Search Results for author:
Found 5 papers, 1 papers with code
Addressing Discrepancies in Semantic and Visual Alignment in Neural Networks
We evaluate whether the method increases semantic alignment by evaluating model performance on adversarially perturbed data, with the idea that it should be easier for an adversary to switch one class to a similarly represented class.
Evaluating the Capabilities of Multi-modal Reasoning Models with Synthetic Task Data
The impressive advances and applications of large language and joint language-and-visual understanding models has led to an increased need for methods of probing their potential reasoning capabilities.
Addressing Mistake Severity in Neural Networks with Semantic Knowledge
Most robust training techniques aim to improve model accuracy on perturbed inputs; as an alternate form of robustness, we aim to reduce the severity of mistakes made by neural networks in challenging conditions.
A Computational Interface to Translate Strategic Intent from Unstructured Language in a Low-Data Setting
Leveraging a game environment, we collect a dataset of over 1000 examples, mapping language strategies to the corresponding goals and constraints, and show that our model, trained on this dataset, significantly outperforms human interpreters in inferring strategic intent (i. e., goals and constraints) from language (p < 0. 05).
Context-Dependent Anomaly Detection with Knowledge Graph Embedding Models
In this work, we leverage contextual awareness for the anomaly detection problem.
