Skip to content
Hamidreza Saghir by Hamidreza Saghir

Research

Selected publications and the questions I keep coming back to.

A few questions I keep returning to: how do we know a learned system is doing what we think it’s doing? When do very different-looking methods turn out to be the same thing underneath? And how do we design tooling (evaluation, agents, interfaces) so that the answers to those questions stay honest as the models get bigger?

Current interests

  • Unified views of machine learning: cases where spectral methods, probabilistic models, kernels, and neural networks collapse to the same underlying object (similarity, message passing, KL divergence).
  • Evaluation: measurement design, LLM-as-judge methods, and the long tail of the metric went up but the product got worse.
  • Agents and planning: how learned decision-makers behave in adversarial or long-horizon settings, and what loop-level tooling they need.
  • AI and security: the verification asymmetry between offense and defense, and what that implies for where agents actually land.
  • Probabilistic ML and complex systems: variational inference, deep generative models, stochastic processes, and the occasional detour into multifractal signal analysis.
  • On-device and edge ML: compressing and factorizing transformers for strict memory and latency budgets.

Selected publications

  1. J. Niu et al. (incl. H. Saghir). Llama See, Llama Do: Contextual Entrainment and Distraction in LLMs. ACL 2025.
  2. M. Mirgbagheri, H. Saghir, T. Chau. Mimicking Linguistic Features of Atypical Speech Transcripts. IEEE TASLP, 2025.
  3. L. Hebert et al. (incl. H. Saghir). Robust Candidate Generation for Entity Linking on Short Social Media. WNUT @ COLING 2022.
  4. H. Saghir, S. Choudhary, S. Eghbali, C. Chung. Factorization-Aware Training of Transformers for NLU on the Edge. InterSpeech 2021.
  5. H. Tu, S. Choudhary, H. Saghir, R. McGowan. Multilingual Neural Language Models for On-Device NLU. The Web Conference (WWW) 2021.
  6. P. Xu, H. Saghir, et al. A Cross-Domain Transferable Neural Coherence Model. ACL 2019.
  7. H. Saghir, A. Dupuis, T. Chau, A. Kushki. Atypical autonomic nervous system complexity accompanies social cognition task performance in ASD. Research in Autism Spectrum Disorders, 2017.
  8. H. Saghir, T. Chau, A. Kushki. Clustering of time-evolving scaling dynamics in a complex signal. Physical Review E, 2016.

Full list on Google Scholar.