KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Augmentations and Constraints Paper β’ 2510.19316 β’ Published Oct 22, 2025 β’ 12 β’ 3
Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models Paper β’ 2511.02650 β’ Published Nov 4, 2025 β’ 10 β’ 1
MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models Paper β’ 2510.19457 β’ Published Oct 22, 2025 β’ 9 β’ 2
KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Augmentations and Constraints Paper β’ 2510.19316 β’ Published Oct 22, 2025 β’ 12 β’ 3
MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge Paper β’ 2502.19870 β’ Published Feb 27, 2025 β’ 9 β’ 2