Igor Fedorov
8 papers · 2019–2026 · 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (14) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver
🧬
Topic Evolution
🔥
Unstoppable · Bronze
Top co-authors
Research topics
Machine Learning
(6)
Application Areas
(6)
Deep Learning
(5)
Artificial Intelligence
(4)
Core AI
(4)
Architectures
(3)
Optimization & Theory · Machine Learning
(3)
Optimization & Theory · Deep Learning
(3)
Learning Types · Machine Learning
(2)
Computer Science
(1)
Natural Language Processing
(1)
Speech & Audio
(1)
Generation
(1)
Learning Types · Deep Learning
(1)
Synthesis
(1)
Keywords
model compression
(4)
neural architecture search
(2)
large language model
(2)
model architecture
(1)
efficient computing
(1)
speech enhancement
(1)
embedding sharing
(1)
neural architecture
(1)
model pruning
(1)
weight sharing
(1)
convolutional neural network
(1)
long short-term memory
(1)
recurrent neural network
(1)
edge device
(1)
weight quantization
(1)
inference latency
(1)
edge inference
(1)
model sparsity
(1)
architecture search
(1)
memory constraint
(1)
Papers
MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment
ACL 2026
SpinQuant: LLM Quantization with Learned Rotations
ICLR 2025
DεpS: Delayed ε-Shrinking for Faster Once-For-All Training
ECCV 2024
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
ICML 2024
Efficient Edge Inference by Selective Query
ICLR 2023
UDC: Unified DNAS for Compressible TinyML Models for Neural Processing Units
NeurIPS 2022
TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids
Interspeech 2020
SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
NeurIPS 2019