PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models Paper • 2602.04029 • Published Feb 3 • 4
TokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token Pruning Paper • 2610.26754 • Published Oct 19 • 12
RT-J: Large-Scale Pretraining of Relational Transformers for Context-Efficient Predictions Paper • 2610.17867 • Published Oct 13 • 14
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
RT-J: Large-Scale Pretraining of Relational Transformers for Context-Efficient Predictions Paper • 2610.17867 • Published Oct 13 • 14
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement Paper • 2609.38721 • Published Sep 30 • 127
view article Article NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction nvidia • Sep 29 • 112