8 papers
Accelerating Prefilling via Decoding-time Contribution Sparsity
Zhiyuan He, Yike Zhang, Chengruidong Zhang +3
Large Language Models (LLMs) incur quadratic attention complexity with input length, creating a major time bottleneck in the prefilling stage. Existing acceleration methods largely…
Joint Optimization of Handoff and Video Rate in LEO Satellite Networks
Kyoungjun Park, Zhiyuan He, Cheng Luo +4
Low Earth Orbit (LEO) satellite communication is a promising approach to providing Internet connectivity to users in many remote areas. As videos are likely to account for most tra…
ReMe: Scaffolding Personalized Cognitive Training via Controllable LLM-Mediated Conversations
Zilong Wang, Nan Chen, Luna K. Qiu +6
Global aging calls for scalable and engaging cognitive interventions. Computerized cognitive training (CCT) is a promising non-pharmacological approach, yet many unsupervised progr…
Optimize Replica Server Placement in a Satellite Network
Zhiyuan He, Yi Xu, Cheng Luo +2
Satellite communication offers Internet connectivity to remote locations, such as villages, deserts, mountains, and at sea. However, transmitting content over satellite networks is…
VL Norm: Rethink Loss Aggregation in RLVR
Zhiyuan He, Xufang Luo, Yike Zhang +2
We propose VL Norm (Variance-reduced Length-dependent Normalization), a simple yet effective loss aggregation method tailored to the characteristic of dynamic generation lengths in…
Dynamic Pacing for Real-time Satellite Traffic
Aashish Gottipati, Lili Qiu
Google's congestion control (GCC) has become a cornerstone for real-time video and audio communication, yet its performance remains fragile in emerging Low Earth Orbit (LEO) networ…