Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation Paper • 2603.12793 • Published 5 days ago • 35
Imagination Helps Visual Reasoning, But Not Yet in Latent Space Paper • 2602.22766 • Published 20 days ago • 42
LLMtimesMapReduce: Simplified Long-Sequence Processing using Large Language Models Paper • 2410.09342 • Published Oct 12, 2024 • 39