71 citations · 133 across the 5 of their papers we have counts for
6 papers
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
The Shapley Taylor Interaction Index
Kedar Dhamdhere, Ashish Agarwal, Mukund Sundararajan
The attribution problem, that is the problem of attributing a model's prediction to its base features, is well-studied. We extend the notion of attribution to also apply to feature…
How Important Is a Neuron?
Kedar Dhamdhere, Mukund Sundararajan, Qiqi Yan
The problem of attributing a deep network's prediction to its \emph{input/base} features is well-studied. We introduce the notion of \emph{conductance} to extend the notion of attr…
Did the Model Understand the Question?
Pramod Kaushik Mudrakarta, Ankur Taly, Mukund Sundararajan +1
We analyze state-of-the-art deep learning models for three tasks: question answering on (1) images, (2) tables, and (3) passages of text. Using the notion of \emph{attribution} (wo…
It was the training data pruning too!
Pramod Kaushik Mudrakarta, Ankur Taly, Mukund Sundararajan +1
We study the current best model (KDG) for question answering on tabular data evaluated over the WikiTableQuestions dataset. Previous ablation studies performed against this model a…
Abductive Matching in Question Answering
Kedar Dhamdhere, Kevin S. McCurley, Mukund Sundararajan +1
We study question-answering over semi-structured data. We introduce a new way to apply the technique of semantic parsing by applying machine learning only to provide annotations th…