VideoRoPE: What Makes for Good Video Rotary Position Embedding? Paper โข 2502.05173 โข Published 4 days ago โข 57
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions Paper โข 2412.09596 โข Published Dec 12, 2024 โข 94
All the ImageNets Collection Noteworthy instances of ImageNet on the Hub. Vetted and tested with timm train and validation scripts. โข 8 items โข Updated Nov 21, 2024 โข 6
Addition is All You Need for Energy-efficient Language Models Paper โข 2410.00907 โข Published Oct 1, 2024 โข 145
Running on CPU Upgrade 4.74k 4.74k MTEB Leaderboard ๐ฅ Select and filter benchmarks for text embedding tasks