Open-vocabulary object detection (OVD) aims to detect arbitrary objects with user-provided text labels. Although recent progress has enhanced zero-shot detection ability, current techniques handicap themselves with three important challenges. They heavily depend on expensive and large-scale region-level annotations, which are hard to scale. Their captions are typically short and not contextually rich, which makes them…

Diffusion models generate images by progressively refining noise into structured representations. However, the computational cost associated with these models remains a key challenge, particularly when operating directly on high-dimensional pixel data. Researchers have been investigating ways to optimize latent space representations to improve efficiency without compromising image quality. A critical problem in diffusion models is…

Despite progress in AI-driven human animation, existing models often face limitations in motion realism, adaptability, and scalability. Many models struggle to generate fluid body movements and rely on filtered training datasets, restricting their ability to handle varied scenarios. Facial animation has seen improvements, but full-body animations remain challenging due to inconsistencies in gesture accuracy and…

Multimodal large language models (MLLMs) have emerged as a promising approach towards artificial general intelligence, integrating diverse sensing signals into a unified framework. However, MLLMs face substantial challenges in fundamental vision-related tasks, significantly underperforming compared to human capabilities. Critical limitations persist in object recognition, localization, and motion recall, presenting obstacles to comprehensive visual understanding. Despite…

Pre-trained vision models have been foundational to modern-day computer vision advances across various domains, such as image classification, object detection, and image segmentation. There is a rather massive amount of data inflow, creating dynamic data environments that require a continual learning process for our models. New regulations for data privacy require specific information to be…

Generative models have revolutionized fields like language, vision, and biology through their ability to learn and sample from complex data distributions. While these models benefit from scaling up during training through increased data, computational resources, and model sizes, their inference-time scaling capabilities face significant challenges. Specifically, diffusion models, which excel in generating continuous data like…

Generative Large Multimodal Models (LMMs), such as LLaVA and Qwen-VL, excel in vision-language (VL) tasks like image captioning and visual question answering (VQA). However, these models face challenges when applied to foundational discriminative VL tasks, such as image classification or multiple-choice VQA, which require discrete label predictions. The primary obstacle is the difficulty in extracting…

One of the major hurdles in AI-driven image modeling is the inability to account for the diversity in image content complexity effectively. The tokenization methods so far used are static compression ratios where all images are treated equally, and the complexities of images are not considered. Due to this reason, complex images get over-compressed and…

Latent diffusion models are advanced techniques for generating high-resolution images by compressing visual data into a latent space using visual tokenizers. These tokenizers reduce computational demands while retaining essential details. However, such models suffer from a critical challenge: increasing the dimensions of the token feature increases reconstruction quality but decreases image generation quality. It thus…

Vision Transformers (ViTs) have become a cornerstone in computer vision, offering strong performance and adaptability. However, their large size and computational demands create challenges, particularly for deployment on devices with limited resources. Models like FLUX Vision Transformers, with billions of parameters, require substantial storage and memory, making them impractical for many use cases. These limitations…