相关论文: Not All Tokens are Guided Equal: Improving Guidanc…

Learning with guidance has proven effective across a wide range of machine learning systems. Guidance may, for example, come from annotated datasets in supervised learning, pseudo-labels in semi-supervised learning, and expert demonstration…

In recent years, Artificial Intelligence Generated Content (AIGC) has gained widespread attention beyond the computer science community. Due to various issues arising from continuous creation of AI-generated images (AIGI), AIGC image…

Incremental learning aims to overcome catastrophic forgetting when learning deep networks from sequential tasks. With impressive learning efficiency and performance, prompt-based methods adopt a fixed backbone to sequential tasks by…

Image generation using diffusion models have demonstrated outstanding learning capabilities, effectively capturing the full distribution of the training dataset. They are known to generate wide variations in sampled images, albeit with a…

The process of using one image to guide the filtering process of another one is called Guided Image Filtering (GIF). The main challenge of GIF is the structure inconsistency between the guidance image and the target image. Besides, noise in…

Knowledge graphs (KGs) are becoming essential resources for many downstream applications. However, their incompleteness may limit their potential. Thus, continuous curation is needed to mitigate this problem. One of the strategies to…

Recent generative data augmentation methods conditioned on both image and text prompts struggle to balance between fidelity and diversity, as it is challenging to preserve essential image details while aligning with varied text prompts.…

Scene graph generation (SGG) endeavors to predict visual relationships between pairs of objects within an image. Prevailing SGG methods traditionally assume a one-off learning process for SGG. This conventional paradigm may necessitate…

We address the problem of prompt-guided image editing in visual autoregressive models. Given a source image and a target text prompt, we aim to modify the source image according to the target prompt, while preserving all regions which are…

Integrated Gradients (IG) is a common explainability technique to address the black-box problem of neural networks. Integrated gradients assumes continuous data. Graphs are discrete structures making IG ill-suited to graphs. In this work,…

Diffusion models have shown significant progress in image translation tasks recently. However, due to their stochastic nature, there's often a trade-off between style transformation and content preservation. Current strategies aim to…

In this work, we first revisit the sampling issues in current autoregressive (AR) image generation models and identify that image tokens, unlike text tokens, exhibit lower information density and non-uniform spatial distribution.…

Conditional image modeling based on textual descriptions is a relatively new domain in unsupervised learning. Previous approaches use a latent variable model and generative adversarial networks. While the formers are approximated by using…

Text-to-video diffusion models generate realistic videos, but often fail on prompts requiring fine-grained compositional understanding, such as relations between entities, attributes, actions, and motion directions. We hypothesize that…

With the rapid development of Artificial Intelligence Generated Content (AIGC), it has become a common practice to train models on synthetic data due to data-scarcity and privacy leakage problems. Owing to massive and diverse information…

Many real-world user queries (e.g. "How do to make egg fried rice?") could benefit from systems capable of generating responses with both textual steps with accompanying images, similar to a cookbook. Models designed to generate interleaved…

Language-guided grasping has emerged as a promising paradigm for enabling robots to identify and manipulate target objects through natural language instructions, yet it remains highly challenging in cluttered or occluded scenes. Existing…

Retrieval-augmented generation (RAG) faces challenges related to factual correctness, source attribution, and response completeness. To address them, we propose a modular pipeline for grounded response generation that operates on…

Graphical User Interface (GUI) grounding requires mapping natural language instructions to precise pixel coordinates. However, due to visually homogeneous elements and dense layouts, models typically grasp semantic intent yet struggle with…

Open-vocabulary 3D Scene Graph (3DSG) can enhance various downstream tasks in robotics by leveraging structured semantic representations, yet current 3DSG construction methods suffer from semantic inconsistencies caused by noisy cross-image…