{ "$schema": "https://schema.org/Person", "generated": "2026-08-10", "canonical": "https://nmotlagh.github.io/", "name": "Nick Kashani Motlagh", "formalName": "Nicholas Kashani Motlagh", "headline": "I build models that know when not to answer.", "summary": "I work on when a machine learning system should answer, weigh evidence, revise, or stay quiet. Every model ships with a confidence signal, and every one of them answers a slightly different question than the one the next decision actually depends on. My dissertation, Answering Under Uncertainty, studies three places where that gap bites: abstaining from an unreliable prediction, checking whether evidence really moved the model, and deciding whether a second pass will repair a draft answer or ruin it.", "location": "Columbus, Ohio, USA", "email": "kashanimotlagh.1@osu.edu", "citizenship": "U.S. citizen", "currentRole": { "title": "Technical Analyst II", "organization": "DCS Corp (AFRL-sponsored)", "since": "2025-05" }, "availability": { "status": "open to offers", "availableFrom": "2026-08", "seeking": [ "Research Scientist", "Applied Scientist", "Machine Learning Engineer" ], "remote": true, "willingToRelocate": true, "note": "Best fit: LLM evaluation, calibration, retrieval-augmented systems, reliability infrastructure. U.S. federal roles welcome." }, "links": { "scholar": "https://scholar.google.com/citations?user=srZXFMcAAAAJ&hl=en", "github": "https://github.com/nmotlagh", "linkedin": "https://www.linkedin.com/in/nicholas-kashani-motlagh", "orcid": "https://orcid.org/0000-0001-6229-6212", "email": "mailto:kashanimotlagh.1@osu.edu" }, "education": [ { "degree": "Ph.D.", "field": "Computer Science and Engineering", "institution": "The Ohio State University", "location": "Columbus, OH", "timeframe": "Aug 2021 — Aug 2026", "completed": "2026-08", "notes": [ "Degree conferred August 2026. Dissertation: Answering Under Uncertainty: Abstention, Ambiguity, and Recoverability, defended July 8, 2026.", "Advised by Prof. Jim Davis. Minors in Mathematics and High-Performance Computing." ] }, { "degree": "M.S.", "field": "Computer Science and Engineering", "institution": "The Ohio State University", "location": "Columbus, OH", "timeframe": "Aug 2021 — May 2025", "completed": "2025-05", "notes": [ "GPA 3.70. Advised by Prof. Jim Davis." ] }, { "degree": "B.S. with Honors", "field": "Computer Science and Engineering", "institution": "The Ohio State University", "location": "Columbus, OH", "timeframe": "Aug 2017 — May 2021", "completed": "2021-05", "notes": [ "GPA 3.86. Minor in Mathematics.", "Maximus, Ten-Hai Lai, Ansel, and Name and Seal scholarships." ] } ], "experience": [ { "role": "Technical Analyst II — DCS Corp", "location": "AFRL-sponsored · Dayton, OH", "timeframe": "May 2025 — Present", "highlights": [ "Built the paired-outcome evaluation behind a 25,870-question study of retrieval-augmented QA across NQ-Open, TriviaQA and PopQA, measuring when evidence-based refinement repairs a draft answer and when it destroys a correct one.", "Trained LoRA answer/refine/abstain controllers on 8× NVIDIA H200 GPUs (~400 GPU-hours for a clean reproduction), beating the strongest confidence baseline and closing two thirds of the gap to an oracle policy.", "Maintain the evaluation harness comparing LLM policy variants across coverage, utility, and out-of-distribution behavior, plus a 480-row blind human audit validating the automatic labels at 90.8% agreement." ] }, { "role": "Graduate Research Associate — Computer Vision Lab", "location": "Ohio State University · Columbus, OH", "timeframe": "Aug 2021 — Present", "highlights": [ "Build selective-prediction systems for vision, multimodal, and language tasks, advised by Prof. Jim Davis.", "Developed per-class reject-option classification that lifts CIFAR-100 selective accuracy from 88.3% to 97.8% at 77.3% coverage, validated on 4 vision, 3 text and 8 synthetic datasets (Springer Best Paper Award at ISVC 2022; MVA 2025 journal extension).", "Designed the ImageCoMMuTE contrastive metrics for multimodal machine translation (WMT 2024), which separated genuine image use (81%) from final translation preference (63%) and built a 1,540-image