How Fast Can Reward Models Score? A Systems Study of C++ and PyTorch Inference Runtimes for RLHF
Paper • 2607.19712 • Published • 3
Maëline Lefebvre
maelinel
AI & ML interests
Alignment-focused model research. Interested in robust deployment.
Recent Activity
upvoted a paper about 22 hours ago
How Fast Can Reward Models Score? A Systems Study of C++ and PyTorch Inference Runtimes for RLHF upvoted a paper 1 day ago
Progress Reward Modeling for Robotic Learning: A Comprehensive Survey upvoted a paper 7 days ago
Distilled Reinforcement Learning for LLM Post-trainingOrganizations
None yet