Related papers: D3PIA: A Discrete Denoising Diffusion Model for Pi…

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…

The optimization of the latents and parameters of diffusion models with respect to some differentiable metric defined on the output of the model is a challenging and complex problem. The sampling for diffusion models is done by solving…

Direct preference optimization (DPO) has shown success in aligning diffusion models with human preference. Previous approaches typically assume a consistent preference label between final generations and noisy samples at intermediate steps,…

Diffusion models form an important class of generative models today, accounting for much of the state of the art in cutting edge AI research. While numerous extensions beyond image and video generation exist, few of such approaches address…

We introduce an extensive new dataset of MIDI files, created by transcribing audio recordings of piano performances into their constituent notes. The data pipeline we use is multi-stage, employing a language model to autonomously crawl and…

Diffusion models have become a powerful backbone for text-to-image generation, producing high-quality visuals from natural language prompts. However, when prompts involve multiple objects alongside global or local style instructions, the…

Molecular optimization, aimed at improving binding affinity or other molecular properties, is a crucial task in drug discovery that often relies on the expertise of medicinal chemists. Recently, deep learning-based 3D generative models…

This paper aims to apply a new deep learning approach to the task of generating raw audio files. It is based on diffusion models, a recent type of deep generative model. This new type of method has recently shown outstanding results with…

Generative modelling over continuous-time geometric constructs, a.k.a such as handwriting, sketches, drawings etc., have been accomplished through autoregressive distributions. Such strictly-ordered discrete factorization however falls…

Text-to-3D generation has shown rapid progress in recent days with the advent of score distillation, a methodology of using pretrained text-to-2D diffusion models to optimize neural radiance field (NeRF) in the zero-shot setting. However,…

Recent advances in recording technology have allowed neuroscientists to monitor activity from thousands of neurons simultaneously. Latent variable models are increasingly valuable for distilling these recordings into compact and…

Recent advances in diffusion models have significantly improved the synthesis of materials, textures, and 3D shapes. By conditioning these models via text or images, users can guide the generation, reducing the time required to create…

Recent text-guided generation of individual 3D object has achieved great success using diffusion priors. However, these methods are not suitable for object insertion and replacement tasks as they do not consider the background, leading to…

Diffusion models excel at capturing the natural design spaces of images, molecules, DNA, RNA, and protein sequences. However, rather than merely generating designs that are natural, we often aim to optimize downstream reward functions while…

We present DiffCollage, a compositional diffusion model that can generate large content by leveraging diffusion models trained on generating pieces of the large content. Our approach is based on a factor graph representation where each…

Diffusion models can be improved with additional guidance towards more effective representations of input. Indeed, prior empirical work has already shown that aligning internal representations of the diffusion model with those of…

Diffusion models have shown promising results for a wide range of generative tasks with continuous data, such as image and audio synthesis. However, little progress has been made on using diffusion models to generate discrete symbolic music…

We investigate the problem of modeling symbolic sequences of polyphonic music in a completely general piano-roll representation. We introduce a probabilistic model based on distribution estimators conditioned on a recurrent neural network…

Zero-shot learning enables models to generalise to unseen classes by leveraging semantic information, bridging the gap between training and testing sets with non-overlapping classes. While much research has focused on zero-shot learning in…

In this paper we propose a novel generative approach, DiffRoll, to tackle automatic music transcription (AMT). Instead of treating AMT as a discriminative task in which the model is trained to convert spectrograms into piano rolls, we think…