research note
UXBench — Measuring the Actionability of LLM-Generated UX Critiques
The paper addresses the emerging role of large language models (LLMs) as UX judges that inspect and critique interactive web interfaces
Research
Page 25 of 104
Skip to content
research note
VisualClaw — A Real-Time, Personalized Agent for the Physical World
VisualClaw presents a novel self-evolving multimodal agent framework designed to efficiently handle streaming video input and adapt its internal skill bank over time without updating VLM weights
research note
Your Privacy My Cloak — Backdoor Attacks on Differentially Private Federated Learning
This paper challenges the conventional assumption that applying differential privacy (DP) to federated learning (FL) inherently strengthens robustness against backdoor attacks
research note
If These Walls Could Talk — Critical Play with Large Language Models in Museums
This paper examines the emerging use of Large Language Models (LLMs) in museums as chatbots that simulate conversations with historical figures or artefacts
research note
LLM-as-Code Agentic Programming for Agent Harness
This paper examines a fundamental architectural flaw in current large language model (LLM) agent frameworks — assigning the orchestration role—that is, managing control flow such as loops, branching…
research note
New lower bounds for the degree/diameter problem via interaction with a browser-accessible LLM
This paper addresses the degree/diameter problem in graph theory, which asks for the largest number of vertices N(Δ,D) in a simple undirected connected graph with maximum degree at most Δ and diame…
research note
Quantum Cinema — An Interactive Cinematic Exploration of Quantum Computing Hardware via Generative World Models
Quantum Cinema addresses a critical educational gap in quantum computing by making the physical quantum hardware—typically inaccessible due to extreme cryogenic conditions and sealed laboratory env…
research note
OSGuard — A Benchmark for Safety in Computer-Use Agents
OSGuard addresses a critical blind spot in evaluating computer-use agents — while many benchmarks assess whether agents complete tasks as instructed, they often ignore safety failures where unsafe s…
research note
A Temporal Planning Framework for Disruption Aware Dynamic Route Optimization in Heterogeneous Railway Systems
This paper addresses the complex problem of dynamic route optimization and disruption-aware scheduling in heterogeneous multi-gauge railway systems
research note
Abstracting Cross-Domain Action Sequences into Interpretable Workflows
This paper addresses the challenge of extracting high-level, interpretable user activities from noisy, granular, and domain-specific low-level action sequences logged by digital applications
research note
Asymptotically Optimal Codes for Correcting Burst Deletions and Insertions in Labeled DNA Sequences
This paper addresses the challenge of correcting burst synchronization errors—specifically bursts of consecutive insertions or deletions—in labeling sequences used in DNA-based data storage
research note
Bond-operator analytical approach for the $t$-$J$ model
This paper develops a bond-operator theory (BOT) as an analytical framework to study the t–J model and its extensions, which is a central model for strongly correlated electrons especially relevant…