FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution Paper • 2608.16157 • Published 5 days ago • 74
ProxSparse: Regularized Learning of Semi-Structured Sparsity Masks for Pretrained LLMs Paper • 2502.00258 • Published Feb 1, 2025 • 1
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models Paper • 2503.16419 • Published Mar 20, 2025 • 77