Related papers: ConceptWeaver: Weaving Disentangled Concepts with …

Visual concept discovery has long been deemed important to improve interpretability of neural networks, because a bank of semantically meaningful concepts would provide us with a starting point for building machine learning models that…

Currently almost all state-of-the-art novel view synthesis and reconstruction models rely on calibrated cameras or additional geometric priors for training. These prerequisites significantly limit their applicability to massive uncalibrated…

Existing 3D-aware image synthesis approaches mainly focus on generating a single canonical object and show limited capacity in composing a complex scene containing a variety of objects. This work presents DisCoScene: a 3Daware generative…

Style transfer must match a target style while preserving content semantics. DiT-based diffusion models often suffer from content-style entanglement, leading to reference-content leakage and unstable generation. We present UniCSG, a unified…

Denoising generative models, such as diffusion and flow-based models, produce high-quality samples but require many denoising steps due to discretization error. Flow maps, which estimate the average velocity between timesteps, mitigate this…

Large language model (LLM) agents often struggle in long-context interactions. As the agent accumulates more interaction history, context management approaches such as sliding window and prompt compression may omit earlier structured…

A creative idea is often born from transforming, combining, and modifying ideas from existing visual examples capturing various concepts. However, one cannot simply copy the concept as a whole, and inspiration is achieved by examining…

Humans have an innate ability to decompose their perceptions of the world into objects and their attributes, such as colors, shapes, and movement patterns. This cognitive process enables us to imagine novel futures by recombining familiar…

A dynamic scene has two types of elements: those that move fluidly and can be predicted from previous frames, and those which are disoccluded (exposed) and cannot be extrapolated. Prior approaches to video prediction typically learn either…

In this paper, we present DesignDiffusion, a simple yet effective framework for the novel task of synthesizing design images from textual descriptions. A primary challenge lies in generating accurate and style-consistent textual and visual…

We describe a method to train a generative model with latent factors that are (approximately) independent and localized. This means that perturbing the latent variables affects only local regions of the synthesized image, corresponding to…

Dataset distillation aims to synthesize a compact proxy dataset that is unreadable or non-raw from the original dataset for privacy protection and highly efficient learning. However, previous approaches typically adopt a single-stage…

Image generation based on text-to-image generation models is a task with practical application scenarios that fine-grained styles cannot be precisely described and controlled in natural language, while the guidance information of stylized…

Generating cognitive-aligned layered SVGs remains challenging due to existing methods' tendencies toward either oversimplified single-layer outputs or optimization-induced shape redundancies. We propose LayerTracer, a diffusion transformer…

Image tokenization plays a central role in modern generative modeling by mapping visual inputs into compact representations that serve as an intermediate signal between pixels and generative models. Diffusion-based decoders have recently…

Generative modeling over discrete structures underpins applications across deep learning, from biological sequence design and code generation to large language models, yet generation often remains sequential, relying on autoregressive…

In this paper, we introduce and illustrate the novel phenomenon of Conceptual Entanglement which emerges due to the representational manifoldness immanent while incrementally modelling domain ontologies step-by-step across the following…

Painting embodies a unique form of visual storytelling, where the creation process is as significant as the final artwork. Although recent advances in generative models have enabled visually compelling painting synthesis, most existing…

Novel view synthesis has observed tremendous developments since the arrival of NeRFs. However, Nerf models overfit on a single scene, lacking generalization to out of distribution objects. Recently, diffusion models have exhibited…

Large language models have improved dialogue systems, but often process conversational turns in isolation, overlooking the event structures that guide natural interactions. Hence we introduce EventWeave, a framework that explicitly models…