IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations Paper β’ 2412.12083 β’ Published 2 days ago β’ 12
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions Paper β’ 2412.09596 β’ Published 6 days ago β’ 87
PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction Paper β’ 2410.17247 β’ Published Oct 22 β’ 45
MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models Paper β’ 2410.17637 β’ Published Oct 23 β’ 34
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree Paper β’ 2410.16268 β’ Published Oct 21 β’ 65
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output Paper β’ 2407.03320 β’ Published Jul 3 β’ 93