21 citations · 34 across the 18 of their papers we have counts for
13 papers · 1 filter
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1
With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associatio…
ExecTune: Effective Steering of Black-Box LLMs with Guide Models
Vijay Lingam, Aditya Golatkar, Anwesan Pal +6
For large language models deployed through black-box APIs, recurring inference costs often exceed one-time training costs. This motivates composed agentic systems that amortize exp…
B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory
Luca Zancato, Arjun Seshadri, Yonatan Dukler +6
We describe a family of architectures to support transductive inference by allowing memory to grow to a finite but a-priori unknown bound while making efficient use of finite resou…
Training Data Protection with Compositional Diffusion Models
Aditya Golatkar, Alessandro Achille, Ashwin Swaminathan +1
We introduce Compartmentalized Diffusion Models (CDM), a method to train different diffusion models (or prompts) on distinct data sources and arbitrarily compose them at inference…
Tangent Transformers for Composition, Privacy and Removal
Tian Yu Liu, Aditya Golatkar, Stefano Soatto
We introduce Tangent Attention Fine-Tuning (TAFT), a method for fine-tuning linearized transformers obtained by computing a First-order Taylor Expansion around a pre-trained initia…
SAFE: Machine Unlearning With Shard Graphs
Yonatan Dukler, Benjamin Bowman, Alessandro Achille +3
We present Synergy Aware Forgetting Ensemble (SAFE), a method to adapt large models on a diverse collection of data while minimizing the expected cost to remove the influence of tr…
Integral Continual Learning Along the Tangent Vector Field of Tasks
Tian Yu Liu, Aditya Golatkar, Stefano Soatto +1
We propose a lightweight continual learning method which incorporates information from specialized datasets incrementally, by integrating it along the vector field of "generalist"…
On Leave-One-Out Conditional Mutual Information For Generalization
Mohamad Rida Rammal, Alessandro Achille, Aditya Golatkar +2
We derive information theoretic generalization bounds for supervised learning algorithms based on a new measure of leave-one-out conditional mutual information (loo-CMI). Contrary…
LQF: Linear Quadratic Fine-Tuning
Alessandro Achille, Aditya Golatkar, Avinash Ravichandran +2
Classifiers that are linear in their parameters, and trained by optimizing a convex loss function, have predictable behavior with respect to changes in the training data, initial c…
Mixed-Privacy Forgetting in Deep Networks
Aditya Golatkar, Alessandro Achille, Avinash Ravichandran +2
We show that the influence of a subset of the training samples can be removed -- or "forgotten" -- from the weights of a network trained on large-scale image classification tasks,…
Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations
Aditya Golatkar, Alessandro Achille, Stefano Soatto
We describe a procedure for removing dependency on a cohort of training data from a trained deep network that improves upon and generalizes previous methods to different readout fu…
Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks
Aditya Golatkar, Alessandro Achille, Stefano Soatto
We explore the problem of selectively forgetting a particular subset of the data used for training a deep neural network. While the effects of the data to be forgotten can be hidde…
Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence
Aditya Golatkar, Alessandro Achille, Stefano Soatto
Regularization is typically understood as improving generalization by altering the landscape of local extrema to which the model eventually converges. Deep neural networks (DNNs),…