Research
Research
Research
Research
12,709+ open-access research outputs.
Fine-tuning large language models (LLMs) on narrowly misaligned data generalizes to broadly misaligned behavior, a phenomenon termed emergent misalignment (EM). While prior work has found a correlatio…
Large Language Models (LLMs) are increasingly used as proxies for human perception in urban analysis, yet it remains unclear whether persona prompting produces meaningful and reproducible behavioral d…
Recent advances in agentic AI are shifting automation from discrete tools to proactive multi-agent systems that coordinate multi-specialized capabilities behind unified interfaces. However, today's ag…
An asymptotically flat spacetime in $D=4$ can be mapped via Couch-Torrence conformal inversion to the geometry around an extremal non-expanding and non-rotating horizon. At the linearized level, an in…
Large Language Models (LLMs) can strongly shape social discourse, yet datasets investigating how LLM outputs vary across controlled social and contextual prompting remain sparse. Cognitive Digital Sha…
To enhance LLMs' impact on math education, we need data on their mathematical prowess and biases across prompts. To fill this gap, we introduce MEDS (Math Education Digital Shadows) as a dataset mappi…
Motion retargeting from humans to human-like artificial agents is becoming increasingly important as humanoid robots grow more capable. However, most existing approaches focus only on reproducing kine…
With the advancement of multimodal large language models (MLLMs) and coding agents, the website development has shifted from manual programming to agent-based project-level code synthesis. Existing be…
In this article, we first explain a group theoretic interpretation of the derivation of the relation between the flat coordinates of the polynomial prepotential $(H_3)$ and those of the algebraic prep…
Text-to-image person re-identification (TI-ReID) relies on natural-language text description to retrieve top matching individuals from a large gallery of images. While recent large vision-language mod…
Claw-style environments support multi-step workflows over local files, tools, and persistent workspace states. However, scalable development around these environments remains constrained by the absenc…
Human-robot interaction is emerging as an important paradigm for integrating persons with disabilities into the workplace. While these systems can enable individuals to work, their design is mostly pe…
Behavioral logs provide rich signals for user modeling, but are noisy and interleaved across diverse intents. Recent work uses LLMs to generate interpretable natural-language personas from user logs, …
We give a counterexample to a recently conjectured variant of the Penrose inequality.…
Formal models for concurrent and distributed systems describe machines; the people who operate them are either ignored or treated as external environment. Yet key distributed systems -- notably grassr…
Deploying machine learning models under production constraints requires joint optimization over model family, quantization scheme, runtime backend, and serving configuration. This induces a hierarchic…
When multiple people share a single voice assistant, the system conflates their histories: one resident's preferences can leak into another's responses, eroding utility and trust. We call this failure…
Applications based on large language models (LLMs), such as multi-agent simulations, require population diversity among agents. We identify a pervasive failure mode we term \emph{Persona Collapse}: ag…
Open-source software (OSS) developers often struggle to understand and respond to user context, while existing tools, such as issue trackers (for handling bugs, requests, and feedback), largely focus …
Extreme Mass Ratio Inspirals (EMRIs) are among the key targe sources for the space-based gravitational wave (GW) detectors. The waveforms of the EMRIs are highly sensitive to the types of the central …
Free open-access publishing with Google Scholar indexing.
Submission Guide →