RT-J: Large-Scale Pretraining of Relational Transformers for Context-Efficient Predictions Paper • 2610.17867 • Published 9 days ago • 2
360Brew: A Decoder-only Foundation Model for Personalized Ranking and Recommendation Paper • 2501.16450 • Published Aug 23, 2025
Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks Paper • 2606.00340 • Published May 29
Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation Paper • 2512.21002 • Published Dec 24, 2025
Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems Paper • 2502.14305 • Published Oct 26, 2025