168 citations · 503 across the 25 of their papers we have counts for
6 papers · 1 filter
Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation
Ziqi Wang, Yuexin Wu, Frederick Liu +5
Knowledge distillation is one of the primary methods of transferring knowledge from large to small models. However, it requires massive task-specific data, which may not be plausib…
DETR++: Taming Your Multi-Scale Detection Transformer
Chi Zhang, Lijuan Liu, Xiaoxue Zang +4
Convolutional Neural Networks (CNN) have dominated the field of detection ever since the success of AlexNet in ImageNet classification [12]. With the sweeping reform of Transformer…
Chefs' Random Tables: Non-Trigonometric Random Features
Valerii Likhosherstov, Krzysztof Choromanski, Avinava Dubey +3
We introduce chefs' random tables (CRTs), a new class of non-trigonometric random features (RFs) to approximate Gaussian and softmax kernels. CRTs are an alternative to standard ra…
Towards Tracing Factual Knowledge in Language Models Back to the Training Data
Ekin Akyürek, Tolga Bolukbasi, Frederick Liu +4
Language models (LMs) have been shown to memorize a great deal of factual knowledge contained in their training data. But when an LM generates an assertion, it is often difficult t…
Threading the Needle of On and Off-Manifold Value Functions for Shapley Explanations
Chih-Kuan Yeh, Kuan-Yun Lee, Frederick Liu +1
A popular explainable AI (XAI) approach to quantify feature importance of a given model is via Shapley values. These Shapley values arose in cooperative games, and hence a critical…
First is Better Than Last for Language Data Influence
Chih-Kuan Yeh, Ankur Taly, Mukund Sundararajan +2
The ability to identify influential training examples enables us to debug training data and explain model behavior. Existing techniques to do so are based on the flow of training d…