Publications

2025

1. WAT, IJCNLP-AACL

   

   A Picture is Worth a Thousand (Correct) Captions: A Vision-Guided Judge-Corrector System for Multimodal Machine Translation

   Siddharth Betala, Kushan Raj, Vipul Betala, and 1 more author

   In The 12th Workshop on Asian Translation (WAT) at IJCNLP-AACL, 2025

   Bib HTML PDF Code

   @inproceedings{betala2025picture,
     title = {A Picture is Worth a Thousand (Correct) Captions: A Vision-Guided Judge-Corrector System for Multimodal Machine Translation},
     author = {Betala, Siddharth and Raj, Kushan and Betala, Vipul and Saswade, Rohan},
     booktitle = {The 12th Workshop on Asian Translation (WAT) at IJCNLP-AACL},
     year = {2025},
     url = {https://arxiv.org/abs/2511.07010},
     dimensions = {true},
   }

2. NeurIPS AI4Mat

   

   LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models

   Siddharth Betala, Samuel P. Gleason, Ali Ramlaoui, and 12 more authors

   In AI for Accelerated Materials Design (AI4Mat) Workshop, NeurIPS, 2025

   Workshop paper, to be submitted to Nature Computational Science

   Spotlight Bib HTML PDF Code

   Spotlight

   @inproceedings{duval2025lemat-genbench,
     title = {LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models},
     author = {Betala, Siddharth and Gleason, Samuel P. and Ramlaoui, Ali and Xu, Andy and Channing, Georgia and Levy, Daniel and Fourrier, Cl{\'e}mentine and Kazeev, Nikita and Joshi, Chaitanya K. and Kaba, S{\'e}kou{-}Oumar and Therrien, F{\'e}lix and Hernandez-Garcia, Alex and Mercado, Roc{\'i}o and Krishnan, N. M. Anoop and Duval, Alexandre},
     booktitle = {AI for Accelerated Materials Design (AI4Mat) Workshop, NeurIPS},
     year = {2025},
     dimensions = {false},
     note = {Workshop paper, to be submitted to Nature Computational Science},
     url = {https://arxiv.org/abs/2512.04562v1},
     leaderboard = {https://huggingface.co/spaces/LeMaterial/LeMat-GenBench}
   }

3. NeurIPS AI4Mat

   

   LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature

   Magdalena Lederbauer, Siddharth Betala, Xiyao Li, and 16 more authors

   In AI for Accelerated Materials Design (AI4Mat) Workshop, NeurIPS, 2025

   Workshop paper, to be submitted to Digital Discovery

   Bib HTML PDF Code

   @inproceedings{lederbauer2025lemat-synth,
     title = {LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature},
     author = {Lederbauer, Magdalena and Betala, Siddharth and Li, Xiyao and Jain, Ayush and Sehaba, Mohammed El Amine and Channing, Georgia and Germain, Grégoire and Leonescu, Anamaria and Flaifil, Faris and Amayuelas, Alfonso and Nozadze, Alexandre and Schmid, Stefan P. and Zaki, Mohd and Ethirajan, Sudheesh Kumar and Pan, Elton and Franckel, Mathilde L. D. and Duval, Alexandre and Krishnan, N M Anoop and Gleason, Samuel P.},
     booktitle = {AI for Accelerated Materials Design (AI4Mat) Workshop, NeurIPS},
     year = {2025},
     dimensions = {false},
     note = {Workshop paper, to be submitted to Digital Discovery},
     url = {https://arxiv.org/abs/2510.26824},
     dataset = {https://huggingface.co/datasets/LeMaterial/LeMat-Synth}
   }

2024

1. NeurIPS WiML

   

   Out-of-Distribution performance as a proxy metric for graph neural network explainers in the absence of ground-truth explanations

