Ignacio Meza

Machine Learning Researcher / Data Scientist / Educator

🇨🇱 Chilean researcher in Adelaide, Australia

Machine Learning Research / Data Science / Teaching

Machine learning research with clarity, rigor, and product-level discipline.

I am Ignacio Meza, a Chilean computer scientist from the University of Chile and a PhD candidate at the University of Adelaide, working across machine learning, computer vision, and neural networks.

My work spans academic research, industry data science, and university teaching. I am currently pursuing my PhD at the University of Adelaide with scholarship support from Naval Group 🇫🇷, with an emphasis on reproducible experiments, careful evaluation, readable systems, and communication that stays clear from idea to delivery.

View publications Open CV
NeurIPS 2025 Mysteries of the Deep
ACL Findings 2026 Truth as a Trajectory
PhD @ Adelaide Supported by a Naval Group 🇫🇷 scholarship
Research depth Reliable systems Clear communication Practical teaching

Research

I explore machine learning and computer vision problems with an emphasis on useful baselines, solid evidence, and honest reporting.

Engineering

I build workflows that are reproducible, readable, and maintainable, with clean implementation choices and traceable experiments.

Teaching

I enjoy turning difficult ideas into practical explanations through courses, notes, examples, and research communication.

Good Practices

Professional habits that shape how I work

Strong outcomes usually come from strong process. I try to keep both research and engineering grounded in careful practice.

  • Reproducible experiments and traceable decisions
  • Clear documentation and readable project structure
  • Thoughtful validation before claiming results
  • Maintainable code and direct communication
Research direction

Computer vision

Representation learning, temporal video grounding, and empirical study around model behavior.

Industry background

Data science

Applied machine learning work connected to practical needs, measurable outcomes, and production constraints.

Academic work

Teaching and mentoring

Course support, technical explanations, and learning materials that help others move faster with confidence.

Research

Selected Publications

Recent academic work with an emphasis on computer vision, machine learning, and careful empirical study.

  1. ICCVW
    2023_ICCV_De_la_Jara.png
    An Empirical Study of the Effect of Video Encoders on Temporal Video Grounding
    Ignacio M. Jara, Cristian Rodriguez-Opazo, Edison Marrese-Taylor, and 1 more author
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops , Oct 2023
    arXiv Cite PDF
  2. NeurIPS
    2025_NeurIPS_Mysteries_of_the_Deep.png
    Mysteries of the Deep: Role of Intermediate Representations in Out-of-Distribution Detection
    Ignacio Meza Jara, Cristian Rodriguez-Opazo, Damien Teney, and 2 more authors
    In Advances in Neural Information Processing Systems , Oct 2025
    arXiv Cite PDF Code Website
  3. ACLF
    2026_ACL_Truth_as_a_Trajectory.png
    Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning
    Ignacio Meza Jara, Hamed Damirchi, Afshar Shamsi, and 3 more authors
    In Findings of the Association for Computational Linguistics: ACL 2026 , Oct 2026
    Accepted to Findings of ACL 2026
    arXiv Cite PDF