extended evaluation set.", "Publish and maintain the public research code for reject-option classification and calibration." ] }, { "role": "Graduate Research Intern — AFRL", "location": "Dayton, OH", "timeframe": "Summers 2022–2024", "highlights": [ "Summer 2024: Adapted and trained JEPA and MAE transformers in a distributed Slurm/Singularity setup for multimodal EO/SAR representation learning in low-data regimes.", "Summer 2023: Developed Reject Option Beam Search for machine translation at large beam widths.", "Summer 2022: Built the end-to-end training procedure for Naturally Constrained Reject Option Classification." ] }, { "role": "Graduate Teaching Associate — Machine Learning & NLP", "location": "Ohio State University · Columbus, OH", "timeframe": "Aug 2023 — Dec 2025", "highlights": [ "Taught and supported machine learning and NLP courses through grading, office hours, and lab materials." ] }, { "role": "Undergraduate Research Intern — AFRL", "location": "Dayton, OH", "timeframe": "Summers 2020–2021", "highlights": [ "Summer 2021: Studied ensemble distillation for ambiguous instances.", "Summer 2020: Built a semi-automated system for temporal satellite imagery collection (ICCV 2021 workshop), released as the Construction-Site-Satellite-Imagery dataset." ] }, { "role": "Undergraduate Research Associate — Computer Vision Lab", "location": "Ohio State University · Columbus, OH", "timeframe": "2020 — 2021", "highlights": [ "Built semi-automatic labeling workflows for remote-sensing change detection, including Python tooling for collecting and preparing temporal satellite datasets." ] }, { "role": "Summer Research Intern — Sii Canada / Concordia University", "location": "Montreal, QC", "timeframe": "Summer 2019", "highlights": [ "Built anomaly-detection dashboards on behavioral telemetry to prioritize follow-up experiments." ] }, { "role": "Undergraduate Teaching Associate — Discrete Structures & Algorithms", "location": "Ohio State University · Columbus, OH", "timeframe": "2018 — 2019", "highlights": [ "Led recitations and office hours for discrete structures and algorithms." ] } ], "service": [ { "role": "Reviewer", "venues": [ "ICCV 2023", "CVPR 2023", "ECCV 2022", "CVPR 2022" ] }, { "role": "Volunteer", "venues": [ "HackOHI/O 2023" ] } ], "awards": [ { "name": "Springer Best Paper Award", "venue": "ISVC 2022", "for": "Learning When to Say \"I Don't Know\"" } ], "publications": [ { "title": "When Retrieval Makes the Answer Worse", "authors": [ "Nick Kashani Motlagh" ], "venue": "Dissertation chapter · manuscript under review", "year": 2026, "status": "under review", "url": "https://nmotlagh.github.io/publications/adaptive-qa-abstention/", "markdown": "https://nmotlagh.github.io/publications/adaptive-qa-abstention.md", "bibtex": "https://nmotlagh.github.io/publications/adaptive-qa-abstention.bib", "summary": "Retrieval-based refinement repairs 10.8% of draft answers and destroys 8.1% that were already correct. Confidence cannot tell you which you are about to get.", "tags": [ "selective prediction", "adaptive QA", "retrieval-augmented generation", "abstention" ] }, { "title": "Naturally Constrained Reject Option Classification", "authors": [ "N. Kashani Motlagh", "J. Davis", "T. Anderson", "J. Gwinnup" ], "venue": "Machine Vision and Applications", "year": 2025, "status": "peer-reviewed", "doi": "10.1007/s00138-024-01620-5", "url": "https://nmotlagh.github.io/publications/naturally-constrained-reject-option-classification/", "markdown": "https://nmotlagh.github.io/publications/naturally-constrained-reject-option-classification.md", "bibtex": "https://nmotlagh.github.io/publications/naturally-constrained-reject-option-classification.bib", "arxiv": "https://arxiv.org/abs/2209.04944", "code": "https://github.com/osu-cvl/learning-idk", "summary": "Journal extension evaluating per-class binomial reject thresholds across 4 vision, 3 text and 8 synthetic datasets, from 2 to 1,000 classes.", "tags": [ "vision", "reject option", "calibration", "ImageNet" ] }, { "title": "Assessing the Role of Imagery in Multimodal Machine Translation", "authors": [ "N. Kashani Motlagh", "J. Davis", "J. Gwinnup", "G. Erdmann", "T. Anderson" ], "venue": "WMT 2024", "year": 2024, "status": "peer-reviewed", "doi": "10.18653/v1/2024.wmt-1.130", "url": "https://nmotlagh.github.io/publications/assessing-imagery-in-multimodal-mt/", "markdown": "https://nmotlagh.github.io/publications/assessing-imagery-in-multimodal-mt.md", "bibtex": "https://nmotlagh.github.io/publications/assessing-imagery-in-multimodal-mt.bib", "pdf": "https://aclanthology.org/2024.wmt-1.130.pdf", "summary": "The best multimodal translation system reads the image correctly 81% of the time, but that only changes its translation 63% of the time. 