Related papers: Beyond Spatial Compression: Interface-Centric Gene…

Transformers predict over a representation of a sequence. The same data can be written as bytes, characters, or subword tokens, and these representations may be lossless. Yet, under a fixed context window, they need not expose the same…

Indoor scene generation aims at creating shape-compatible, style-consistent furniture arrangements within a spatially reasonable layout. However, most existing approaches primarily focus on generating plausible furniture layouts without…

The benefit of pretrained autoencoders for reinforcement learning in comparison to training on raw observations is already known [1]. In this paper, we address the generation of a compact and information-rich state representation. In…

3D generative models have been recently successful in generating realistic 3D objects in the form of point clouds. However, most models do not offer controllability to manipulate the shape semantics of component object parts without…

Continuous diffusion and flow models are attractive for non-autoregressive text generation because they can update all positions in parallel. A major difficulty is the interface between continuous latent states and discrete tokens. This…

Existing generative models, such as diffusion and auto-regressive networks, are inherently static, relying on a fixed set of pretrained parameters to handle all inputs. In contrast, humans flexibly adapt their internal generative…

Text-conditioned generative models for volumetric medical imaging provide semantic control but lack explicit anatomical guidance, often resulting in outputs that are spatially ambiguous or anatomically inconsistent. In contrast,…

Recent advances in auto-regressive transformers have achieved remarkable success in generative modeling. However, text-to-3D generation remains challenging, primarily due to bottlenecks in learning discrete 3D representations. Specifically,…

Recent conditional image synthesis approaches provide high-quality synthesized images. However, it is still challenging to accurately adjust image contents such as the positions and orientations of objects, and synthesized images often have…

We present a novel neural network architecture, termed Decomposer-Composer, for semantic structure-aware 3D shape modeling. Our method utilizes an auto-encoder-based pipeline, and produces a novel factorized shape embedding space, where the…

Networks of interdependent industrial assets (clients) are tightly coupled through physical processes and control inputs, raising a key question: how would the output of one client change if another client were operated differently? This is…

We propose a novel Auto-Regressive (AR) image generation approach that models images as hierarchical compositions of interpretable visual layers. While AR models have achieved transformative success in language modeling, replicating this…

Accurate and efficient tools for calculating the ground state properties of interacting quantum systems are essential in the design of nanoelectronic devices. The exact diagonalization method fully accounts for the Coulomb interaction…

As generative technologies advance, visual content has evolved into a complex mix of natural and AI-generated images, driving the need for more efficient coding techniques that prioritize perceptual quality. Traditional codecs and learned…

3D Lookup Tables (3D LUTs) are widely used for color mapping, but their grid-based representation requires discretizing the RGB space, leading to a capacity-memory trade-off that becomes prohibitive when storing large numbers of LUTs.…

Autoregressive visual generation models typically rely on tokenizers to compress images into tokens that can be predicted sequentially. A fundamental dilemma exists in token representation: discrete tokens enable straightforward modeling…

We propose a systematic approach to constructing microscopic models with fractional excitations in three-dimensional (3D) space. Building blocks are quantum wires described by the (1+1)-dimensional conformal field theory (CFT) associated…

3D generation has made significant progress, however, it still largely remains at the object-level. Feedforward 3D scene-level generation has been rarely explored due to the lack of models capable of scaling-up latent representation…

Over the last years, 3D morphable models (3DMMs) have emerged as a state-of-the-art methodology for modeling and generating expressive 3D avatars. However, given their reliance on a strict topology, along with their linear nature, they…

Feed-forward 3D reconstruction models based on Vision Transformers can directly estimate scene geometry and camera poses from a small set of input images, but scaling them to video inputs with hundreds or thousands of frames remains…