Yue Yu
where else to find them
no profile links on file
what they talk about
all 7 in the filters
where they keep going back
no series more than once — all 5 in the filters
on a stage with
all 47 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Kairox: Adaptive GPU-CPU Hybrid LLM Inference via Online Neuron Balancing | 20th USENIX Symposium on Operating Systems Design and Implementation (OSDI '26) | 2026-07-13 |
Kairox is a GPU–CPU hybrid inference system that dynamically moves FFN neuron groups at runtime to trade CPU compute for PCIe transfers, implemented in ~6,000… | ||
| ParaSync: Exploiting Fine-Grained Parallelism for Efficient File Synchronization | FAST '26 | 2026-02-24 |
ParaSync breaks the CDC sync bottlenecks by (1) multi-threaded chunking that computes CRC32 per sub-chunk and merges checksums via checksum combination instead… | ||
| InSituTale: Enhancing Augmented Data Storytelling with Physical Objects | UIST 2025 | 2025-09-28 |
Prototype InSituTale enables presenters to manipulate visualizations by physically moving objects, claiming real-time augmented data storytelling with tangible… | ||
| DEEPSERVE: Serverless Large Language Model Serving at Scale | USENIX ATC '25 | 2025-07-07 |
DEEPSERVE is a serverless LLM platform that serves models on Huawei Ascend NPUs with a concrete request-job-task model abstraction, an in-house FLOWSERVE… | ||
| Obscura: Concealing Recomputation Overhead in Training of Large Language Models... | USENIX ATC '25 | 2025-07-07 |
Obscura is a pipeline training system that transforms the standard 1F1B schedule to shift forward work into unused forward bubbles and turn them into backward… | ||
| StreamBox: A Lightweight GPU SandBox for Serverless Inference Workflow | USENIX ATC 2024 | 2024-07-10 |
StreamBox replaces heavy per-function CUDA contexts with concurrent GPU streams plus an auto-scaling memory pool that profiles models offline, does lazy… | ||
| nothing matches | ||