'Images don't help' was partly a measurement artifact.", "tags": [ "multimodal MT", "vision-language models", "evaluation", "WMT" ] }, { "title": "Learning When to Say “I Don’t Know”", "authors": [ "N. Kashani Motlagh", "J. Davis", "T. Anderson", "J. Gwinnup" ], "venue": "ISVC 2022", "year": 2022, "status": "peer-reviewed", "award": "Springer Best Paper Award", "doi": "10.1007/978-3-031-20713-6_15", "url": "https://nmotlagh.github.io/publications/learning-when-to-say-i-dont-know/", "markdown": "https://nmotlagh.github.io/publications/learning-when-to-say-i-dont-know.md", "bibtex": "https://nmotlagh.github.io/publications/learning-when-to-say-i-dont-know.bib", "arxiv": "https://arxiv.org/abs/2209.04944", "code": "https://github.com/osu-cvl/learning-idk", "summary": "Per-class abstention thresholds that need no rejection cost or coverage target: CIFAR-100 selective accuracy climbs from 88.3% to 97.8% at 77.3% coverage.", "tags": [ "vision", "reject option", "selective accuracy", "ImageNet" ] }, { "title": "A Framework for Semi-automatic Collection of Temporal Satellite Imagery for Analysis of Dynamic Regions", "authors": [ "N. Kashani Motlagh", "A. Radhakrishnan", "J. Davis", "R. Ilin" ], "venue": "ICCV 2021 Workshop on LUAI", "year": 2021, "status": "peer-reviewed", "url": "https://nmotlagh.github.io/publications/framework-for-semi-automatic-collection/", "markdown": "https://nmotlagh.github.io/publications/framework-for-semi-automatic-collection.md", "bibtex": "https://nmotlagh.github.io/publications/framework-for-semi-automatic-collection.bib", "pdf": "https://openaccess.thecvf.com/content/ICCV2021W/LUAI/papers/Motlagh_A_Framework_for_Semi-Automatic_Collection_of_Temporal_Satellite_Imagery_for_ICCVW_2021_paper.pdf", "code": "https://github.com/osu-cvl/Construction-Site-Satellite-Imagery-Collection", "summary": "OpenStreetMap-guided imagery collection and labeling tools for building temporal satellite datasets for dynamic-region analysis.", "tags": [ "remote sensing", "data collection", "labeling pipelines", "change detection" ] } ], "repositories": [ { "name": "calibration", "url": "https://github.com/osu-cvl/calibration", "summary": "PyTorch calibration utilities for histogram binning, global temperature scaling, and class-wise temperature scaling.", "stack": [ "Python", "PyTorch", "calibration" ] }, { "name": "construction-site-satellite-imagery-collection", "url": "https://github.com/osu-cvl/Construction-Site-Satellite-Imagery-Collection", "summary": "Companion code for OpenStreetMap-guided temporal satellite imagery collection and annotation.", "stack": [ "Python", "OpenStreetMap", "remote sensing" ] }, { "name": "learning-idk", "url": "https://github.com/osu-cvl/learning-idk", "summary": "Companion code for ISVC 2022 / MVA 2025: per-class reject-option classification with binomial threshold search.", "stack": [ "Python", "PyTorch", "selective prediction" ] } ], "skills": { "build": [ "Python", "PyTorch", "Hugging Face", "scikit-learn", "FAISS" ], "run": [ "Slurm", "Singularity", "Multi-GPU training", "LoRA fine-tuning" ], "study": [ "LLM evaluation", "Retrieval-augmented generation", "Selective prediction", "Calibration", "Multimodal systems" ] }, "researchInterests": [ "Machine Learning", "Large Language Models", "Selective Prediction", "Abstention and Reject-Option Classification", "Uncertainty Quantification", "Model Calibration", "Retrieval-Augmented Generation", "LLM Evaluation", "Multimodal Machine Translation", "Vision-Language Models", "Distributed Training", "PyTorch", "Python" ], "news": [ { "date": "2026-07-08", "title": "Successfully defended