Related papers: Black-Box Forgetting
With the emergence of pretrained vision-language models (VLMs), considerable efforts have been devoted to fine-tuning them for downstream tasks. Despite the progress made in designing efficient fine-tuning methods, such methods require…
Pre-trained language models (PLM) have revolutionized the NLP landscape, achieving stellar performances across diverse tasks. These models, while benefiting from vast training data, often require fine-tuning on specific data to cater to…
Over-prompting, a phenomenon where excessive examples in prompts lead to diminished performance in Large Language Models (LLMs), challenges the conventional wisdom about in-context few-shot learning. To investigate this few-shot dilemma, we…
In general class-incremental learning, researchers typically use sample sets as a tool to avoid catastrophic forgetting during continuous learning. At the same time, researchers have also noted the differences between class-incremental…
Catastrophic forgetting is a challenge issue in continual learning when a deep neural network forgets the knowledge acquired from the former task after learning on subsequent tasks. However, existing methods try to find the joint…
Face representation learning using datasets with a massive number of identities requires appropriate training methods. Softmax-based approach, currently the state-of-the-art in face recognition, in its usual "full softmax" form is not…
While improving prediction accuracy has been the focus of machine learning in recent years, this alone does not suffice for reliable decision-making. Deploying learning systems in consequential settings also requires calibrating and…
Explaining the behaviors of deep neural networks, usually considered as black boxes, is critical especially when they are now being adopted over diverse aspects of human life. Taking the advantages of interpretable machine learning…
As large language models (LLMs) are applied across diverse domains, the ability to selectively unlearn specific information is becoming increasingly essential. For instance, LLMs are expected to selectively provide confidential information…
We introduce a novel, closed-form approach for selective unlearning in multimodal models, specifically targeting pretrained models such as CLIP. Our method leverages nullspace projection to erase the target class information embedded in the…
Feature selection, an effective technique for dimensionality reduction, plays an important role in many machine learning systems. Supervised knowledge can significantly improve the performance. However, faced with the rapid growth of newly…
Custom Diffusion Models (CDMs) have gained significant attention due to their remarkable ability to personalize generative processes. However, existing CDMs suffer from catastrophic forgetting when continuously learning new concepts. Most…
Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning…
The no free lunch theorem states that no model is better suited to every problem. A question that arises from this is how to design methods that propose optimizers tailored to specific problems achieving state-of-the-art performance. This…
Various methods for robot design optimization have been developed so far. These methods are diverse, ranging from numerical optimization to black-box optimization. While numerical optimization is fast, it is not suitable for cases involving…
Machine learning has been widely applied in many aspects, but training a machine learning model is increasingly difficult. There are more optimization problems named "black-box" where the relationship between model parameters and outcomes…
Even in the era of large models, one of the well-known issues in continual learning (CL) is catastrophic forgetting, which is significantly challenging when the continual data stream exhibits a long-tailed distribution, termed as…
Large language models (LLMs) and multimodal models (MMs) have exhibited impressive capabilities in various domains, particularly in general language understanding and visual reasoning. However, these models, trained on massive data, may not…
Explaining the behaviors of deep neural networks, usually considered as black boxes, is critical especially when they are now being adopted over diverse aspects of human life. Taking the advantages of interpretable machine learning…
Contrastively trained text-image models have the remarkable ability to perform zero-shot classification, that is, classifying previously unseen images into categories that the model has never been explicitly trained to identify. However,…