Imran Lab’s Paper Reading Group

Schedule (Summer 2026)

Fridays (Zoom meeting)

Focus Areas

Machine learning, computer vision, image processing, earth sciences, and biomedical image analysis

Next Discussion

June 26, 2026: [N. Munia], Do Transformers Need Three Projections? Systematic Study of QKV Variants

$~$

Past Discussions

June 19, 2026: [N. Nayla], Generative Multi-modal Models are Good Class Incremental Learners

June 12, 2026: [T. Ward], A foundation model of vision, audition, and language for in-silico neuroscience

June 5, 2026: [N. Munia], Seeing is Believing: Rich-Context Hallucination Detection for MLLMs via Backward Visual Grounding

May 29, 2026: [N. Nayla], MIMO: A medical vision language model with visual referring multimodal input and pixel grounding multimodal output

May 22, 2026: [T. Ward], Using Self-supervised Learning Can Improve Model Fairness

May 15, 2026: [N. Munia], When Pretty Isn’t Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators

$~$

Spring 2026, Fall 2025, Summer 2025, Spring 2025, Fall 2024, Spring 2024, Fall 2023