Nick Kashani Motlagh
Research archive

Papers and manuscript notes

A reading-friendly archive of peer-reviewed papers and current research reports on selective prediction, multimodal evidence, calibration, and typed abstention for ML systems.

Status labels are explicit: current manuscript notes are separated from peer-reviewed work, and public PDFs/code/data are linked where available.

Current manuscript

In preparation

ARR submission in preparation / 2026

Retrieval-Augmented Selective QA (Title Withheld for Anonymous Review)

N. Kashani Motlagh and collaborators

Measures when evidence-based revision fixes a draft answer and when it breaks one, so routing policies can decide to answer, revise, or abstain.

  • selective prediction
  • adaptive QA
  • retrieval-augmented generation
  • abstention
  • Compares a model's direct answer with its evidence-revised answer on the same questions, measuring how often revision fixes a wrong answer, breaks a right one, or changes nothing.
  • Shows that answer confidence and the expected value of revision are separate routing signals: a policy needs both to decide whether to answer, revise, or abstain.
Manuscript note

Peer-reviewed

Published papers

Machine Vision and Applications / 2025

Naturally Constrained Reject Option Classification

N. Kashani Motlagh, J. Davis, T. Anderson, J. Gwinnup

Journal extension of ISVC 2022 Best Paper, evaluating per-class binomial reject thresholds on ImageNet and remote-sensing datasets.

  • vision
  • reject option
  • calibration
  • ImageNet
  • remote sensing
  • Invited journal extension of the ISVC 2022 Best Paper; adds long-tailed wildlife and remote-sensing splits with class-conditional threshold analysis.
  • Per-class binomial thresholds outperform global thresholding on ImageNet and remote-sensing splits.
Paper Code
Code and data

learning-idk

WMT 2024 / 2024

Assessing the Role of Imagery in Multimodal Machine Translation

N. Kashani Motlagh, J. Davis, T. Anderson, J. Gwinnup, G. Erdmann

Contrastive evaluation of WMT 2024 multimodal MT systems shows measurable dependence on paired visual context.

  • multimodal MT
  • vision-language models
  • evaluation
  • WMT
  • Introduced imagery-aware contrastive probes for testing whether translations change under mismatched visual context.
  • Benchmarked nine multimodal MT systems under matched and mismatched visual context, with wide variance in how much each system relies on the image.
Paper Code Data
Code and data

calibration

ISVC 2022 / 2022

Best Paper

Learning When to Say "I Don't Know"

N. Kashani Motlagh, J. Davis, T. Anderson, J. Gwinnup

Per-class reject thresholds estimated from validation statistics, improving selective accuracy and coverage over global thresholding.

  • vision
  • reject option
  • selective accuracy
  • ImageNet
  • Best Paper at ISVC 2022; later extended in the MVA 2025 journal version.
  • Reported +0.4% selective-accuracy and +1.3% coverage gains on ImageNet over global thresholding.
Paper arXiv Code
Code and data

learning-idk

ICCV 2021 Workshop on LUAI / 2021

A Framework for Semi-automatic Collection of Temporal Satellite Imagery for Analysis of Dynamic Regions

N. Kashani Motlagh, A. Radhakrishnan, J. Davis, R. Ilin

OpenStreetMap-guided imagery collection and labeling tools for building temporal satellite datasets for dynamic-region analysis.

  • remote sensing
  • data collection
  • labeling pipelines
  • change detection
  • Combined imagery download, polygon filtering, temporal organization, and annotation UI in a reproducible Python pipeline.
  • Reduced manual setup for construction-site monitoring datasets and downstream change-detection experiments.
Paper Code
Code and data

construction-site-satellite-imagery-collection