TAAFT
Free mode
100% free
Freemium
Free Trial
Deals

Papers

Filter by company
  • Robust Post-Training for Generative Recommenders: Why Exponential Reward-Weighted SFT Outperforms RLHF
    Meta Platforms, Netflix / Stanford University
    Published on: 2026-03-10 5 authors
0 AIs selected
Clear selection
#
Name
Task