Deep Fusion Memory: A Chunk-Level Parametric Memory for Large Language Models Paper • 2610.25100 • Published 14 days ago • 55
LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation Paper • 2610.19975 • Published 18 days ago • 78
Compass-Embedding v4: Robust Contrastive Learning for Multilingual E-commerce Embeddings Paper • 2601.11565 • Published Dec 25, 2025 • 1
NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction Paper • 2609.10715 • Published Sep 9 • 182
MemSFT Collection Official collection of models and resources for the MemSFT project. • 6 items • Updated Aug 1 • 5
FlowRL: Matching Reward Distributions for LLM Reasoning Paper • 2509.15207 • Published Sep 18, 2025 • 119