KDD 2025 - ResMoE: Space efficient Compression of Mixture of Experts LLMs via Residual Restoration
About this video
Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidenceResMoE: space-efficient compression of mixture-of-experts LLMs via residual restoration. Teaches model compression technique for large language models.
A 3-minute video from Association for Computing Machinery (ACM): “KDD 2025 - ResMoE: Space efficient Compression of Mixture of Experts LLMs via Residual Restoration”.
Video by Association for Computing Machinery (ACM), played through YouTube's embedded player.