Chengzhong Xu
where else to find them
no profile links on file
what they talk about
where they keep going back
no series more than once — all 2 in the filters
on a stage with
- Li Li2×
- Chunlin Tianonce
- Dazhao Chengonce
all 13 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge | USENIX ATC '25 | 2025-07-07 |
Claims a combined algorithm–hardware co‑design that prunes and customizes LLMs to fit edge memory/energy budgets, implements a 28nm scalable accelerator with a… | ||
| AssyLLM: Efficient Federated Fine-tuning of LLMs via Assembling Pre-trained Blocks | USENIX ATC '25 | 2025-07-07 |
AssyLLM assembles pre-trained transformer blocks from multiple LLMs (LLaMA, OPT, etc.) so clients only run forward passes and upload block indices instead of… | ||
| Expeditious High-Concurrency MicroVM SnapStart in Persistent Memory with an... | USENIX ATC 2024 | 2024-07-10 |
PASS is a user-space augmented hypervisor that maps entire MicroVM snapshots into a single-tier Intel PMEM address space and implements zero-copy on-demand… | ||
| nothing matches | ||