research note
This paper investigates whether websites can passively identify which large language model (LLM) powers an autonomous browser agent based solely on the agent's user interface (UI) interaction trace…
research note
This paper addresses the runtime provider-routing problem faced by tool-augmented LLM agents
research note
This paper identifies a novel and previously overlooked backdoor attack vector in large language models (LLMs) that exploits positional encoding as the trigger rather than input text modifications
research note
This paper addresses the challenge of efficiently and selectively exciting lattice vibrations (phonons) in two-dimensional semiconductors at room temperature, which is critical for nanoscale energy…
research note
This paper addresses the emerging need for model forensics within AI-native wireless networks, where AI models play a critical role in signal processing, resource scheduling, and network control
research note
This paper addresses the longstanding challenge of reactive synthesis: automatically creating hardware circuit designs from formal logical specifications
research note
The Orchard paper addresses the research and infrastructure bottlenecks in scalable agentic modeling of large language models (LLMs)
research note
This paper addresses the critical challenge of quantitatively evaluating geometric and physical consistency in generative video models, which are increasingly framed as implicit world models
research note
This paper addresses the integration of physical unclonable functions (PUFs) with quantum security principles using silicon photonic integrated circuits (PICs)
research note
SimPersona addresses the limitation of large language model (LLM)-based e-commerce agents that typically simulate buyers as a single 'average' persona, failing to capture the diversity and distribu…
research note
This paper provides a comprehensive review of strong gravitational lensing and the transformational impact of the James Webb Space Telescope (JWST) on this field
research note
This paper addresses the emerging problem of unauthorized fine-tuning of Large Vision-Language Models (LVLMs) on scraped multimodal web data, which raises serious copyright and privacy concerns for…
