We study how in-context learning (ICL) in language models is affected by semantic priors
versus input-label mappings. We investigate two setups-ICL with flipped labels and ICL with …

Neural networks have achieved remarkable empirical performance, while the current
theoretical analysis is not adequate for understanding their success, eg, the Neural Tangent …

Large language models (LLMs) and vision-language models (VLMs) have demonstrated
remarkable performance across a wide range of tasks and domains. Despite this promise …

Diffusion models have made rapid progress in generating high-quality samples across
various domains. However, a theoretical understanding of the Lipschitz continuity and …

In the evolving landscape of machine learning, a pivotal challenge lies in deciphering the
internal representations harnessed by neural networks and Transformers. Building on recent …

Foundation models have emerged as a powerful tool for many AI problems. Despite the
tremendous success of foundation models, effective adaptation to new tasks, particularly …

Training data privacy is a fundamental problem in modern Artificial Intelligence (AI)
applications, such as face recognition, recommendation systems, language generation, and …

The softmax activation function plays a crucial role in the success of large language models
(LLMs), particularly in the self-attention mechanism of the widely adopted Transformer …

Large language models (LLM) have emerged as a powerful tool exhibiting remarkable in-
context learning (ICL) capabilities. In this study, we delve into the ICL capabilities of LLMs on …

Foundation models have emerged as a powerful tool in AI, yet come with substantial
computational cost, limiting their deployment in resource-constraint devices. Several recent …