2 papers
cs.LG2026
CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits
Mehrshad Saadatinia, Parsa Razmara, Ardalan Aryashad +2
Controlling the behavior of large language models (LLMs) remains a critical challenge for AI alignment. Existing steering methods, such as Contrastive Activation Addition (CAA), ty…
cs.CV2026
From Filters to VLMs: Benchmarking Defogging Methods through Object Detection and Segmentation Performance
Ardalan Aryashad, Parsa Razmara, Amin Mahjoub +3
Autonomous driving perception systems are particularly vulnerable in foggy conditions, where light scattering reduces contrast and obscures fine details critical for safe operation…