AISurfingShort, clear updates with the original source one click away
← Back to brief
Research→Official→Preprint→arXiv Software Engineering

RepTran: Search-Based Repair of Transformer Models

Jul 14, 2026

Researchers introduce RepTran, a search-based method designed to repair Transformer models by focusing on their feed-forward networks. RepTran identifies suspicious weights using a combination of variance-based and bidirectional scores, then optimizes these weights through differential evolution. Evaluated on 18 fault benchmarks derived from CIFAR-100 and Tiny-ImageNet, RepTran achieved a 74.7% average repair rate, statistically outperforming existing DNN repair methods such as Arachne.

Why it matters: This work presents a novel approach for automated repair of Transformer models, potentially improving the reliability of AI-enabled software systems.

Full story at: arXiv Software Engineering ↗

Related coverage

FlowGuard: Evidence-Grounded Security Detection for MCP InteractionsFully Automated End-to-End Adversary Emulation from MITRE ATT&CK-Based Cyber Threat Intelligence Using LLMsRouting Ceilings Are Domain-Independent: Structural Prior Injection in Code Security Vulnerability Detection