Imagination Helps Visual Reasoning, But Not Yet in Latent Space Paper • 2602.22766 • Published 29 days ago • 42
HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing Paper • 2602.03560 • Published Feb 3 • 48
SLA2: Sparse-Linear Attention with Learnable Routing and QAT Paper • 2602.12675 • Published Feb 13 • 57
Next Embedding Prediction Makes World Models Stronger Paper • 2603.02765 • Published 24 days ago • 20
view article Article NEO-unify: Building Native Multimodal Unified Models End to End 22 days ago • 104