Learning from Yesterday's Error: An Efficient Online Learning Method for Traffic Demand Prediction
arxiv
Meeting SLOs, Slashing Hours: Automated Enterprise LLM Optimization with OptiKIT
arxiv
Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning
arxiv
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
arxiv
The Key to State Reduction in Linear Attention: A Rank-based Perspective
arxiv