RULER: Instance-aware Rubric Rewards for SVG Generation Paper • 2609.25270 • Published 18 days ago • 103
Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents Paper • 2609.17708 • Published 24 days ago • 78
CausalMix: Data Mixture as Causal Inference for Language Model Training Paper • 2607.01104 • Published Jul 1 • 20