research note
SEC-bench Pro addresses gaps in evaluating large language models (LLMs) for automated software security tasks by providing a benchmark designed for real-world, long-horizon bug hunting on complex, …
research note
This paper addresses the critical security challenges faced by unmanned aerial vehicle (UAV) swarms operating in low-altitude wireless networks, where open wireless environments, high dynamics, and…
research note
This paper analyzes the fundamental limits of card payment fraud detection through the lens of online learning with impaired feedback
research note
This paper addresses the underexplored problem of tactile reasoning in multimodal large language models (MLLMs)
research note
This paper addresses the challenge of providing Just-in-Time (JiT) adaptive feedback at scale in STEM education by grounding Large Language Models (LLMs) with domain-specific expert knowledge
research note
This paper addresses the detection of AI-generated images (AIGC), focusing on person-centric and multi-person interaction scenarios where conventional low-level artifact cues (pixel fingerprints, f…
research note
This paper addresses the robustness challenge faced by autonomous computer-use agents powered by multimodal large language models (MLLMs) operating in real-world desktop environments
research note
This paper addresses a critical and overlooked problem in legal AI — the temporal consistency of legal reasoning when large language models (LLMs) are augmented with agentic search
research note
This paper develops a rigorous probabilistic construction of compactified imaginary Toda conformal field theory (CFT) on closed Riemann surfaces, extending the known rank-one (Liouville) case to hi…
research note
This paper addresses the critical bottleneck of scalable, verifiable training data for Reinforcement Learning with Verifiable Rewards (RLVR) applied to computer-use agents (CUAs)
research note
GeoSVG-RL addresses the challenge of generating structurally reliable, layout-constrained text-to-SVG diagrams, a problem where standard large language models often fail due to outputs with subtle …
research note
MobileGym addresses a critical gap in mobile GUI agent research — the lack of a lightweight, scalable, and verifiable simulation environment for everyday mobile apps
