Related papers: AnchorFlow: Training-Free 3D Editing via Latent An…

Previous text-guided video editing methods often suffer from temporal inconsistency, motion distortion, and-most notably-limited domain transformation. We attribute these limitations to insufficient modeling of spatiotemporal pixel…

Modern audio generation predominantly relies on latent-space compression, introducing additional complexity and potential information loss. In this work, we challenge this paradigm with WavFlow, a framework that generates high-fidelity…

While recent flow-based image editing models demonstrate general-purpose capabilities across diverse tasks, they often struggle to specialize in challenging scenarios -- particularly those involving large-scale shape transformations. When…

Flow matching has emerged as a simulation-free alternative to diffusion-based generative modeling, producing samples by solving an ODE whose time-dependent velocity field is learned along an interpolation between a simple source…

Enabling robots to execute novel manipulation tasks zero-shot is a central goal in robotics. Most existing methods assume in-distribution tasks or rely on fine-tuning with embodiment-matched data, limiting transfer across platforms. We…

We propose a novel training-free image generation algorithm that precisely controls the occlusion relationships between objects in an image. Existing image generation methods typically rely on prompts to influence occlusion, which often…

Test-Time Prompt Tuning (TPT) adapts vision-language models using augmented views, but its effectiveness is hindered by the challenge of determining which views are beneficial. Standard entropy-based filtering relies on the internal…

Generative AI promises to allow people to create high-quality personalized media. Although powerful, we identify three fundamental design problems with existing tooling through a literature review. We introduce a multimodal generative AI…

The automated generation of agentic workflows is a promising frontier for enabling large language models (LLMs) to solve complex tasks. However, our investigation reveals that the robustness of agentic workflow remains a critical,…

Reconstructing dynamic 3D scenes from monocular videos remains a fundamental challenge in 3D vision. While 3D Gaussian Splatting (3DGS) achieves real-time rendering in static settings, extending it to dynamic scenes is challenging due to…

A central challenge in mobile manipulation is preserving multiple plausible action models while remaining reactive during execution. A bottle in a cluttered scene can often be approached and grasped in multiple valid ways. Robust behavior…

Tuning-free diffusion-based models have demonstrated significant potential in the realm of image personalization and customization. However, despite this notable progress, current models continue to grapple with several complex challenges…

We present a semi-supervised learning algorithm for learning discrete factor analysis models with arbitrary structure on the latent variables. Our algorithm assumes that every latent variable has an "anchor", an observed variable with only…

High-dimensional datasets present substantial challenges in statistical modeling across various disciplines, necessitating effective dimensionality reduction methods. Deep learning approaches, notable for their capacity to distill essential…

Modern text-to-image diffusion models encode rich visual priors, but expose them only through one-way text-conditioned generation. Existing unified vision--language models derived from them recover bidirectional capability through…

6D object pose estimation is crucial for robotic perception and precise manipulation. Occlusion and incomplete object visibility are common challenges in this task, but existing pose refinement methods often struggle to handle these issues…

Generative art unlocks boundless creative possibilities, yet its full potential remains untapped due to the technical expertise required for advanced architectural concepts and computational workflows. To bridge this gap, we present…

Understanding how humans interact with the surrounding environment, and specifically reasoning about object interactions and affordances, is a critical challenge in computer vision, robotics, and AI. Current approaches often depend on…

We present ShapeFlow, a dynamic abstract interpreter for TensorFlow which quickly catches tensor shape incompatibility errors, one of the most common bugs in deep learning code. ShapeFlow shares the same APIs as TensorFlow but only captures…

Human action-reaction synthesis, a fundamental challenge in modeling causal human interactions, plays a critical role in applications ranging from virtual reality to social robotics. While diffusion-based models have demonstrated promising…