activity
20242026
collaborators

8 papers

cs.AI2026

TerraBench: Can Agents Reason Over Heterogeneous Earth-System Data?

Dat Tien Nguyen, Thao Nguyen, Fadillah Adamsyah Maani +5

Climate and environmental decision-making increasingly requires reasoning across heterogeneous inputs, including gridded physical data, satellite imagery, geospatial context, and s…

cs.CV2026

DARK: Diagonal-Anchored Repulsive Knowledge Distillation for Vision-Language Models under Extreme Compression

Numan Saeed, Asif Hanif, Fadillah Adamsyah Maani +2

Compressing vision-language models for on-device deployment is increasingly important in clinical settings, but knowledge distillation (KD) degrades sharply when the teacher-studen…

eess.IV2025

FetalCLIP: A Visual-Language Foundation Model for Fetal Ultrasound Image Analysis

Fadillah Maani, Numan Saeed, Tausifa Saleem +8

Foundation models are becoming increasingly effective in the medical domain, offering pre-trained models on large datasets that can be readily adapted for downstream tasks. Despite…

cs.CV2025

DuPLUS: Dual-Prompt Vision-Language Framework for Universal Medical Image Segmentation and Prognosis

Numan Saeed, Tausifa Jan Saleem, Fadillah Maani +3

Deep learning for medical imaging is hampered by task-specific models that lack generalizability and prognostic capabilities, while existing 'universal' approaches suffer from simp…

cs.CV2025

All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages

Ashmal Vayani, Dinura Dissanayake, Hasindri Watawana +66

Existing Large Multimodal Models (LMMs) generally focus on only a few regions and languages. As LMMs continue to improve, it is increasingly important to ensure they understand cul…

eess.IV2024

Optimizing Brain Tumor Segmentation with MedNeXt: BraTS 2024 SSA and Pediatrics

Sarim Hashmi, Juan Lugo, Abdelrahman Elsayed +6

Identifying key pathological features in brain MRIs is crucial for the long-term survival of glioma patients. However, manual segmentation is time-consuming, requiring expert inter…