most citedMonarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture

14 citations · 18 across the 3 of their papers we have counts for

collaborators

10 papers

cs.LG2024

State-Free Inference of State-Space Models: The Transfer Function Approach

Rom N. Parnichkun, Stefano Massaroli, Alessandro Moro +10

We approach designing a state-space model for deep learning applications through its dual representation, the transfer function, and uncover a highly efficient sequence parallel in…

cs.LG2024

Mechanistic Design and Scaling of Hybrid Architectures

Michael Poli, Armin W Thomas, Eric Nguyen +9

The development of deep learning architectures is a resource-demanding process, due to a vast design space, long prototyping times, and high compute costs associated with at-scale…

cs.LG20243 cited

The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry

Michael Zhang, Kush Bhatia, Hermann Kumbong +1

Linear attentions have shown potential for improving Transformer efficiency, reducing attention's quadratic complexity to linear in sequence length. This holds exciting promise for…

cs.CL2024

Simple linear attention language models balance the recall-throughput tradeoff

Simran Arora, Sabri Eyuboglu, Michael Zhang +6

Recent work has shown that attention-based language models excel at recall, the ability to ground generations in tokens previously seen in context. However, the efficiency of atten…

cs.LG2024

Prospector Heads: Generalized Feature Attribution for Large Models & Data

Gautam Machiraju, Alexander Derry, Arjun Desai +6

Feature attribution, the ability to localize regions of the input data that are relevant for classification, is an important capability for ML models in scientific and biomedical d…

cs.IR2024

Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT

Jon Saad-Falcon, Daniel Y. Fu, Simran Arora +2

Retrieval pipelines-an integral component of many machine learning systems-perform poorly in domains where documents are long (e.g., 10K tokens or more) and where identifying the r…