4 papers
LeanStream: A Speculate-and-Refine Streaming Framework for Efficient on-Device LLM Inference
Renyuan Liu, Yuyang Leng, Kaiyan Liu +7
On-device LLM inference is attractive for privacy and responsiveness, but remains challenging on mobile and embedded devices because model weights far exceed available DRAM. Prior…
Physical Self-Supervised Learning: IMU Sensing without Manual Labels
Yuyang Leng, Renyuan Liu, Shaohan Hu +4
Deep neural networks have become a promising approach for IMU-based sensing, but their scalability is fundamentally limited by costly labeled data and poor robustness to heterogene…
TokenFlow: Responsive LLM Text Streaming Serving under Request Burst via Preemptive Scheduling
Junyi Chen, Chuheng Du, Renyuan Liu +6
Real-time LLM interactions demand streamed token generations, where text tokens are progressively generated and delivered to users while balancing two objectives: responsiveness (i…
DAF: An Efficient End-to-End Dynamic Activation Framework for on-Device DNN Training
Renyuan Liu, Yuyang Leng, Kaiyan Liu +6
Recent advancements in on-device training for deep neural networks have underscored the critical need for efficient activation compression to overcome the memory constraints of mob…