Imran Lab’s Paper Reading Group

Spring 2025 Discussions

May 14, 2025: [T. Ward], Describe Anything: Detailed Localized Image and Video Captioning

Apr 30, 2025: [N. Munia], Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization

Apr 23, 2025: [R. Rifa], Bridging Compressed Image Latents and Multimodal Large Language Models

Apr 9, 2025: [M. Massey], PEACE: Empowering Geologic Map Holistic Understanding with MLLMs

Apr 2, 2025: [T. Ward], SAM-Med3D-MoE: Towards a Non-Forgetting Segment Anything Model via Mixture of Experts for 3D Medical Image Segmentation

Mar 26, 2025: [N. Munia], Retaining and Enhancing Pre-trained Knowledge in Vision-Language Models with Prompt Ensembling

Mar 5, 2025: [T. Ward], Prompt injection attacks on vision language models in oncology

Feb 26, 2025: [M. Massey], MLLM-as-a-Judge for Image Safety without Human Labeling

Feb 5, 2025: [N. Munia], Large Concept Models: Language Modeling in a Sentence Representation Space

Jan 29, 2025: [R. Rifa], Tackling Structural Hallucination in Image Translation with Local Diffusion

Jan 22, 2025: [T. Ward], Prompt-Driven Latent Domain Generalization for Medical Image Classification

Jan 15, 2025: [M. Massey], OmniSat: Self-Supervised Modality Fusion for Earth Observation

Jan 8, 2025: [A. Imran], Ethical Use of Artificial Intelligence in Medical Diagnostics Demands a Focus on Accuracy, Not Fairness