Author

Mert D. Pesé

h-index 2 View on Semantic Scholar

We have 3 of 18 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

GATE: Reliability-Gated Gaussian Evidence Fusion for Training-Free Test-Time Adaptation of Vision-Language Models

GATE is introduced, a training-free two-pass transductive test-time adaptation framework that uses the unlabeled target set while keeping the image encoder, text encoder, and prompt parameters fully frozen, and demonstrates the benefit of reliability-gated distributional evidence for frozen VLM adaptation.

Pedram MohajerAnsari, Amir Salarpour, Run-Min Wang et al. · 0 citations

Jul 2026

Adversarial Prompts for Acceptance Collapse in Speculative Decoding

ADSD is introduced, which is the first prompt-suffix attack that collapses verifier acceptance by pushing draft probability mass toward tokens the target is unlikely to accept, and successfully generates highly effective adversarial suffixes.

Run-Min Wang, Chaoyi Zhou, Xi Liu et al. · arXiv.org · 0 citations

Preprint Aug 2026

Distilling Vision-Language Models for Robust Traffic Sign Perception in Autonomous Vehicles

Evaluated on GTSRB and LISA across four backbones and three physical attack types, LAMDA is the only method among ten evaluated that consistently improves robustness across all attack-backbone-dataset combinations, while preserving or improving clean accuracy in nearly all cases.

Pedram MohajerAnsari, Amir Salarpour, M. Pesé · 0 citations