research note
This paper presents a detailed content analysis of a rare, publicly released dataset from a controversial and ethically discontinued field experiment in which undisclosed LLM-powered synthetic acco…
research note
This paper addresses a key limitation in online skill learning for web automation agents — traditional approaches reuse skills only at the task level based on initial instructions and keep them fixe…
research note
This paper addresses the challenging problem of detecting AI-generated videos, which have become increasingly realistic and threaten misinformation and content trust
research note
This paper introduces SearchLog, a novel Chromium-based web browser extension designed for laboratory studies capturing naturalistic search logs during participants' open web search sessions
research note
SentinelBench addresses a pressing gap in AI agent evaluation — how to benchmark agents on long-running monitoring tasks that unfold over minutes to hours
research note
This paper presents SLUSCHI-UP, a publicly deployed web infrastructure for estimating melting temperatures of materials using the SLUSCHI small-size solid–liquid coexistence method combined with un…
research note
This paper investigates how well large language models (LLMs) can create synthetic individual-level digital twins using heterogeneous panel survey data rather than bespoke, purpose-collected datase…
research note
This paper addresses the challenge of systematically discovering cybercriminal communities on Telegram, a popular encrypted messaging platform increasingly used for illicit activities
research note
This paper studies a novel security vulnerability in stateful agentic systems that extend large language models (LLMs) beyond session-bounded assistants into systems persisting context across multi…
research note
AAD-1 addresses key limitations in one-step autoregressive image-to-video generation, where prior adversarial distillation approaches struggled with motion collapse and unstable training that produ…
research note
This paper addresses the challenge of denoising diffusion-weighted imaging (DWI) scans corrupted by signal-dependent Rician noise, which arises from magnitude reconstruction and complicates restora…
research note
This paper addresses the challenge of generating attosecond pulse trains from solid-state materials, specifically single-layer graphene (SLG), by identifying macroscopic phase-matching conditions i…
