5 citations · 7 across the 7 of their papers we have counts for
7 papers
Optical Context Compression Is Just (Bad) Autoencoding
Ivan Yee Lee, Cheng Yang, Taylor Berg-Kirkpatrick
DeepSeek-OCR shows that rendered text can be reconstructed from a small number of vision tokens, sparking excitement about using vision as a compression medium for long textual con…
Victim as a Service: Designing a System for Engaging with Interactive Scammers
Daniel Spokoyny, Nikolai Vogler, Xin Gao +7
Pig butchering, and similar interactive online scams, lower their victims' defenses by building trust over extended periods of conversation - sometimes weeks or months. They have b…
Readability Learnability: Rethinking the Role of Simplicity in Training Small Language Models
Ivan Lee, Taylor Berg-Kirkpatrick
Recent studies suggest that very small language models (SLMs) can generate surprisingly coherent text when trained on simplified, child-directed corpora such as TinyStories. These…
Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability
Ivan Lee, Nan Jiang, Taylor Berg-Kirkpatrick
What is the relationship between model architecture and the ability to perform in-context learning? In this empirical study, we take the first steps toward answering this question.…
Towards Answering Climate Questionnaires from Unstructured Climate Reports
Daniel Spokoyny, Tanmay Laud, Tom Corringham +1
The topic of Climate Change (CC) has received limited attention in NLP despite its urgency. Activists and policymakers need NLP tools to effectively process the vast and rapidly gr…
Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context
Daniel Spokoyny, Ivan Lee, Zhao Jin +1
Physical measurements constitute a large portion of numbers in academic papers, engineering reports, and web tables. Current benchmarks fall short of properly evaluating numeracy o…
An Empirical Investigation of Contextualized Number Prediction
Daniel Spokoyny, Taylor Berg-Kirkpatrick
We conduct a large scale empirical investigation of contextualized number prediction in running text. Specifically, we consider two tasks: (1)masked number prediction-predicting a…