Atri Rudra
17 papers · 2018–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π Academic Marathon (7) π Cross-Pollinator (14) π Interdisciplinary Bridge π Conference Polyglot (3) πΊοΈ Taxonomy Completionist (20)
π
Conference Polyglot
(3)
π
Academic Marathon
(7)
π€
Dynamic Duo
(17)
π
Triple Crown
π§¬
Topic Evolution
β‘
Prolific Year
(5)
π₯
Unstoppable
(8)
π
Century Club
(17)
ποΈ
Keyword Collector
(54)
π
Trend Setter
Conferences
NIPS (7)
ICLR (6)
ICML (4)
Top co-authors
Keywords
model compression
(4)
sequence model
(3)
attention mechanism
(3)
structured matrix
(2)
recurrent neural network
(2)
neural network
(2)
language modeling
(2)
model architecture
(2)
matrix approximation
(1)
time series
(1)
knowledge distillation
(1)
locality sensitive hashing
(1)
low-rank approximation
(1)
kernel smoothing
(1)
computational efficiency
(1)
state-space model
(1)
state space model
(1)
sparse matrix
(1)
temporal dependencies
(1)
efficient computing
(1)
Papers
Towards Learning High-Precision Least Squares Algorithms with Sequence Models
ICLR 2025
Zoology: Measuring and Improving Recall in Efficient Language Models
ICLR 2024
Simple linear attention language models balance the recall-throughput tradeoff
ICML 2024
How to Train your HIPPO: State Space Models with Generalized Orthogonal Basis Projections
ICLR 2023
Hungry Hungry Hippos: Towards Language Modeling with State Space Models
ICLR 2023
Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions
NIPS 2023
Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture
NIPS 2023
Simple Hardware-Efficient Long Convolutions for Sequence Modeling
ICML 2023
Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models
ICLR 2022
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
NIPS 2022
Monarch: Expressive Structured Matrices for Efficient and Accurate Training
ICML 2022
Scatterbrain: Unifying Sparse and Low-rank Attention
NIPS 2021
Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers
NIPS 2021
Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps
ICLR 2020
HiPPO: Recurrent Memory with Optimal Polynomial Projections
NIPS 2020
Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations
ICML 2019
Learning Compressed Transforms with Low Displacement Rank
NIPS 2018