Related papers: FlowBind: Efficient Any-to-Any Generation with Bid…

Diffusion models, and their generalization, flow matching, have had a remarkable impact on the field of media generation. Here, the conventional approach is to learn the complex mapping from a simple source distribution of Gaussian noise to…

We propose InsNet, an expressive insertion-based text generator with efficient training and flexible decoding (parallel or sequential). Unlike most existing insertion-based text generation works that require re-encoding of the context after…

In this work we present a novel, robust transition generation technique that can serve as a new tool for 3D animators, based on adversarial recurrent neural networks. The system synthesizes high-quality motions that use temporally-sparse…

With the emergence of diffusion models and rapid development in image processing, it has become effortless to generate fancy images in tasks such as style transfer and image editing. However, these impressive image processing approaches…

Next-generation wireless networks are expected to leverage multi-modal data sources to execute various wireless communication tasks such as beamforming and blockage prediction with situational-awareness. To do so, multi-modal transformers…

The progress on generative models has led to significant advances on text-to-video (T2V) generation, yet the motion controllability of generated videos remains limited. Existing motion transfer methods explored the motion representations of…

Computational notebooks are notoriously prone to reproducibility failures. By permitting out-of-order cell execution, notebooks accumulate hidden state and implicit dependencies that cause interactive executions to silently diverge from…

Synthesizing visually impressive images that seamlessly align both text prompts and specific artistic styles remains a significant challenge in Text-to-Image (T2I) diffusion models. This paper introduces StyleBlend, a method designed to…

Intrinsic Image Decomposition (IID) separates an image into albedo and shading components. It is a core step in many real-world applications, such as relighting and material editing. Existing IID models achieve good results, but often use a…

With the rapid advancement of generative models, general-purpose generation has gained increasing attention as a promising approach to unify diverse tasks across modalities within a single system. Despite this progress, existing open-source…

Generative flow networks (GFlowNets) are a family of algorithms for training a sequential sampler of discrete objects under an unnormalized target density and have been successfully used for various probabilistic modeling tasks. Existing…

We present UniFluid, a unified autoregressive framework for joint visual generation and understanding leveraging continuous visual tokens. Our unified autoregressive architecture processes multimodal image and text inputs, generating…

Any-to-any generative models aim to enable seamless interpretation and generation across multiple modalities within a unified framework, yet their ability to preserve relationships across modalities remains uncertain. Do unified models…

Feature matching across video streams remains a cornerstone challenge in computer vision. Increasingly, robust multimodal matching has garnered interest in robotics, surveillance, remote sensing, and medical imaging. While traditional rely…

In our prior work we have proposed the use of GFlowNets, a generative AI (GenAI) framework, for designing a secure communication system comprising a time-modulated intelligent reflecting surface (TM-IRS). However, GFlowNet-based approaches…

We present ActionPlan, a unified motion diffusion framework that bridges real-time streaming with high-quality offline generation within a single model. The core idea is to introduce a per-frame action plan: the model predicts frame-level…

We aim to develop a model-based planning framework for world models that can be scaled with increasing model and data budgets for general-purpose manipulation tasks with only language and vision inputs. To this end, we present FLow-centric…

We introduce FLOWR, a novel structure-based framework for the generation and optimization of three-dimensional ligands. FLOWR integrates continuous and categorical flow matching with equivariant optimal transport, enhanced by an efficient…

Generative Flow Networks (GFlowNets) were developed to learn policies for efficiently sampling combinatorial candidates by interpreting their generative processes as trajectories in directed acyclic graphs. In the value-based training…

Denoising-based models, such as diffusion and flow matching, have been a critical component of robotic manipulation for their strong distribution-fitting and scaling capacity. Concurrently, several works have demonstrated that simple…