research note
This paper develops a rigorous competitive-equilibrium economic model to analyze Proof-of-Useful-Work (PoUW) blockchains, where computational effort simultaneously secures consensus and produces ex…
research note
This paper addresses the complex dual impact of large language models (LLMs) on dialect resource creation, introducing the generator-eraser paradox framework
research note
This paper addresses the challenge of discovering reusable skills for data-analytic agents without relying on costly labeled supervision or ground-truth answers
research note
Sparse attention methods have become essential for efficiently serving large language models (LLMs) with long generation lengths
research note
This paper addresses the challenge of liveness detection in biometric and digital interactions, which is increasingly critical due to sophisticated AI-driven spoofing that mimics human behavior
research note
This paper addresses the problem of safely steering text-to-video (T2V) diffusion transformer models to reduce unsafe content generation without degrading visual quality or prompt fidelity
research note
This paper addresses the challenge of building GUI agents that operate on continuously evolving, dynamic screens as found in short-video platforms, where video content plays autonomously and a user…
research note
CARE-Link is an open-source, web-based platform designed to improve gestational diabetes management by integrating electronic health records (EHR) with patient-generated data via WhatsApp, mediated…
research note
This study focuses on detailed cosmographic mapping of the Sloan Great Wall (SGW) and its associated large-scale structure through probabilistic reconstruction of cosmic density and velocity fields
research note
This paper investigates the effectiveness of Answer Engine Optimization (AEO)—a practice analogous to SEO that targets referrals from large language model (LLM) answer engines such as ChatGPT—on a …
research note
This paper investigates the reproducibility and domain-specificity of prompt-injection red-teaming results against state-of-the-art computer-using agents (CUAs)
research note
GraphAlg Playground is a fully client-side, web-based platform designed to teach and allow experimentation with GraphAlg, a domain-specific language for graph algorithms that integrates tightly wit…
