4 papers
The Seeds of Scheming: Weakness of Will in the Building Blocks of Agentic Systems
Robert Yang
Large language models display a peculiar form of inconsistency: they "know" the correct answer but fail to act on it. In human philosophy, this tension between global judgment and…
Unlearning as Ablation: Toward a Falsifiable Benchmark for Generative Scientific Discovery
Robert Yang
Bold claims about AI's role in science-from "AGI will cure all diseases" to promises of radically accelerated discovery-raise a central epistemic question: do large language models…
BERT-VQA: Visual Question Answering on Plots
Tai Vu, Robert Yang
Visual question answering has been an exciting challenge in the field of natural language understanding, as it requires deep learning models to exchange information from both visio…
GANime: Generating Anime and Manga Character Drawings from Sketches with Deep Learning
Tai Vu, Robert Yang
The process of generating fully colorized drawings from sketches is a large, usually costly bottleneck in the manga and anime industry. In this study, we examine multiple models fo…