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

Oct 6, 2026: [N. Biswas], VoxTell: Free-Text Promptable Universal 3D Medical Image Segmentation

$~$

Past Discussions

Sep 29, 2026: [S. Casas], Multimodal Misinformation Detection using Large Vision-Language Models

Sep 22, 2026: [N. Nayla], Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models

Sep 15, 2026: [N. Biswas], Revisiting 2D Foundation Models for Scalable 3D Medical Image Classification

Sep 8, 2026: [V. Jorige], MedMO: Grounding and Understanding Multimodal Large Language Model for Medical Images

Sep 1, 2026: [N. Nayla], UltraMamba: Mamba-Based Multimodal Ultrasound Image Adaptive Fusion for Breast Lesion Segmentation

Aug 14, 2026: [N. Nayla], Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model

Aug 7, 2026: [N. Munia], Tag2Text: Guiding Vision-Language Model via Image Tagging

Jul 31, 2026: [N. Nayla], Unified and Semantically Grounded Domain Adaptation for Medical Image Segmentation

Jul 24, 2026: [T. Ward], BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation

Jul 17, 2026: [N. Munia], Do Transformers Need Three Projections? Systematic Study of QKV Variants

Jul 10, 2026: [N. Nayla], Make Foundation Models Trustworthy Again: Causal Fine-Adaptation for Medical Image Segmentation

Jul 3, 2026: [T. Ward], Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images

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

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

Jun 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