research note
This paper investigates whether fine-tuned large language models (LLMs) genuinely learn to reason about software vulnerabilities or simply calibrate their outputs without true comprehension
research note
This paper addresses the problem of systematic evaluator bias propagation in multi-agent large language model (LLM) systems, where agents iteratively assess each other's outputs
research note
This paper introduces CUPID, a novel Person-of-Interest (POI) video deepfake detection method that leverages 3D Morphable Model (3DMM)-based UV texture maps combined with a Masked Autoencoder (MAE)…
research note
This work addresses the intertwined problems of algorithmic bias and insufficient subgroup representation in machine learning datasets, specifically focusing on intersectional groups defined by mul…
research note
This qualitative study investigates how Muslim women engage with digital Islamic learning tools, particularly apps focusing on the Qur'an, Hadith, and Seerah
research note
This paper introduces Easy Reads, an open-source Python tool designed to enhance the readability and accessibility of scientific papers hosted on arXiv by transforming their default dense formattin…
research note
This paper addresses a key bottleneck in low-latency, small-batch on-device serving of large language models (LLMs) and physical-AI workloads, where interactive sessions repeatedly branch, reset, a…
research note
This paper addresses a critical vulnerability in the verification of high-dimensional quantum entanglement
research note
This paper addresses the critical bottleneck in training computer use agents (CUAs) for web browsers — the scarcity and high cost of collecting high-quality human demonstration data in realistic env…
research note
This paper addresses the persistent market access challenges faced by smallholder maize farmers in Uganda, including weak bargaining power, low price transparency, reliance on intermediaries, poor …
research note
FreeStyle addresses the challenging problem of style-content dual-reference image generation, where a synthesized image must preserve the content and structure of a content reference image while ad…
research note
Neutral atom quantum computers (NAQC) hold promise due to long qubit coherence, flexible layouts, and native multi-qubit gates
