Publications and manuscripts
Selected work on efficient LLM inference and serving systems. See Google Scholar for the full publication record.
Rethinking KV Cache Eviction for Agentic LLM Serving
Jiakun Fan, Han Meng, Yuxuan Xia, Hao Mark Chen, Dong Li, Dimitrios S. Nikolopoulos.
Athanor: An Agent-Native System for Autonomous Post-Training Research
Yufa Zhou, Yichen Wang, Jiakun Fan, et al.
Factorization-Guided Training and Inference for Diffusion-Drafted Speculative Decoding
Jiakun Fan, Min Xiao, et al.
dLLM-Serve: Bridging the Memory Gap in Diffusion Language Model Serving
Jiakun Fan, Yanglin Zhang, Xiangchen Li, Dimitrios S. Nikolopoulos.
APEX: Asynchronous Parallel CPU-GPU Execution for Online LLM Inference on Constrained GPUs
Jiakun Fan, Yanglin Zhang, Xiangchen Li, Dimitrios S. Nikolopoulos.
WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching
Xiangchen Li, Jiakun Fan, et al.
SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving
Xiangchen Li, Dimitrios Spatharakis, Saeid Ghafouri, Jiakun Fan, et al.