BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning
Paper • 2603.04124 • Published • 1
Tarjei Paule Hage
tphage
AI & ML interests
Graduate student and Aker Scholar at MIT
Recent Activity
authored a paper about 1 month ago
BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning updated a dataset about 1 month ago
tphage/AMC-23 published a dataset about 1 month ago
tphage/AMC-23Organizations
authored a
paper about 1 month ago