Junchen Jiang
where else to find them
linkedin:junchen-jiang-13b8581a
what they talk about
all 10 in the filters
where they keep going back
- NSDI2 editions2019–2023
all 10 in the filters
on a stage with
all 82 in the filters
who talks about the same things
- Yue Zhu2 talks
- Yihua Cheng5 talks
- Yuhan Liu5 talks
- Maroon Ayoub5 talks
- Ziwen Ning2 talks
- Joinal Ahmed6 talks
| title | conference | date |
|---|---|---|
| DroidSpeak: KV Cache Sharing Across Fine-tuned Model Variants | NSDI '26 | 2026-05-04 |
DroidSpeak enables KV cache reuse across fine‑tuned variants of the same architecture by profiling model pairs to find a small set of critical layers (about… | ||
| LMCache: Lower LLM Performance Costs in the Enterprise | Cloud Native + Kubernetes AI Day North America 2025 | 2025-11-10 |
Claims a practical open source KV-cache layer that reduces Time to First Token and increases throughput by reusing attention tensors instead of recomputing… | ||
| Scalable and Efficient LLM Serving With the VLLM Production Stack | Open Source Summit North America 2025 | 2025-06-23 |
Open source vLLM Production Stack combines vLLM Production Stack router, an LMCache KV cache backend, Kubernetes + Helm deployment and SkyPilot for cross‑cloud… | ||
| Holmes: Localizing Irregularities in LLM Training with Mega-scale GPU Clusters | NSDI '25 | 2025-04-28 |
Holmes localizes slow or spiky iterations in multi‑thousand GPU LLM training by logging only communication operators, classifying abnormal operators with a… | ||
| ChameleonAPI: Automatic and Efficient Customization of Neural Networks for ML... | 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI '24) | 2024-07-10 |
Paper builds ChameleonAPI that parses app code to extract a decision-making summary, then uses it to construct an application-specific loss function and… | ||
| GRACE: Loss-Resilient Real-Time Video through Neural Codecs | 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI '24) | 2024-04-16 |
A neural video codec that jointly trains encoder and decoder under simulated packet losses and randomly zeroed tensor partitions yields graceful quality… | ||
| ARTEMIS: Adaptive Bitrate Ladder Optimization for Live Video Streaming | 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI '24) | 2024-04-16 |
System implements a cloud service that advertises a mega manifest of many candidate bitrate-resolution pairs, collects CDN logs and encoder quality metrics… | ||
| Towards Domain-Specific Network Transport for Distributed DNN Training | 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI '24) | 2024-04-16 |
MLT is a domain-specific transport for distributed DNN training that implements a 3-step progressive scheme: (1) per-packet load balancing across multiple… | ||
| Run-Time Prevention of Software Integration Failures of Machine Learning APIs | OOPSLA 2023 | 2023-10-23 |
SmartGear is a run-time adapter that sits between ML cloud APIs and application code, inserted via bytecode instrumentation, that detects… | ||
| RECL: Responsive Resource-Efficient Continuous Learning for Video Analytics | NSDI 2023 | 2023-04-17 |
System integrates a shared model zoo of previously adapted lightweight experts, a learned model selector that predicts per-frame accuracy and aggregates… | ||
| Privid: Practical, Privacy-Preserving Video Analytics Queries | 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI '22) | 2022-04-04 |
Privid defines ρ,K,ε-event-duration privacy and enforces it by splitting video into chunks, running analyst-provided black-box neural nets per chunk, then… | ||
| Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers | 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI '22) | 2022-04-04 |
Edge servers run compressed video models that drift with live data; Ekya continuously retrains selected models and schedules GPU time to maximize mean… | ||
| SENSEI: Aligning Video Streaming Quality with Dynamic User Sensitivity | NSDI ’21 | 2021-04-12 |
Shows that per-video crowdsourced sensitivity profiles let adaptation trade short-term rebuffering for higher quality at important moments, implemented in a… | ||
| Preview Sessions | NSDI 2019 | 2019-02-26 |
Ten-minute rapid tour that names concrete problems, numbers and fixes: NICs hit 120 ns per 100Gb packet so CPU cycles matter; kernel bypass shows a tradeoff… | ||
| nothing matches | ||