activity
20212026
most citedDomino: Discovering Systematic Errors with Cross-Modal Embeddings

39 citations · 44 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

MLPs are Hebbians: Constructing Efficient Fact-Storing MLPs for Transformers

Roberto Garcia, Jerry Liu, Ronny Junkins +3

Large language models (LLMs) store factual knowledge in their parameters. While recent work has shown that this knowledge resides in MLP layers, existing constructive and mechanist…

cs.LG2025

Constructing Efficient Fact-Storing MLPs for Transformers

Owen Dugan, Roberto Garcia, Ronny Junkins +5

The success of large language models (LLMs) can be attributed in part to their ability to efficiently store factual knowledge as key-value mappings within their MLP parameters. Rec…

cs.LG2025

Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA Adapters

Roberto Garcia, Jerry Liu, Daniel Sorvisto +1

Large Language Models (LLMs) are computationally intensive, particularly during inference. Neuron-adaptive techniques, which selectively activate neurons in Multi-Layer Perceptron…

cs.LG2025

Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models

Avanika Narayan, Dan Biderman, Sabri Eyuboglu +4

We investigate an emerging setup in which a small, on-device language model (LM) with access to local data communicates with a frontier, cloud-hosted LM to solve real-world tasks i…

cs.LG202314 cited

Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture

Daniel Y. Fu, Simran Arora, Jessica Grogan +7

Machine learning models are increasingly being scaled in both sequence length and model dimension to reach longer contexts and better performance. However, existing architectures s…

cs.LG202239 cited

Domino: Discovering Systematic Errors with Cross-Modal Embeddings

Sabri Eyuboglu, Maya Varma, Khaled Saab +5

Machine learning models that achieve high overall accuracy often make systematic errors on important subsets (or slices) of data. Identifying underperforming slices is particularly…