research note
This paper tackles key challenges in computational science related to interoperability across numerical optimization solvers implemented in different programming languages
research note
This paper addresses a critical gap in autonomous agent infrastructure control — the inability of existing access control and admission certificate mechanisms to enforce guaranteed, certificate-boun…
research note
This paper addresses the challenge of generating high-utility synthetic data for intent classification in task-oriented dialogue systems entirely without human-annotated seed data
research note
The paper addresses the challenge of Long Video Question Answering (LVQA) where the goal is to answer natural language queries about hours-long untrimmed videos of Activities of Daily Living (ADL)
research note
This paper addresses the challenge of detecting both major and subtle minor events in complex, high-dimensional multivariate time-series data arising from industrial processes, such as an olefins p…
research note
UNIEGO addresses the fundamental limitation in egocentric video understanding caused by the narrow perspective and single modality of wearable cameras
research note
This paper addresses the challenge of novel view synthesis (NVS) from sparse input views, where existing methods like NeRF and Gaussian Splatting (GS) struggle due to ambiguous 3D geometry recovery…
research note
This paper investigates how large language models (LLMs) aligned for safety interpret and learn from mixed demonstrations of compliance, specifically benign compliance (helpful responses to harmles…
research note
This paper addresses the emerging challenge of reliably identifying and attributing AI-powered autonomous web agents that use large language models coupled with browser-level control to browse and …
research note
This paper addresses the challenge of aligning Large Language Models (LLMs) to human preferences without relying heavily on scarce explicit feedback
research note
This work addresses a critical gap in medical AI validation by introducing a clinician-centered pipeline designed specifically for ultrasound imaging AI studies
research note
This paper addresses a significant gap in Conflict-free Replicated Data Types (CRDTs), which ensure strong eventual consistency but typically assume honest participants and do not handle Byzantine …
