Related papers: Realistic Evaluation of Model Merging for Composit…
Compact and discriminative visual codebooks are preferred in many visual recognition tasks. In the literature, a number of works have taken the approach of hierarchically merging visual words of an initial large-sized codebook, but…
In recent years, machine learning, and in particular generative adversarial neural networks (GANs) and attention-based neural networks (transformers), have been successfully used to compose and generate music, both melodies and polyphonic…
In this thesis a comprehensive verification framework is proposed to contend with some important issues in composability verification and a verification process is suggested to verify composability of different kinds of systems models, such…
We consider statistical procedures for hypothesis testing of real valued functionals of matched pairs with missing values. In order to improve the accuracy of existing methods, we propose a novel multiplication combination procedure.…
Model merging is a powerful technique for integrating the specialized knowledge of multiple machine learning models into a single model. However, existing methods require manually partitioning model parameters into fixed groups for merging,…
Compositional generalization is the capability of a model to understand novel compositions composed of seen concepts. There are multiple levels of novel compositions including phrase-phrase level, phrase-word level, and word-word level.…
In this paper, we study multi-target domain adaptation of scene understanding models. While previous methods achieved commendable results through inter-domain consistency losses, they often assumed unrealistic simultaneous access to images…
This paper describes a generalizable model evaluation method that can be adapted to evaluate AI/ML models across multiple criteria including core scientific principles and more practical outcomes. Emerging from prediction competitions in…
With the development of cheap image sensors, the amount of available image data have increased enormously, and the possibility of using crowdsourced collection methods has emerged. This calls for development of ways to handle all these…
Diffusion models now generate high-quality, diverse samples, with an increasing focus on more powerful models. Although ensembling is a well-known way to improve supervised models, its application to unconditional score-based diffusion…
Composing basic skills from simple tasks to accomplish composite tasks is crucial for modern intelligent systems. We investigate the in-context composition ability of language models to perform composite tasks that combine basic skills…
We present a method for storing multiple models within a single set of parameters. Models can coexist in superposition and still be retrieved individually. In experiments with neural networks, we show that a surprisingly large number of…
Neural networks have shown great abilities in estimating depth from a single image. However, the inferred depth maps are well below one-megapixel resolution and often lack fine-grained details, which limits their practicality. Our method…
Achieving balanced alignment of large language models (LLMs) in terms of Helpfulness, Honesty, and Harmlessness (3H optimization) constitutes a cornerstone of responsible AI. Existing methods like data mixture strategies face limitations,…
To understand and predict the performance of scientific applications, several analytical and machine learning approaches have been proposed, each having its advantages and disadvantages. In this paper, we propose and validate a hybrid…
Compositional generalization is a crucial property in artificial intelligence, enabling models to handle novel combinations of known components. While most deep learning models lack this capability, certain models succeed in specific tasks,…
To improve model generalization, model designers often restrict the features that their models use, either implicitly or explicitly. In this work, we explore the design space of leveraging such feature priors by viewing them as distinct…
In many medical and business applications, researchers are interested in estimating individualized treatment effects using data from a randomized experiment. For example in medical applications, doctors learn the treatment effects from…
While large language models (LLMs) fine-tuned with lightweight adapters achieve strong performance across diverse tasks, their performance on individual tasks depends on the fine-tuning strategy. Fusing independently trained models with…
Diffusion models have become prevalent in generative modeling due to their ability to sample from complex distributions. To improve the quality of generated samples and their compliance with user requirements, two commonly used methods are:…