Sora: A review on background, technology, limitations, and opportunities of large vision models
Sora is a text-to-video generative AI model, released by OpenAI in February 2024. The
model is trained to generate videos of realistic or imaginative scenes from text instructions …
model is trained to generate videos of realistic or imaginative scenes from text instructions …
Moviechat: From dense token to sparse memory for long video understanding
Recently integrating video foundation models and large language models to build a video
understanding system can overcome the limitations of specific pre-defined vision tasks. Yet …
understanding system can overcome the limitations of specific pre-defined vision tasks. Yet …
Chat-univi: Unified visual representation empowers large language models with image and video understanding
P Jin, R Takanobu, W Zhang… - Proceedings of the …, 2024 - openaccess.thecvf.com
Large language models have demonstrated impressive universal capabilities across a wide
range of open-ended tasks and have extended their utility to encompass multimodal …
range of open-ended tasks and have extended their utility to encompass multimodal …
Scaling open-vocabulary object detection
M Minderer, A Gritsenko… - Advances in Neural …, 2024 - proceedings.neurips.cc
Open-vocabulary object detection has benefited greatly from pretrained vision-language
models, but is still limited by the amount of available detection training data. While detection …
models, but is still limited by the amount of available detection training data. While detection …
On efficient training of large-scale deep learning models: A literature review
The field of deep learning has witnessed significant progress, particularly in computer vision
(CV), natural language processing (NLP), and speech. The use of large-scale models …
(CV), natural language processing (NLP), and speech. The use of large-scale models …
Patch n'pack: Navit, a vision transformer for any aspect ratio and resolution
The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution
before processing them with computer vision models has not yet been successfully …
before processing them with computer vision models has not yet been successfully …
Fastcomposer: Tuning-free multi-subject image generation with localized attention
Diffusion models excel at text-to-image generation, especially in subject-driven generation
for personalized images. However, existing methods are inefficient due to the subject …
for personalized images. However, existing methods are inefficient due to the subject …
Zero-shot video editing using off-the-shelf image diffusion models
Large-scale text-to-image diffusion models achieve unprecedented success in image
generation and editing. However, how to extend such success to video editing is unclear …
generation and editing. However, how to extend such success to video editing is unclear …
Token merging for fast stable diffusion
The landscape of image generation has been forever changed by open vocabulary diffusion
models. However, at their core these models use transformers, which makes generation …
models. However, at their core these models use transformers, which makes generation …
Llmlingua: Compressing prompts for accelerated inference of large language models
Large language models (LLMs) have been applied in various applications due to their
astonishing capabilities. With advancements in technologies such as chain-of-thought (CoT) …
astonishing capabilities. With advancements in technologies such as chain-of-thought (CoT) …