Alexey Tumanov
9 papers · 2016–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (15) 🐣 Hot Topic Early Bird
🧬
Topic Evolution
🌈
Renaissance Researcher
(7)
🗃️
Keyword Collector
(54)
📈
Trend Setter
Top co-authors
Research topics
Machine Learning
(7)
Application Areas
(6)
Optimization & Theory
(4)
Computer Science
(3)
Deep Learning
(3)
Systems
(3)
Artificial Intelligence
(2)
Architectures
(2)
Core AI
(2)
Computer Vision
(1)
Data Science & Analytics
(1)
Healthcare & Medicine
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Applications
(1)
Keywords
neural architecture search
(2)
uncertainty quantification
(1)
model deployment
(1)
weight sharing
(1)
distributed computing
(1)
model serving
(1)
cascade classifier
(1)
resource allocation
(1)
latency-accuracy tradeoff
(1)
disease detection
(1)
multi-objective optimization
(1)
convolutional neural network
(1)
memory efficiency
(1)
cost-aware learning
(1)
knowledge distillation
(1)
kv cache compression
(1)
request scheduling
(1)
inference serving
(1)
reinforcement learning
(1)
federated learning
(1)
Papers
RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression
ICML 2025
SuperServe: Fine-Grained Inference Serving for Unpredictable Workloads
NSDI 2025
DεpS: Delayed ε-Shrinking for Faster Once-For-All Training
ECCV 2024
SuperFedNAS: Cost-Efficient Federated Neural Architecture Search for On-Device Inference
ECCV 2024
Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve
OSDI 2024
UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification
NeurIPS 2022
CompOFA – Compound Once-For-All Networks for Faster Multi-Platform Deployment
ICLR 2021
Ray: A Distributed Framework for Emerging AI Applications
OSDI 2018
Morpheus: Towards Automated SLOs for Enterprise Clusters
OSDI 2016