Avner May
9 papers · 2019–2025 · 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (20) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver
🧭
Keyword Pioneer
❓
The Questioner
Top co-authors
Research topics
Machine Learning
(7)
Artificial Intelligence
(6)
Application Areas
(6)
Core AI
(6)
Deep Learning
(3)
Natural Language Processing
(3)
Optimization & Theory · Machine Learning
(3)
Core Methods
(2)
Generation
(2)
Learning Types
(2)
Optimization & Theory · Deep Learning
(2)
Resources & Methods
(2)
Mathematics & Optimization
(1)
Speech & Audio
(1)
Learning Paradigms
(1)
Keywords
speculative decoding
(4)
model compression
(2)
inference acceleration
(2)
kernel approximation
(2)
word embedding
(2)
token generation
(2)
batch processing
(1)
masked language model
(1)
knowledge distillation
(1)
model inference
(1)
generalization bound
(1)
state space model
(1)
dynamic programming
(1)
language model
(1)
speech recognition
(1)
low-precision quantization
(1)
model serving
(1)
downstream performance
(1)
draft model
(1)
acoustic modeling
(1)
Papers
Cost-efficient Collaboration between On-device and Cloud Language Models
ICML 2025
MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding
ICLR 2025
Sequoia: Scalable and Robust Speculative Decoding
NeurIPS 2024
SpecExec: Massively Parallel Speculative Decoding For Interactive LLM Inference on Consumer Devices
NeurIPS 2024
The Mamba in the Llama: Distilling and Accelerating Hybrid Models
NeurIPS 2024
Contextual Embeddings: When Are They Worth It?
ACL 2020
Kernel Approximation Methods for Speech Recognition
JMLR 2019
Low-Precision Random Fourier Features for Memory-constrained Kernel Approximation
AISTATS 2019
On the Downstream Performance of Compressed Word Embeddings
NeurIPS 2019