collaborators

6 papers

cs.LG2026

Thermodynamic Signatures of Reasoning: Free-Energy and Spectral-Form-Factor Diagnostics for Hallucination Detection in Large Language Models

Salim Khazem

Hallucination detection in large language models (LLMs) is deployment-critical, and recent work shows that the spectrum of attention-derived graph Laplacians carries strong signal…

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,…

cs.CV2026

AdapterTune: Zero-Initialized Low-Rank Adapters for Frozen Vision Transformers

Salim Khazem

Frozen-backbone transfer with Vision Transformers faces two under-addressed issues: optimization instability when adapters are naively inserted into a fixed feature extractor, and…

cs.CV2026

Margin and Consistency Supervision for Calibrated and Robust Vision Models

Salim Khazem

Deep vision classifiers often achieve high accuracy while remaining poorly calibrated and fragile under small distribution shifts. We present Margin and Consistency Supervision (Ma…

cs.LG2026

SAFE-KD: Risk-Controlled Early-Exit Distillation for Vision Backbones

Salim Khazem

Early-exit networks reduce inference cost by allowing ``easy'' inputs to stop early, but practical deployment hinges on knowing \emph{when} early exit is safe. We introduce SAFE-KD…

cs.CV2026

TopoLoRA-SAM: Topology-Aware Parameter-Efficient Adaptation of Foundation Segmenters for Thin-Structure and Cross-Domain Binary Semantic Segmentation

Salim Khazem

Foundation segmentation models such as the Segment Anything Model (SAM) exhibit strong zero-shot generalization through large-scale pretraining, but adapting them to domain-specifi…