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 …

Several recent works demonstrate that transformers can implement algorithms like gradient
descent. By a careful construction of weights, these works show that multiple layers of …

Large language models (LLMs) excel at few-shot in-context learning (ICL)--learning from a
few examples provided in context at inference, without any weight updates. Newly expanded …

Machine unlearning, the study of efficiently removing the impact of specific training points on
the trained model, has garnered increased attention of late, driven by the need to comply …

The sample selection approach is popular in learning with noisy labels. The state-of-the-art
methods train two deep networks simultaneously for sample selection, which aims to employ …

In this article, we review the literature on statistical theories of neural networks from three
perspectives: approximation, training dynamics, and generative models. In the first part …

Large language models have exhibited emergent abilities, demonstrating exceptional
performance across diverse tasks for which they were not explicitly trained, including those …

Human motion prediction is a classical problem in computer vision and computer graphics,
which has a wide range of practical applications. Previous effects achieve great empirical …

Since its inception in" Attention Is All You Need", transformer architecture has led to
revolutionary advancements in NLP. The attention layer within the transformer admits a …

Some autoregressive models exhibit in-context learning capabilities: being able to learn as
an input sequence is processed, without undergoing any parameter changes, and without …