Dan Roth

8

Papers

44

Total Citations

Papers (8)

ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding

Fewer Truncations Improve Language Modeling

Cross-Modal Map Learning for Vision and Language Navigation

Learning Pipelines with Limited Data and Domain Knowledge: A Study in Parsing Physics Problems

Learnability with Indirect Supervision Signals

On Learning Latent Models with Multi-Instance Weak Supervision

CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion

Distributed Box-Constrained Quadratic Optimization for Dual Linear SVM