Research
Research
Research
Research
19,024+ 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…
We present D-Rex, a person-specific framework for photorealistic, relightable, expressive, and animatable full-body human avatars with free-viewpoint rendering. Existing methods for relightable full-b…
Task-based dialogue systems assist users in achieving specific goals, such as executing actions or retrieving information, through natural language interactions. Accurate coreference resolution is ess…
Scene-text image captioning requires fusing three information streams -- visual features, OCR-detected text, and linguistic knowledge -- to generate descriptions that faithfully integrate text visible…
Incorporating molecular-scale effects in the description of contact line motion is essential for accurately capturing all sources of energy dissipation in wetting dynamics. This holds particularly tru…
Software stacks embedded on microcontroller-based hardware typically provide rudimentary APIs programmed in C/C++, basic connectivity and, sometimes, a firmware update mechanism. Such coarse mechanism…
We demonstrate exponential quantum speedup for a restricted-Hamming-weight version of Simon's problem on present-day superconducting quantum processors by introducing a hardware-aware compilation stra…
Perturbation probing generates task-specific causal hypotheses for FFN neurons in large language models using two forward passes per prompt and no backpropagation, followed by a one-time intervention …
The rapid proliferation of harmful and emotionally damaging content on social media platforms has intensified concerns regarding societal harm. While content moderation efforts primarily focus on dete…
Learning rate scheduling has evolved from the single global fixed rate of early SGD to sophisticated layer-wise adaptive strategies. We systematize this evolution into five generations: (Gen1) global …
Current LLM safety alignment techniques improve model robustness against adversarial attacks, but overlook whether and how LLMs can recover helpfulness when benign users clarify their intent. We intro…
IRAS 13224-3809 is one of the most intensively studied narrow-line Seyfert 1 galaxies, with a rich literature reporting diverse and sometimes contrasting interpretations of its complex X-ray spectra a…
Geoscientists often solve inverse problems to estimate values of parameters of interest given relevant data sets. Bayesian inference solves these problems by combining probability distributions that d…
We present a Spatially Embedded Evolutionary Algorithm where robot individuals exist in a physically simulated 2D environment, must navigate to encounter potential mates, and compete for survival unde…
Trust in clinical artificial intelligence (AI) cannot be reduced to model accuracy, fluency of generation, or overall positive user impression. In medicine, trust must be engineered as a measurable sy…
The theory of planned behavior (TPB) is one of the most influential frameworks in social psychology, stating that a person's behavior is driven by intention, which is primarily shaped by attitude, sub…
Safety-aligned language models must refuse harmful requests without collapsing into broad over-refusal, but the training-time mechanisms behind this tradeoff remain unclear. Prior work characterizes r…
Large language models (LLMs) are increasingly considered for deployment as the control component of robotic health attendants, yet their safety in this context remains poorly characterized. We introdu…
Quantum annealing targets low-energy solutions of Ising/QUBO problems, but reliable assessment requires more than best-energy comparisons. This dissertation develops a benchmarking framework for D-Wav…
Purpose: Rapid and reliable diagnostic tools are crucial for managing respiratory diseases like COVID-19, where chest X-ray analysis coupled with artificial intelligence techniques has proven invaluab…
Free open-access publishing with Google Scholar indexing.
Submission Guide →