MemSFT: Mitigating Alignment Tax with an External Parametric Memory Paper • 2607.25614 • Published Jul 28 • 23
Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory Paper • 2607.27919 • Published Jul 30 • 59
ConceptLM Collection The Collection of ConceptLM models and data, ConceptLM integrates Next-Concept-Prediction and Next-Token-Prediction. • 2 items • Updated Feb 3 • 5
FlowRL: Matching Reward Distributions for LLM Reasoning Paper • 2509.15207 • Published Sep 18, 2025 • 119