Yuanda Wang

Yuanda Wang

I received my B.E. degree from Beijing University of Posts and Telecommunications(BUPT), Beijing, China, in 2024. I am currently working toward the master’s degree at Peking University. My research interest include system security and AI for security.

BDLF-Qwen3: Enhanced Cross-Architecture Binary Function Similarity Detection Through Binary Dynamic Layer Fusion

Published in The Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), 2026

BDLF-Qwen3 dynamically fuses multi-layer Qwen3-Embedding representations for cross-architecture binary similarity detection. Powered by a two-stage training strategy and the novel Cross-Bin dataset, it significantly outperforms existing methods at scale and demonstrates robust zero-shot generalization on unseen RISC-V architectures.

Recommended citation: Y Wang, J Zhou, X Han, C Zhang. (2026). "BDLF-Qwen3: Enhanced Cross-Architecture Binary Function Similarity Detection Through Binary Dynamic Layer Fusion." The Fortieth AAAI Conference on Artificial Intelligence (AAAI-26).
Download Paper