6 papers
The Format Tax
Ivan Yee Lee, Loris D'Antoni, Taylor Berg-Kirkpatrick
Asking a large language model to respond in JSON should be a formatting choice, not a capability tax. Yet we find that structured output requirements -- JSON, XML, LaTeX, Markdown…
UReason: Benchmarking Reasoning-to-Generation Alignment in Unified Multimodal Models
Cheng Yang, Chufan Shi, Bo Shui +7
Unified multimodal models (UMMs) aim to integrate multimodal understanding and generation within a unified architecture, yet it remains unclear to what extent textual and visual mo…
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…
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.…
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…