Submitted by Tianyu Fu 122 TokenRouter: Efficient Serving System for Token-Level LLM Routing Tsinghua-NICS-EFC 72 2
Submitted by Yichen You 62 Improving Test-Time Scaling with Adaptive Looped Transformers Tsinghua-NICS-EFC 107 2
Submitted by Tongcheng Fang 15 SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer Tsinghua-NICS-EFC 3
Submitted by Tianyu Fu 110 Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models Tsinghua-NICS-EFC 5
Submitted by Tianyu Fu 99 Cache-to-Cache: Direct Semantic Communication Between Large Language Models Tsinghua-NICS-EFC 766 9
Tianyu Fu 
