Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation Paper • 2603.12793 • Published Mar 13 • 38
Scaling Spatial Reasoning in MLLMs through Programmatic Data Synthesis Paper • 2512.16237 • Published Dec 18, 2025 • 2
LLMtimesMapReduce: Simplified Long-Sequence Processing using Large Language Models Paper • 2410.09342 • Published Oct 12, 2024 • 39