my PhD dissertation, ‘Answering Under Uncertainty: Abstention, Ambiguity, and Recoverability,’ in Computer Science and Engineering at The Ohio State University." }, { "date": "2026-05-19", "title": "Prepared an ARR submission on retrieval-augmented selective QA: deciding when to answer, refine, or abstain." }, { "date": "2026-04-10", "title": "Reported LLM reject-option training and evaluation results for DCS Corp / AFRL." }, { "date": "2025-05-20", "title": "Joined DCS Corp (AFRL) as Technical Analyst II working on LLM reject-option training and evaluation." }, { "date": "2024-11-26", "title": "Journal extension on naturally constrained reject-option classification published online in Machine Vision and Applications." }, { "date": "2024-11-15", "title": "Accepted WMT 2024 paper on imagery-aware multimodal MT evaluations." } ], "faq": [ { "question": "What does Nick Kashani Motlagh work on?", "answer": "Reliability of machine learning systems under uncertainty — specifically when a model should answer, weigh evidence, revise its answer, or abstain. The work spans selective prediction and reject-option classification for classifiers, evidence-use metrics for multimodal systems, and answer/refine/abstain policies for retrieval-augmented question answering with large language models." }, { "question": "Is he available for hire, and when?", "answer": "Yes. He is available now for Research Scientist, Applied Scientist, and Machine Learning Engineer roles. He is based in Columbus, Ohio and is open to relocation or remote work." }, { "question": "What is his education?", "answer": "A PhD in Computer Science and Engineering from The Ohio State University, conferred August 2026 (dissertation defended July 8, 2026), advised by Prof. Jim Davis, with graduate minors in Mathematics and High-Performance Computing. He also holds an M.S. (2025) and a B.S. with Honors (2021) in Computer Science and Engineering from Ohio State." }, { "question": "What has he published?", "answer": "Four peer-reviewed first-author papers: “Naturally Constrained Reject Option Classification” (Machine Vision and Applications, 2025), “Assessing the Role of Imagery in Multimodal Machine Translation” (WMT 2024), “Learning When to Say I Don’t Know” (ISVC 2022, Springer Best Paper Award), and “A Framework for Semi-automatic Collection of Temporal Satellite Imagery” (ICCV Workshop 2021). A fifth manuscript, on retrieval-augmented selective QA, is under review and not yet accepted." }, { "question": "Has he won any awards?", "answer": "Yes — the Springer Best Paper Award at ISVC 2022 for “Learning When to Say I Don’t Know,” the reject-option classification work later extended into the Machine Vision and Applications journal version." }, { "question": "What is his engineering experience, as opposed to research output?", "answer": "He writes the training code, the evaluation harnesses, and the cluster orchestration himself. Recent work includes LoRA fine-tuning of answer/refine/abstain controllers on 8× NVIDIA H200 GPUs (roughly 400 GPU-hours for a clean reproduction) and a paired-outcome evaluation harness over 25,870 held-out questions. Day-to-day stack: Python, PyTorch, Hugging Face, FAISS, Slurm, and Singularity." }, { "question": "Can he work on U.S. federal or defense contracts?", "answer": "Yes. He is a U.S. citizen and has completed five summers of AFRL-sponsored research, and currently works as a Technical Analyst II at DCS Corp on AFRL-sponsored LLM reliability work. Federal and cleared-adjacent roles are welcome." }, { "question": "How should someone contact him?", "answer": "By email at kashanimotlagh.1@osu.edu. His CV is at https://nmotlagh.github.io/resume.pdf, code at https://github.com/nmotlagh, and publication record at https://scholar.google.com/citations?user=srZXFMcAAAAJ&hl=en and ORCID https://orcid.org/0000-0001-6229-6212." } ], "resources": { "cv": "https://nmotlagh.github.io/resume.pdf", "llms": "https://nmotlagh.github.io/llms.txt", "llmsFull": "https://nmotlagh.github.io/llms-full.txt", "bibtex": "https://nmotlagh.github.io/citations.bib", "rss": "https://nmotlagh.github.io/rss.xml", "sitemap": "https://nmotlagh.github.io/sitemap-index.xml" } }