LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding Paper โข 2410.17434 โข Published Oct 22 โข 25
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases Paper โข 2402.14905 โข Published Feb 22 โข 126
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything Paper โข 2312.00863 โข Published Dec 1, 2023 โข 4