research note
VISUALSKILL — Multimodal Skills for Computer-Use Agents
This paper addresses the limitations of current computer-use agents (CUAs) that interact with graphical user interfaces (GUIs)
Research
Page 23 of 104
Skip to content
research note
WEQA — Wearable hEalth Question Answering with Query-Adaptive Agentic Reasoning
WEQA addresses the challenging problem of answering natural language questions about wearable health data, which is continuous, high-dimensional, and temporally complex—unlike typical text data tha…
research note
A Multi-Center Benchmark for Abdominal Disease Diagnosis and Report Generation from Non-Contrast CT
This paper addresses the clinical and logistical challenges of multiphasic contrast-enhanced CT (CECT) for abdominal disease diagnosis, including risks of nephropathy, increased workload, and limit…
research note
Cache to the Future — A Distributed Webpage Archive for Internet Blackouts
Cache to the Future (CttF) addresses the challenge of maintaining access to web-hosted knowledge during internet blackouts caused by infrastructure failures or state censorship
research note
Consensus-based Agentic Large Language Model Framework for Harmonized Tariff Schedule Code Classification
This paper addresses the challenging problem of exact classification of Canadian 10-digit Harmonized Tariff Schedule (HTS) codes from short, ambiguous product descriptions typical in maritime logis…
research note
Constructive Preference Relations — Navigating Undecidability in Rational LTL Contraction
This paper investigates the computational challenges of belief contraction in linear temporal logic (LTL), focusing on the construction and verification of epistemic preference relations that under…
research note
Disentangling multi-spin dynamic correlations in the Heisenberg spin-$\frac{1}{2}$ chain
This paper addresses a fundamental challenge in quantum materials research — extracting and characterizing multi-spin dynamical correlations beyond conventional two-spin correlations accessible via …
research note
ExpRL — Exploratory RL for LLM Mid-Training
This paper addresses the challenge of improving large language model (LLM) reasoning capabilities through reinforcement learning (RL) when sparse reward signals are insufficient due to limited base…
research note
FraudSMSWalker — Benchmarking Agentic Large Language Models for SMS-to-Webpage Fraud Detection
This paper addresses the increasingly cross-channel nature of SMS fraud, where a fraudulent text message directs a user to a webpage and risk depends on the joint consistency of the SMS claim, webp…
research note
From 911 to Hospital — Challenges and Opportunities for AI Integration in Emergency Medical Services
This paper investigates the complex challenges and opportunities for integrating AI technologies into Emergency Medical Services (EMS), a high-stakes healthcare domain characterized by distributed …
research note
From Third-Party to First-Party — Measuring and Protecting Against Modern Web Tracking Mechanisms
This paper addresses the emerging shift in web user tracking from traditional third-party tracking techniques to first-party tracking (FPT) and server-side tracking (SST)
research note
Human Universal Grasping
This paper addresses the gap between human dexterous grasping capabilities and multi-fingered robot grasping generality by directly learning from large-scale, in-the-wild human grasp data