Based on GAIA, we evaluate a suite of popular text-to-video (T2V) models on their ability to generate visually rational actions, revealing their pros and cons on different categories of actions.

The denoising model has been proven a powerful generative model but has little exploration of discriminative tasks. Representation learning is important in discriminative tasks, which is defined as "learning representations (or features) of

Next, we propose a high-frequency guidance sampling method to explicitly control the denoising process and preserve high-frequency details in unprocessed areas. Finally, we design an auxiliary prompting adapter, utilizing Vision-Language Models (VLMs) to enhance text prompts and improve the model's task

These approaches employ a refinement module to identify and correct inaccurately predicted amino acids.

We show how this idealized loss can be reformulated to a functionally equivalent loss that is more efficient to compute.

However, visual representations are inherently independent of language.

We explore those different aspects in relation to mutual knowledge, and analyze zero-shot predictions.