Unlike natural language processing and computer vision, the development of Foundation Models (FMs) for time series forecasting is blocked due to data scarcity.

In this section, we will describe the evaluation process in detail. We evaluated various L VLMs, including medical-specific models, open-source general models, and closed-source API general models.

Before that, it is crucial to develop benchmarks to evaluate L VLMs' effectiveness in various medical applications.

As a cost-effective alternative, learning-free PTQ schemes have been proposed. However, the performance is somewhat limited because they cannot consider the inter-layer dependency within the attention module, which is a significant feature of Transformers. In this paper, we thus propose a novel PTQ algorithm that balances accuracy and efficiency. The key idea of the proposed algorithm called aespa is to perform quantization layer-wise for efficiency while targeting attention-wise reconstruction to consider the cross-layer dependency.

Additionally, a learnable component of the language prompts is trained using the available few-shot labeled data.

Discriminative methods were used to execute such tasks and achieved state-of-the-art performance.

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation framework that captures salient aspects of an unsafe input by modeling the interaction between the task the model is asked to perform (e.g., "design") versus the specific concepts the task is asked to be performed upon (e.g., a "cycle" vs. a "bomb").

Modeling the human as Boltzmann-rational w.r.t. a belief over trajectories, we prove conditions under which RLHF is