Papers by Bryan A. Plummer
Real, Fake, or Manipulated? Detecting Machine-Influenced Text (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work on machine generated text detection focused on identifying whether document was human or machine written, ignoring these fine-grained uses. |
| Approach: | They propose a machine-influenced text detector that learns to separate text samples from four primary types . the detector uses a subcategory guidance module to help separate the fine-grained categories . |
| Outcome: | The proposed detector outperforms the state-of-the-art in five LLMs and six domains. |
Walk and Read Less: Improving the Efficiency of Vision-and-Language Navigation via Tuning-Free Multimodal Token Pruning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large models achieve strong performance on Vision-and-Language Navigation tasks, but are costly to run in resource-limited environments. |
| Approach: | They propose a method to prune large models to minimize information loss . they use navigation-specific traits to filter the model into foreground and background . |
| Outcome: | The proposed method outperforms previous work on standard VLN benchmarks while saving 50% FLOPS. |
Scaling Up Temporal Domain Generalization via Temporal Experts Averaging (2025.emnlp-main)
Copied to clipboard
Aoming Liu, Kevin Miller, Venkatesh Saligrama, Kate Saenko, Boqing Gong, Ser-Nam Lim, Bryan A. Plummer
| Challenge: | Temporal Domain Generalization (TDG) aims to generalize across temporal distribution shifts, e.g., lexical change over time. |
| Approach: | They propose a framework that updates the entire model using weight averaging to maximize generalization potential while minimizing computational costs. |
| Outcome: | The proposed framework outperforms previous methods by up to 69% while being up to 60x more efficient. |