This paper presents BenDi, an energy-efficient quasi-stochastic systolic architecture for bioelectronic systems on the edge.

The paper introduces PostRI, a novel method that allows for computing a Randomization Interval (RI) for differentially private median queries after the median has already been estimated, significantly…

The paper introduces 'dashi,' an open-source Python library that provides comprehensive tools for characterizing dataset shifts (covariate, prior, concept) to ensure robust and trustworthy AI developm…

The paper systematically studies the trade-offs between the number of slopes, bends per edge, and required area for planar drawings of bounded-degree graphs, providing new constructions for high-degre…

The paper advocates for the deployment of the European Communication Infrastructure (EuroQCI), a continent-wide Quantum Key Distribution (QKD) network, to safeguard critical European digital services…

SIRI introduces a self-internalizing reinforcement learning framework that allows LLM agents to autonomously discover and integrate reusable skills directly into their core policy, significantly impro…

PlanarBench introduces a novel benchmark to test LLM spatial reasoning by requiring them to draw planar graphs as ASCII art from an edge list, finding that edge count is a stronger difficulty predicto…

This paper demonstrates a proof-of-concept method using top-view video to detect 'Pen-Up' states in handwriting, showing it can reliably complement traditional digitizing tablets for developmental dis…

The paper demonstrates the potential of using LLMs within verifier-guided evolutionary coding agents to develop and improve algorithms, specifically applied to contraction order optimization in tensor…

The paper proposes GovAI-Pipe, a novel four-layer governance pipeline that operationalizes high-level AI policies (like the EU AI Act) into auditable, technical checkpoints for deploying AI in large-s…

This pilot study evaluates curator-guided multilingual art description using a small, on-premise VLM (Qwen2.5-VL-3B-Instruct) for German, Romanian, and Serbian, finding that language-specific adapters…

The paper introduces PassNet, a large-scale ecosystem for generating compiler passes using LLMs, demonstrating that LLMs can significantly accelerate graph compilation for long-tail workloads, suggest…

The paper introduces Opir, an efficient family of encoder-based multi-task guardrail models that provides competitive safety classification performance across various tasks while maintaining a signifi…

CRAFTQA introduces a novel adaptive, code-driven framework that significantly enhances complex structured data reasoning by dynamically generating custom code functions beyond predefined operations.

This paper details the process of architecting and releasing LINICS, an open-source platform designed to provide necessary pentesting and security analysis capabilities for Operational Technology (OT)…

The paper introduces Script-Normalized WER (SN-WER), a novel evaluation metric that transliterates ASR transcripts into a canonical script to accurately measure speech recognition performance across d…

The paper introduces 3DCodeBench, a systematic benchmark and platform for evaluating Vision-Language Model (VLM) agents' ability to generate procedural 3D models from text and images using code.

GaMi is a multimodal material identification system that uses mmWave and acoustic sensing with a cross-modal subtractive disentanglement framework to achieve high accuracy (95.2%) for material identif…

PhyGenHOI introduces a novel framework that generates physically accurate and visually faithful 4D Human-Object Interactions by coupling generative human motion with explicit physical object simulatio…

Minor, single-character perturbations to prompts can significantly degrade the security of code generated by LLMs, suggesting that prompt fragility is a major security concern beyond simple prompt inj…