In Natural Language Processing (NLP), Large Language Models (LLMs) have demonstrated
high text generation quality. However, in real-world applications, LLMs must meet …

In the rapidly evolving field of large language models (LLMs), data augmentation (DA) has
emerged as a pivotal technique for enhancing model performance by diversifying training …

Visual Prompting is a technique for teaching models to perform a visual task via in-context
examples, without any additional training. In this work, we analyze the activations of MAE …

The scaling of inference computation has unlocked the potential of long-context large
language models (LLMs) across diverse settings. For knowledge-intensive tasks, the …

Advancements in LLMs have recently unveiled challenges tied to computational efficiency
and continual scalability due to their requirements of huge parameters, making the …

Large Language Models (LLMs) are transforming the way people generate, explore, and
engage with content. We study how we can develop LLM applications for online social …

Medical report generation (MRG) has emerged as a pivotal research topic in the medical
multi-modal field, given its potential to alleviate the heavy workloads of radiologists …

Safety alignment is indispensable for Large language models (LLMs) to defend threats from
malicious instructions. However, recent researches reveal safety-aligned LLMs prone to …

Ensuring the trustworthiness of large language models (LLMs) is crucial. Most studies
concentrate on fully pre-trained LLMs to better understand and improve LLMs' …

Radiotherapy treatment planning is a time-consuming and potentially subjective process
that requires the iterative adjustment of model parameters to balance multiple conflicting …