Related papers: DEIG: Detail-Enhanced Instance Generation with Fin…

We introduce DEIM, an innovative and efficient training framework designed to accelerate convergence in real-time object detection with Transformer-based architectures (DETR). To mitigate the sparse supervision inherent in one-to-one (O2O)…

Effectively adapting powerful pretrained foundation models to diverse tasks remains a key challenge in AI deployment. Current approaches primarily follow two paradigms:discrete optimization of text prompts through prompt engineering, or…

Detecting machine-generated text (MGT) has emerged as a critical challenge, driven by the rapid advancement of large language models (LLMs) capable of producing highly realistic, human-like content. However, the performance of current…

Dense visual perception tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbounded. While Vision-Language Models (VLMs) like CLIP have…

Large language models (LLMs) enabled dialogue systems have become one of the central modes in human-machine interaction, which bring about vast amounts of conversation logs and increasing demand for dialogue generation. The dialogue's…

Recent text-to-image diffusion models can generate striking visuals from text prompts, but they often fail to maintain subject consistency across generations and contexts. One major limitation of current fine-tuning approaches is the…

We introduce a new domain expert mixture (DEMix) layer that enables conditioning a language model (LM) on the domain of the input text. A DEMix layer is a collection of expert feedforward networks, each specialized to a domain, that makes…

Instance-aware embeddings predicted by deep neural networks have revolutionized biomedical instance segmentation, but its resource requirements are substantial. Knowledge distillation offers a solution by transferring distilled knowledge…

Recent advances in vision-language pre-training have enabled machines to perform better in multimodal object discrimination (e.g., image-text semantic alignment) and image synthesis (e.g., text-to-image generation). On the other hand,…

Definition Extraction (DE) is one of the well-known topics in Information Extraction that aims to identify terms and their corresponding definitions in unstructured texts. This task can be formalized either as a sentence classification task…

Semantic segmentation and object detection research have recently achieved rapid progress. However, the former task has no notion of different instances of the same object, and the latter operates at a coarse, bounding-box level. We propose…

Text-to-image generation models have achieved remarkable capabilities in synthesizing images, but often struggle to provide fine-grained control over the output. Existing guidance approaches, such as segmentation maps and depth maps,…

The advancement of text-to-image synthesis has introduced powerful generative models capable of creating realistic images from textual prompts. However, precise control over image attributes remains challenging, especially at the instance…

With the advancement of large pre-trained vision-language models, effectively transferring the knowledge embedded within these foundational models to downstream tasks has become a pivotal topic, particularly in data-scarce environments.…

Large language models (LLMs) promise to accelerate UI design, yet current tools struggle with two fundamentals: externalizing designers' intent and controlling iterative change. We introduce SPEC, a structured, parameterized, hierarchical…

Representation of semantic context and local details is the essential issue for building modern semantic segmentation models. However, the interrelationship between semantic context and local details is not well explored in previous works.…

Item indexing, which maps a large corpus of items into compact discrete representations, is critical for both discriminative and generative recommender systems, yet existing Vector Quantization (VQ)-based approaches struggle with the highly…

Scene Graph Generation (SGG) provides basic language representation of visual scenes, requiring models to grasp complex and diverse semantics between objects. This complexity and diversity in SGG leads to underrepresentation, where parts of…

Despite astonishing progress, generating realistic images of complex scenes remains a challenging problem. Recently, layout-to-image synthesis approaches have attracted much interest by conditioning the generator on a list of bounding boxes…

Fine-grained object detection in challenging visual domains, such as vehicle damage assessment, presents a formidable challenge even for human experts to resolve reliably. While DiffusionDet has advanced the state-of-the-art through…