Related papers: Large Scale Qualitative Evaluation of Generative I…

Current language models can generate high-quality text. Are they simply copying text they have seen before, or have they learned generalizable linguistic abstractions? To tease apart these possibilities, we introduce RAVEN, a suite of…

Comprehending long videos remains a significant challenge for Large Multi-modal Models (LMMs). Current LMMs struggle to process even minutes to hours videos due to their lack of explicit memory and retrieval mechanisms. To address this…

While modern visual generation models excel at creating aesthetically pleasing natural images, they struggle with producing or editing structured visuals like charts, diagrams, and mathematical figures, which demand composition planning,…

Language models have demonstrated the ability to generate highly fluent text; however, it remains unclear whether their output retains coherent high-level structure (e.g., story progression). Here, we propose to apply a statistical tool,…

Text-to-image retrieval is a fundamental task in vision-language learning, yet in real-world scenarios it is often challenged by short and underspecified user queries. Such queries are typically only one or two words long, rendering them…

With recent advancements in text-to-image (T2I) models, effectively generating multiple instances within a single image prompt has become a crucial challenge. Existing methods, while successful in generating positions of individual…

Machine unlearning has emerged as a new paradigm to deliberately forget data samples from a given model in order to adhere to stringent regulations. However, existing machine unlearning methods have been primarily focused on classification…

Gatys et al. (2015) showed that optimizing pixels to match features in a convolutional network with respect reference image features is a way to render images of high visual quality. We show that unrolling this gradient-based optimization…

One of the most significant challenges in statistical signal processing and machine learning is how to obtain a generative model that can produce samples of large-scale data distribution, such as images and speeches. Generative Adversarial…

Diffusion models enable high-quality and diverse visual content synthesis. However, they struggle to generate rare or unseen concepts. To address this challenge, we explore the usage of Retrieval-Augmented Generation (RAG) with image…

Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a…

Generative Image Restoration (GIR) has achieved impressive perceptual realism, but how far have its practical capabilities truly advanced compared with previous methods? To answer this, we present a large-scale study grounded in a new…

Vision-language models (VLMs) have shown strong performance on text-to-image retrieval benchmarks. However, bridging this success to real-world applications remains a challenge. In practice, human search behavior is rarely a one-shot…

Developing inherently interpretable models for prediction has gained prominence in recent years. A subclass of these models, wherein the interpretable network relies on learning high-level concepts, are valued because of closeness of…

Interactive model analysis, the process of understanding, diagnosing, and refining a machine learning model with the help of interactive visualization, is very important for users to efficiently solve real-world artificial intelligence and…

Research in Image Generation has recently made significant progress, particularly boosted by the introduction of Vision-Language models which are able to produce high-quality visual content based on textual inputs. Despite ongoing…

The increasing use of Retrieval-Augmented Generation (RAG) systems in various applications necessitates stringent protocols to ensure RAG systems accuracy, safety, and alignment with user intentions. In this paper, we introduce VERA…

The rapid advancements in generative AI and large language models (LLMs) have opened up new avenues for producing synthetic data, particularly in the realm of structured tabular formats, such as product reviews. Despite the potential…

Evaluating generative models for synthetic medical imaging is crucial yet challenging, especially given the high standards of fidelity, anatomical accuracy, and safety required for clinical applications. Standard evaluation of generated…

Evaluating generative adversarial networks (GANs) is inherently challenging. In this paper, we revisit several representative sample-based evaluation metrics for GANs, and address the problem of how to evaluate the evaluation metrics. We…