6 papers
Functional compatibility as a determinant of persistent neural learning
Hossein Javidnia
Neural networks can acquire new capabilities while damaging existing ones, but what determines whether new learning persists remains unclear. We identify functional compatibility,…
Semantic Sections: An Atlas-Native Feature Ontology for Obstructed Representation Spaces
Hossein Javidnia
Recent interpretability work often treats a feature as a single global direction, dictionary atom, or latent coordinate shared across contexts. We argue that this ontology can fail…
A Gauge Theory of Superposition: Toward a Sheaf-Theoretic Atlas of Neural Representations
Hossein Javidnia
We develop a discrete gauge-theoretic framework for superposition in large language models (LLMs) that replaces the single-global-dictionary premise with a sheaf-theoretic atlas of…
Multi-scale Attention-Guided Intrinsic Decomposition and Rendering Pass Prediction for Facial Images
Hossein Javidnia
Accurate intrinsic decomposition of face images under unconstrained lighting is a prerequisite for photorealistic relighting, high-fidelity digital doubles, and augmented-reality e…
Benchmarking Microsaccade Recognition with Event Cameras: A Novel Dataset and Evaluation
Waseem Shariff, Timothy Hanley, Maciej Stec +2
Microsaccades are small, involuntary eye movements vital for visual perception and neural processing. Traditional microsaccade studies typically use eye trackers or frame-based ana…
Leveraging AV1 motion vectors for Fast and Dense Feature Matching
Julien Zouein, Hossein Javidnia, François Pitié +1
We repurpose AV1 motion vectors to produce dense sub-pixel correspondences and short tracks filtered by cosine consistency. On short videos, this compressed-domain front end runs c…