   Siddharth Betala, Guadalupe Gonzalez, and Chirag Agarwal

   In Women in Machine Learning (WiML) Workshop, NeurIPS, 2024

   Workshop poster, presented by Guadalupe Gonzalez

   Bib

   @inproceedings{betala2024out-of-distribution,
     title = {Out-of-Distribution performance as a proxy metric for graph neural network explainers in the absence of ground-truth explanations},
     author = {Betala, Siddharth and Gonzalez, Guadalupe and Agarwal, Chirag},
     booktitle = {Women in Machine Learning (WiML) Workshop, NeurIPS},
     year = {2024},
     dimensions = {false},
     note = {Workshop poster, presented by Guadalupe Gonzalez}
   }

2. WMT, EMNLP

   

   Brotherhood at WMT 2024: Leveraging LLM-Generated Contextual Conversations for Cross-Lingual Image Captioning

   Siddharth Betala and Ishan Chokshi

   In Ninth Conference on Machine Translation (WMT) at EMNLP, 2024

   Bib HTML PDF

   @inproceedings{betala2024brotherhood,
     title = {Brotherhood at WMT 2024: Leveraging LLM-Generated Contextual Conversations for Cross-Lingual Image Captioning},
     author = {Betala, Siddharth and Chokshi, Ishan},
     booktitle = {Ninth Conference on Machine Translation (WMT) at EMNLP},
     year = {2024},
     url = {https://aclanthology.org/2024.wmt-1.81/},
     dimensions = {true},
   }

3. EMNLP Main

   

   De-Identification of Sensitive Personal Data in Datasets Derived from IIT-CDIP

   Stefan Larson, Nicole Cornehl Lima, Santiago Pedroza Diaz, and 9 more authors

   In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024

   Bib HTML PDF

   @inproceedings{larson2024deidentification,
     title = {De-Identification of Sensitive Personal Data in Datasets Derived from IIT-CDIP},
     author = {Larson, Stefan and Lima, Nicole Cornehl and Diaz, Santiago Pedroza and Joshi, Amogh Manoj and Betala, Siddharth and Suleiman, Jamiu Tunde and Mathur, Yash and Prajapati, Kaushal Kumar and Alakraa, Ramla and Shen, Junjie and Okotore, Temi and Leach, Kevin},
     booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
     year = {2024},
     url = {https://aclanthology.org/2024.emnlp-main.1198/},
     dimensions = {true},
   }

4. MLCB

   

   Screening Protein Sequences Generated via Conditional Diffusion for Enhanced Fitness using a GNN-based Function Predictor

   Siddharth Betala, Zhiqing Xu, Rana Ahmed Barghout, and 2 more authors

   In Machine Learning for Computational Biology (MLCB), 2024

   Poster presentation

   Bib

   @inproceedings{betala2024mlcb,
     title = {Screening Protein Sequences Generated via Conditional Diffusion for Enhanced Fitness using a GNN-based Function Predictor},
     author = {Betala, Siddharth and Xu, Zhiqing and Barghout, Rana Ahmed and Bhatt, Nirav and Mahadevan, Radhakrishnan},
     booktitle = {Machine Learning for Computational Biology (MLCB)},
     year = {2024},
     dimensions = {false},
     note = {Poster presentation}
   }

2023

1. COBIOT

   

   Advances in generative modeling methods and datasets to design novel enzymes for renewable chemicals and fuels

   Rana A. Barghout, Zhiqing Xu, Siddharth Betala, and 1 more author

   Current Opinion in Biotechnology, 2023

   DOI Bib HTML

   @article{barghout2023advances,
     title = {Advances in generative modeling methods and datasets to design novel enzymes for renewable chemicals and fuels},
     author = {Barghout, Rana A. and Xu, Zhiqing and Betala, Siddharth and Mahadevan, Radhakrishnan},
     journal = {Current Opinion in Biotechnology},
     volume = {84},
     pages = {103007},
     year = {2023},
     doi = {10.1016/j.copbio.2023.103007},
     url = {https://www.sciencedirect.com/science/article/abs/pii/S0958166923001179},
     dimensions = {true},
   }