Related papers: DisCo-Layout: Disentangling and Coordinating Seman…

Brain magnetic resonance imaging (MRI) has been extensively employed across clinical and research fields, but often exhibits sensitivity to site effects arising from non-biological variations such as differences in field strength and…

Prompt tuning (PT) offers a cost-effective alternative to fine-tuning large-scale pre-trained language models (PLMs), requiring only a few parameters in soft prompt tokens added before the input text. However, existing PT approaches face…

Recent advances in language models opened new opportunities to address complex schema matching tasks. Schema matching approaches have been proposed that demonstrate the usefulness of language models, but they have also uncovered important…

Self-supervised learning (SSL) and diffusion models have advanced representation learning and image synthesis, but in 3D medical imaging they are still largely used separately for analysis and synthesis, respectively. Unifying them is…

Compositional text-to-video generation, which requires synthesizing dynamic scenes with multiple interacting entities and precise spatial-temporal relationships, remains a critical challenge for diffusion-based models. Existing methods…

Semantic segmentation is a fundamental task in multimedia processing, which can be used for analyzing, understanding, editing contents of images and videos, among others. To accelerate the analysis of multimedia data, existing segmentation…

Existing alignment techniques for Large Language Models (LLMs), such as Direct Preference Optimization (DPO), typically treat the model as a monolithic entity, applying uniform optimization pressure across all layers. This approach…

A crucial problem in learning disentangled image representations is controlling the degree of disentanglement during image editing, while preserving the identity of objects. In this work, we propose a simple yet effective model with the…

Embodied agents need to plan and act reliably in real and complex 3D environments. Classical planning (e.g., PDDL) offers structure and guarantees, but in practice it fails under noisy perception and incorrect predicate grounding. On the…

Domain Generalization (DG) seeks to develop a versatile model capable of performing effectively on unseen target domains. Notably, recent advances in pre-trained Visual Foundation Models (VFMs), such as CLIP, have demonstrated considerable…

Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend…

We present an open-source, real-time implementation of SemanticPaint, a system for geometric reconstruction, object-class segmentation and learning of 3D scenes. Using our system, a user can walk into a room wearing a depth camera and a…

Layout generation is a task to synthesize a harmonious layout with elements characterized by attributes such as category, position, and size. Human designers experiment with the placement and modification of elements to create aesthetic…

Deep generative models come with the promise to learn an explainable representation for visual objects that allows image sampling, synthesis, and selective modification. The main challenge is to learn to properly model the independent…

Dense indoor scene modeling from 2D images has been bottlenecked due to the absence of depth information and cluttered occlusions. We present an automatic indoor scene modeling approach using deep features from neural networks. Given a…

Indoor scene synthesis aims to automatically produce plausible, realistic and diverse 3D indoor scenes, especially given arbitrary user requirements. Recently, the promising generalization ability of pre-trained large language models (LLM)…

Tasks requiring deductive reasoning, especially those involving multiple steps, often demand adaptive strategies such as intermediate generation of rationales or programs, as no single approach is universally optimal. While Language Models…

Semantic image editing provides users with a flexible tool to modify a given image guided by a corresponding segmentation map. In this task, the features of the foreground objects and the backgrounds are quite different. However, all…

Despite recent advances in the reasoning capabilities of Large Language Models (LLMs), improving the reasoning ability of Small Language Models (SLMs, e.g., up to 1.5B parameters) remains challenging. A key obstacle lies in the complexity…

Supervised Fine-Tuning (SFT) accelerates taskspecific large language models (LLMs) development, but the resulting proliferation of finetuned models incurs substantial memory overhead. Delta compression addresses this by retaining a single…