3 papers
cs.LG2026
TAME: Token Attribution and Masking for Emergent misalignment
Md Rayhanul Masud, Md Rizwan Parvez
Fine-tuning an aligned language model on narrow, flawed data can induce harmful behavior far outside the training domain, known as emergent misalignment (EM). Prior work has locali…
cs.SE2026
Reward Engineering for Software Tasks: A Survey of Reinforcement Learning Approaches
Md Rayhanul Masud, Azmine Toushik Wasi, Salman Rahman +1
Reinforcement learning is increasingly used for code-centric software engineering tasks, including code generation, understanding, repair, testing, and optimization, especially wit…
cs.SE2024
Unveiling A Hidden Risk: Exposing Educational but Malicious Repositories in GitHub
Md Rayhanul Masud, Michalis Faloutsos
Are malicious repositories hiding under the educational label in GitHub? Recent studies have identified collections of GitHub repositories hosting malware source code with notable…