← Authors

Albert Gu

32 papers · 2018–2025 · 5 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (8) πŸŒ‰ Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (12) 🧭 Keyword Pioneer πŸ—ΊοΈ Taxonomy Completionist (43) 🌍 Conference Polyglot (5) πŸƒ Academic Marathon (7) 🧬 Topic Evolution πŸ‘‘ Triple Crown πŸ† Keyword Champion (5) 🀝 Dynamic Duo (18) πŸ—ƒοΈ Keyword Collector (92) ⚑ Prolific Year (5) πŸ’Ž Century Club (32) πŸ”₯ Unstoppable (8) πŸ“ˆ Trend Setter

Conferences

ICML (12) NIPS (11) ICLR (7) EMNLP (1) NAACL (1)

Top co-authors

Christopher Re (18) Tri Dao (11) Karan Goel (7) Atri Rudra (6) Razvan Pascanu (2) Ines Chami (2) Isys Johnson (2) Matthew Eichhorn (2) Ankit Gupta (2) Caglar Gulcehre (2)

Research topics

Models (1)

Keywords

state space model (6) sequence modeling (5) recurrent neural network (5) sequence model (3) model architecture (3) state-space model (3) model compression (3) dimensionality reduction (2) representation learning (2) long-range dependency (2) hyperbolic embedding (2) parallel training (2) long sequence modeling (2) long-range dependencies (2) data augmentation (1) knowledge distillation (1) attention mechanism (1) video classification (1) structured matrix (1) principal component analysis (1)

Papers

Understanding and Improving Length Generalization in Recurrent Models ICML 2025
Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism ICML 2025
On the Benefits of Memory for Modeling Time-Dependent PDEs ICLR 2025
Towards Codec-LM Co-design for Neural Codec Language Models NAACL 2025
Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers NIPS 2024
Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models NIPS 2024
Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling ICML 2024
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality ICML 2024
How to Train your HIPPO: State Space Models with Generalized Orthogonal Basis Projections ICLR 2023
Structured State Space Models for In-Context Reinforcement Learning NIPS 2023
Pretraining Without Attention EMNLP 2023
Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN ICLR 2023
Resurrecting Recurrent Neural Networks for Long Sequences ICML 2023
Efficiently Modeling Long Sequences with Structured State Spaces ICLR 2022
On the Parameterization and Initialization of Diagonal State Space Models NIPS 2022
Diagonal State Spaces are as Effective as Structured State Spaces NIPS 2022
S4ND: Modeling Images and Videos as Multidimensional Signals with State Spaces NIPS 2022
It’s Raw! Audio Generation with State-Space Models ICML 2022
HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projections ICML 2021
Catformer: Designing Stable Transformers via Sensitivity Analysis ICML 2021
Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers NIPS 2021
Model Patching: Closing the Subgroup Performance Gap with Data Augmentation ICLR 2021
Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps ICLR 2020
From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering NIPS 2020
Improving the Gating Mechanism of Recurrent Neural Networks ICML 2020
HiPPO: Recurrent Memory with Optimal Polynomial Projections NIPS 2020
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems NIPS 2020
Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations ICML 2019
A Kernel Theory of Modern Data Augmentation ICML 2019
Learning Mixed-Curvature Representations in Product Spaces ICLR 2019
Representation Tradeoffs for Hyperbolic Embeddings ICML 2018
Learning Compressed Transforms with Low Displacement Rank NIPS 2018