3 papers
cs.LG2026
Adapting Without Gradients: Affine Statistics Transport and What Its Certificate Can Tell You
Salim Khazem, Ibrahim Mohamed Serouis
Test-time adaptation (TTA) typically assumes that model parameters can be updated at inference time. This assumption is restrictive for inference-only accelerators, frozen or third…
cs.AI2026
Imag-Eval: a language-grounded framework for interpretable Text-to-Image instruction following evaluation
Ibrahim Mohamed Serouis, David Jaramillo Duque
Text-to-Image (T2I) models have recently achieved impressive visual fidelity, yet their evaluation remains constrained by benchmarks that are often difficult to interpret and insuf…
cs.CV2026
MC-RFM: Geometry-Aware Few-Shot Adaptation via Mixed-Curvature Riemannian Flow Matching
Salim Khazem, Ibrahim Mohamed Serouis, Zakaria Ezzahed
Parameter-efficient adaptation of pretrained vision models is commonly performed through linear probes, prompts, low-rank updates, or lightweight residual modules. While effective,…