2 citations · 3 across the 6 of their papers we have counts for
3 papers · 1 filter
Only Project Once: Projection-Adaptive Loss for Exact Constraint Satisfaction
Tim Aebersold, Soheyl Massoudi, Mark Fuge
Precise constraint satisfaction is a prerequisite to deploying learned models in many areas, motivating methods that repair raw neural predictions with a repair procedure. Current…
Conditional Flow Matching for ML-Based Inverse Design Problems
Juliana Felder, Milad Habibi, Soheyl Massoudi +1
Engineering inverse design is often limited by the high computational cost of iterative solvers for optimization problems constrained by partial differential equations (PDEs) and b…
Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers
Soheyl Massoudi, Gabriel Apaza, Milad Habibi +1
Large language models (LLMs) typically approach combinatorial optimization as an inference-time procedure, solving each instance separately through sampling, search, or repeated pr…