Author

Mahyar Fazlyab

3 papers indexed here

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 Sep 2026

Anytime-Feasible Gradient Descent for Constrained Optimization Under Gradient Uncertainty

Constrained optimization is central to many engineering systems in which decisions must satisfy strict safety and operational requirements, especially in real-time settings with limited computational budgets. In such scenarios, optimization algorithms are often terminated before full convergence, making *anytime feasib...

Sina Sharifi, Jiarui Wang, Mahyar Fazlyab · 0 citations

#artificial intelligence Preprint Sep 2026

Minimally Invasive Steering of Language Models

Minimally Invasive Steering Vector Optimization (MISVO), which penalizes interventions using the local KL geometry of the induced token distribution, achieves the highest mean reward in six of seven model--task settings, with diversity and coherence scores close to those of Best-of-N.

Taha Entesari, Jingyu (Jack) Zhang, Daniel Khashabi et al. · 0 citations

#artificial intelligence Preprint Sep 2026

Beyond Average Safety: Chance-Constrained LLM Fine-tuning

This work proposes a chance-constrained formulation for safety-preserving fine-tuning that limits the fraction of safety examples whose degradation relative to a reference model exceeds a prescribed threshold and develops a constraint-aware gradient descent method that treats the majorized constraint as a safe set in p...

Taha Entesari, Mahyar Fazlyab · 0 citations