4 papers
Nine Emotion Centroids: A Label-Free Valence Axis That Transfers Across Four Modalities
Yousef Radwan
Inside a modern language model sits a single internal direction that tracks how positive or negative a sentence feels. We show how to find this valence axis (V-axis) from just 9 em…
The Cross-Architecture Substrate: A Domain-Transcendent, Calibration-Surviving Geometric Invariant of Modern Vision Encoders
Yousef Radwan
Different vision neural networks -- trained to classify, contrast, reconstruct, or match images to text -- should have correspondingly different internal representations. We report…
ReefNet: A Large-Scale Dataset and Benchmark for Fine-Grained Coral Reef Recognition
Abdulwahab Felemban, Yahia Battach, Faizan Farooq Khan +10
Coral reefs are rapidly declining under anthropogenic pressures (e.g., climate change), creating an urgent need for scalable and automated monitoring. Progress in data-driven coral…
FishNet++: Analyzing the capabilities of Multimodal Large Language Models in marine biology
Faizan Farooq Khan, Yousef Radwan, Eslam Abdelrahman +6
Multimodal large language models (MLLMs) have demonstrated impressive cross-domain capabilities, yet their proficiency in specialized scientific fields like marine biology remains…