The most advanced text-to-image (T2I) models require significant training costs (eg, millions
of GPU hours), seriously hindering the fundamental innovation for the AIGC community …

Despite significant progress in generative AI, comprehensive evaluation remains
challenging because of the lack of effective metrics and standardized benchmarks. For …

Video generation has witnessed significant advancements yet evaluating these models
remains a challenge. A comprehensive evaluation benchmark for video generation is …

While next-token prediction is considered a promising path towards artificial general
intelligence, it has struggled to excel in multimodal tasks, which are still dominated by …

Diffusion models have exhibit exceptional performance in text-to-image generation and
editing. However, existing methods often face challenges when handling complex text …

Abstract Text-to-Image (T2I) and multimodal large language models (MLLMs) have been
adopted in solutions for several computer vision and multimodal learning tasks. However, it …

Recent advancements in AI, especially deep learning, have contributed to a significant
increase in the creation of new realistic-looking synthetic media (video, image, and audio) …

Despite significant strides in multimodal tasks, Multimodal Large Language Models (MLLMs)
are plagued by the critical issue of hallucination. The reliable detection of such …

Existing text-to-image (T2I) diffusion models usually struggle in interpreting complex prompts
especially those with quantity object-attribute binding and multi-subject descriptions. In this …

Text-to-video (T2V) generation models have advanced significantly, yet their ability to
compose different objects, attributes, actions, and motions into a video remains unexplored …