Jonathan Ragan-Kelley
9 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (5) π Cross-Pollinator (9)
πΊοΈ
Taxonomy Completionist
(20)
π£
Hot Topic Early Bird
Conferences
ICML (3)
NIPS (3)
ICLR (2)
EMNLP (1)
Top co-authors
Keywords
large language model
(2)
model quantization
(1)
neural tangent kernel
(1)
feature learning
(1)
cognitive modeling
(1)
hyperparameter optimization
(1)
model architecture
(1)
efficient inference
(1)
efficient computing
(1)
model parallelism
(1)
distributed computing
(1)
feature space
(1)
gradient descent
(1)
monte carlo algorithm
(1)
kernel optimization
(1)
autoregressive model
(1)
convolutional neural network
(1)
memory efficiency
(1)
memory optimization
(1)
inference optimization
(1)
Papers
Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding
ICML 2025
Ladder-Residual: Parallelism-Aware Architecture for Accelerating Large Model Inference with Communication Overlapping
ICML 2025
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
NIPS 2024
Fast Matrix Multiplications for Lookup Table-Quantized LLMs
EMNLP 2024
The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning
ICLR 2024
Inferring the Future by Imagining the Past
NIPS 2023
Gradient Descent: The Ultimate Optimizer
NIPS 2022
Neural Kernels Without Tangents
ICML 2020
DiffTaichi: Differentiable Programming for Physical Simulation
ICLR 2020