
research note
LEO Satellite Network Orchestration with Heterogeneous Graph Neural Networks
The paper addresses the challenge of real-time network orchestration in Low Earth Orbit (LEO) satellite constellations, which are highly dynamic and.

research note
The paper addresses the challenge of real-time network orchestration in Low Earth Orbit (LEO) satellite constellations, which are highly dynamic and.

research note
This paper addresses the challenging problem of producing statistically rigorous and computationally tractable global maps of Ocean Heat Content (OHC).

research note
This paper addresses the core challenge of zero-shot object goal navigation (ZSON) under RGB-only perception constraints, where no explicit depth.

research note
The PPT-EVAL benchmark addresses the challenge of evaluating AI agents on realistic, complex PowerPoint slide creation and editing tasks.

research note
This paper addresses the core bottleneck in building capable web browser agents: decision-making under incomplete information rather than low-level.

research note
This paper investigates whether modern vision-language models (VLMs) can accurately distinguish between potential and established common ground in.

research note
Xiaomi-GUI-0 addresses the persistent gap between the high benchmark performance of mobile GUI agents and their practical usability in real-world.

research note
This paper addresses the challenges of malware classification posed by heterogeneous malware data distributions, the presence of packed binaries, and diverse malware family characteristics

research note
Cross-view object geo-localization (CVOGL) involves locating a target object seen from a query perspective (such as ground or drone view) within geo-tagged satellite reference images

research note
This paper addresses fundamental reliability issues in Sparse Autoencoders (SAEs) used to interpret large language model (LLM) activations by breaking them down into sparse, human-understandable fe…

research note
This paper addresses the pressing challenge of detecting audio deepfakes in a manner that respects user privacy and is computationally efficient for.

research note
This paper addresses the computational challenge of accurately modeling long-lived gravitational wave inspirals from eccentric black hole binaries using the effective-one-body (EOB) framework