6 papers
Revising RVL-CDIP: Quantifying Errors and Test-Train Overlap
Stefan Larson, Attila Nagy, Sam Desai +8
RVL-CDIP is a popular dataset for benchmarking document classifiers. However, the dataset contains ample amounts of label errors as well as non-trivial amounts of test-train overla…
Quantifying Explanation Quality in Graph Neural Networks using Out-of-Distribution Generalization
Ding Zhang, Siddharth Betala, Chirag Agarwal
Evaluating the quality of post-hoc explanations for Graph Neural Networks (GNNs) remains a significant challenge. While recent years have seen an increasing development of explaina…
LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models
Siddharth Betala, Samuel P. Gleason, Ali Ramlaoui +12
Generative machine learning (ML) models hold great promise for accelerating materials discovery through the inverse design of inorganic crystals, enabling an unprecedented explorat…
A Picture is Worth a Thousand (Correct) Captions: A Vision-Guided Judge-Corrector System for Multimodal Machine Translation
Siddharth Betala, Kushan Raj, Vipul Betala +1
In this paper, we describe our system under the team name BLEU Monday for the English-to-Indic Multimodal Translation Task at WAT 2025. We participate in the text-only translation…
LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature
Magdalena Lederbauer, Siddharth Betala, Valerie Gentzke +22
Wide access to advanced experimental methods in materials science has given rise to an abundance of procedural knowledge, which is scattered across decades of scientific literature…
Brotherhood at WMT 2024: Leveraging LLM-Generated Contextual Conversations for Cross-Lingual Image Captioning
Siddharth Betala, Ishan Chokshi
In this paper, we describe our system under the team name Brotherhood for the English-to-Lowres Multi-Modal Translation Task. We participate in the multi-modal translation tasks fo…