Vision-language models (VLMs) are typically composed of a vision encoder, eg CLIP, and a
language model (LM) that interprets the encoded features to solve downstream tasks …

We propose SlowFast-LLaVA (or SF-LLaVA for short), a training-free video large language
model (LLM) that can jointly capture detailed spatial semantics and long-range temporal …

In this work, we introduce OmniGen, a new diffusion model for unified image generation.
Unlike popular diffusion models (eg, Stable Diffusion), OmniGen no longer requires …

Given the rapid emergence and applications of Large Language Models (LLMs) across
various scientific fields, insights regarding their applicability in agriculture are still only …

This paper presents a versatile image-to-image visual assistant, PixWizard, designed for
image generation, manipulation, and translation based on free-from language instructions …

Artificial intelligence (AI) methods are poised to revolutionize intellectual work, with
generative AI enabling automation of text analysis, text generation, and simple decision …

Semantic future prediction is important for autonomous systems navigating dynamic
environments. This paper introduces FUTURIST, a method for multimodal future semantic …

Abstract Foundation Models (FMs) hold transformative potential to accelerate scientific
discovery, yet reaching their full capacity in complex, highly multimodal domains such as …

Cloth folding is a complex task due to the inevitable self-occlusions of clothes, their
complicated dynamics, and the disparate materials, geometries, and textures that garments …

Multimodal large language models (MLLMs) have made rapid progress in recent years, yet
continue to struggle with low-level visual perception (LLVP)--particularly the ability to …