Picture for Pratyush Maini

Pratyush Maini

LLM Dataset Inference: Did you train on my dataset?

Add code
Jun 10, 2024
Viaarxiv icon

Rethinking LLM Memorization through the Lens of Adversarial Compression

Add code
Apr 23, 2024
Viaarxiv icon

Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic

Add code
Apr 10, 2024
Figure 1 for Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic
Figure 2 for Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic
Figure 3 for Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic
Figure 4 for Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic
Viaarxiv icon

Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling

Add code
Jan 29, 2024
Viaarxiv icon

TOFU: A Task of Fictitious Unlearning for LLMs

Add code
Jan 11, 2024
Viaarxiv icon

Can Neural Network Memorization Be Localized?

Add code
Jul 18, 2023
Figure 1 for Can Neural Network Memorization Be Localized?
Figure 2 for Can Neural Network Memorization Be Localized?
Figure 3 for Can Neural Network Memorization Be Localized?
Figure 4 for Can Neural Network Memorization Be Localized?
Viaarxiv icon

T-MARS: Improving Visual Representations by Circumventing Text Feature Learning

Add code
Jul 06, 2023
Figure 1 for T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
Figure 2 for T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
Figure 3 for T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
Figure 4 for T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
Viaarxiv icon

Model-tuning Via Prompts Makes NLP Models Adversarially Robust

Add code
Mar 13, 2023
Figure 1 for Model-tuning Via Prompts Makes NLP Models Adversarially Robust
Figure 2 for Model-tuning Via Prompts Makes NLP Models Adversarially Robust
Figure 3 for Model-tuning Via Prompts Makes NLP Models Adversarially Robust
Figure 4 for Model-tuning Via Prompts Makes NLP Models Adversarially Robust
Viaarxiv icon

Characterizing Datapoints via Second-Split Forgetting

Add code
Oct 26, 2022
Figure 1 for Characterizing Datapoints via Second-Split Forgetting
Figure 2 for Characterizing Datapoints via Second-Split Forgetting
Figure 3 for Characterizing Datapoints via Second-Split Forgetting
Figure 4 for Characterizing Datapoints via Second-Split Forgetting
Viaarxiv icon

Dataset Inference: Ownership Resolution in Machine Learning

Add code
Apr 21, 2021
Figure 1 for Dataset Inference: Ownership Resolution in Machine Learning
Figure 2 for Dataset Inference: Ownership Resolution in Machine Learning
Figure 3 for Dataset Inference: Ownership Resolution in Machine Learning
Figure 4 for Dataset Inference: Ownership Resolution in Machine Learning
Viaarxiv icon