A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
This paper systematically evaluates six training-free sparse attention methods for transformer LLMs, proposing a taxonomy along four design axes and deriving actionable insights.
Unknown
Proposes a retraining-free model quantization method using one-shot weight-coupling learning to achieve efficient compression without fine-tuning.
Hao Liu, Chenghuan Huang, Ye Huang, et al.
FVAttn is a training-free sparse-attention system that uses runtime load balancing and slack-aware augmentation to improve distributed execution efficiency for video generation.