmanned aerial vehicles (UAVs…

Read Paper →
Computer Science Preprint PDF DOI

Succinct Graph Representations and Algorithmic Applications

Ahammed Ullah, Alex Pothen · 2026

We propose new graph representations that exploit dense local structure to improve time and space simultaneously. Given an undirected graph $G$, we define a dual clique cover (DCC) representation of $…

Read Paper →
Mathematics Preprint PDF DOI

On centered local $\pi$-bases

Nathan Carlson · 2026

In 1967 Hajnal and Juh{\'a}sz showed that the cardinality of a first-countable Hausdorff space with the countable chain condition has cardinality at most $\mathfrak{c}$, the cardinality of the real li…

Read Paper →
Computer Science Preprint PDF DOI

Tailwind: A Practical Framework for Query Accelerators

Geoffrey X. Yu, Ryan Marcus, Tim Kraska · 2026

Relational database management systems (RDBMSes) can process general-purpose queries, but often have lower performance compared to custom-built solutions for specific queries. For example, consider a …

Read Paper →
AI & Data Science Preprint PDF DOI

Collaborative Agent Reasoning Engineering (CARE): A Three-Party Design Methodology for Systematically Engineering AI Agents with Subject Matter Experts, Developers, and Helper Agents

Rahul Ramachandran, Nidhi Jha, Muthukumaran Ramasubramanian · 2026

We present Collaborative Agent Reasoning Engineering (CARE), a disciplined methodology for engineering Large Language Model (LLM) agents in scientific domains. Unlike ad-hoc trial-and-error approaches…

Read Paper →
Physics Preprint PDF DOI

Topological Susceptibility and QCD at Finite Theta Angle

Claudio Bonanno, Claudio Bonati, Massimo D'Elia · 2026

In this chapter we provide a pedagogical introduction to the main theoretical aspects related to topology and $\theta$-dependence in Quantum Chromo-Dynamics (QCD), and to their phenomenological releva…

Read Paper →
AI & Data Science Preprint PDF DOI

Learning from Disagreement: Clinician Overrides as Implicit Preference Signals for Clinical AI in Value-Based Care

Prabhjot Singh, Abhishek Gupta, Chris Betz, Abe Flansburg, Brett Ives, Sudeep Lama, Jung Hoon Son · 2026

We reframe clinician overrides of clinical AI recommendations as implicit preference data - the same signal structure exploited by reinforcement learning from human feedback (RLHF), but richer: the an…

Read Paper →
Engineering Preprint PDF DOI

Dreaming Across Towns: Semantic Rollout and Town-Adversarial Regularization for Zero-Shot Held-Out-Town Fixed-Route Driving in CARLA

Feeza Khan Khanzada, Jaerock Kwon · 2026

Learned driving agents often degrade when deployed in unseen environments. This paper studies a deliberately bounded instance of that problem in the CARLA simulator: zero-shot transfer of a closed-loo…

Read Paper →
Mathematics Preprint PDF DOI

Noise-induced enhancement of regime lifetimes -- A data-driven approach using deterministic trajectories

Henry Schoeller, Robin Chemnitz, Peter Koltai, Maximilian Engel, Stephan Pfahl · 2026

We investigate the lifetime of dynamical regimes under the impact of noise motivated by low-dimensional models of the atmosphere. One may expect that the inclusion of noise tends to make the system le…

Read Paper →
AI & Data Science Preprint PDF DOI

From LLM-Driven Trading Card Generation to Procedural Relatedness: A Pok\'emon Case Study

Johannes Pfau, Panagiotis Vrettis · 2026

Since the dawn of Trading Card Games, the genre has grown into a multi-billion-dollar industry engaging millions of analog and digital players worldwide. Popular TCGs rely on regular updates, balance …

Read Paper →
Computer Science Preprint PDF DOI

From Mirage to Grounding: Towards Reliable Multimodal Circuit-to-Verilog Code Generation

Guang Yang, Xing Hu, Xiang Chen, Xin Xi · 2026

Multimodal large language models (MLLMs) are increasingly used to translate visual artifacts into code, from UI mockups into HTML to scientific plots into Python scripts. A circuit diagram can be view…

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

Data-Driven Continuous-Time Linear Quadratic Regulator via Closed-Loop and Reinforcement Learning Parameterizations

Armin Gie{ss}ler, Felix Thommes, Soren Hohmann · 2026

This paper studies data-driven approaches to the continuous-time linear quadratic regulator (LQR) problem based on two existing parameterizations, namely a closed-loop (CL) parameterization from behav…

Read Paper →
Computer Science Preprint PDF DOI

Can We Volunteer Out of the Peer Review Crisis?

Theo Tang, Toby Handfield, Julian Garcia · 2026

The volume of scientific manuscripts is growing faster than the capacity to evaluate them, yet the institutions that govern peer review have remained largely unchanged. The result is a widening mismat…

Read Paper →
Mathematics Preprint PDF DOI

On the homotopy types of $4$-dimensional toric orbifolds

Tyrone Cutler, Tseleung So · 2026

The cohomological rigidity problem for toric orbifolds asks when an integral cohomology isomorphism implies a homotopy equivalence. In this paper we reformulate the cohomological rigidity problem in t…

Read Paper →
Physics Preprint PDF DOI

Theory for the mixed alkali effect in glasses

Justus Leiber, Quinn Emilia Fischer, Sven Lohmann, Philipp Maass · 2026

The mixed alkali or mixed mobile ion effect in glasses manifests itself by strong nonlinear variations of ionic transport properties upon mixing of different types of mobile ions. We develop a theory …

Read Paper →
AI & Data Science Preprint PDF DOI

Modeling Clinical Concern Trajectories in Language Model Agents

Sukesh Subaharan, Venkatesan VS, Murugadasan P, Sivakumar D, Gautham N, Ganeshkumar M · 2026

Large language model (LLM) agents deployed in clinical settings often exhibit abrupt, threshold-driven behavior, offering little visibility into accumulating risk prior to escalation. In real-world ca…

Read Paper →
AI & Data Science Preprint PDF DOI

Reversible Jump MCMC With No Regrets: Bayesian Variable Selection Using Mixtures of Mutually Singular Distributions

Don van den Bergh, Merlise A. Clyde, Adrian E. Raftery, Maarten Marsman · 2026

Bayesian variable selection requires sampling from a posterior distribution that combines discrete model indicators with continuously varying parameters, a challenge often addressed through reversible…

Read Paper →
Page 1 of 7128 Next →