Related papers: Segment-Level Diffusion: A Framework for Controlla…

Despite the growing success of diffusion models in continuous-valued domains (e.g., images), similar efforts for discrete domains such as text have yet to match the performance of autoregressive language models. In this work, we present…

The Semantic Layered Embedding Diffusion (SLED) mechanism redefines the representation of hierarchical semantics within transformer-based architectures, enabling enhanced contextual consistency across a wide array of linguistic tasks. By…

Text-to-image generation has witnessed significant progress with the advent of diffusion models. Despite the ability to generate photorealistic images, current text-to-image diffusion models still often struggle to accurately interpret and…

The modern autoregressive Large Language Models (LLMs) have achieved outstanding performance on NLP benchmarks, and they are deployed in the real world. However, they still suffer from limitations of the autoregressive training paradigm.…

Controlling the behavior of language models (LMs) without re-training is a major open problem in natural language generation. While recent works have demonstrated successes on controlling simple sentence attributes (e.g., sentiment), there…

Latent diffusion models offer an attractive alternative to discrete diffusion for non-autoregressive text generation by operating on continuous text representations and denoising entire sequences in parallel. The major challenge in latent…

Synthetic tabular data generation has attracted growing attention due to its importance for data augmentation, foundation models, and privacy. However, real-world tabular datasets increasingly contain free-form text fields (e.g., reviews or…

Preparing training data for deep vision models is a labor-intensive task. To address this, generative models have emerged as an effective solution for generating synthetic data. While current generative models produce image-level category…

Diffusion Language models (DLMs) are a promising avenue for text generation due to their practical properties on tractable controllable generation. They also have the advantage of not having to predict text autoregressively. However,…

Language diffusion models aim to improve sampling speed and coherence over autoregressive LLMs. We introduce Neural Flow Diffusion Models for language generation, an extension of NFDM that enables the straightforward application of…

Diffusion language models (DLMs) have strong theoretical efficiency but are limited by fixed-length decoding and incompatibility with key-value (KV) caches. Block diffusion mitigates these issues, yet still enforces a fixed block size and…

Time series generation is a crucial research topic in the area of decision-making systems, which can be particularly important in domains like autonomous driving, healthcare, and, notably, robotics. Recent approaches focus on learning in…

Discrete diffusion models have emerged as a powerful class of models and a promising route to fast language generation, but practical implementations typically rely on factored reverse transitions ignoring cross-token dependencies and…

Latent Diffusion Models (LDMs) inherently follow a coarse-to-fine generation process, where high-level semantic structure is generated slightly earlier than fine-grained texture. This indicates the preceding semantics potentially benefit…

Lidar point cloud synthesis based on generative models offers a promising solution to augment deep learning pipelines, particularly when real-world data is scarce or lacks diversity. By enabling flexible object manipulation, this synthesis…

Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation? To circumvent the discrete nature of text data, we can simply project tokens in a continuous space of embeddings, as…

Text-conditioned diffusion models have emerged as a promising tool for neural video generation. However, current models still struggle with intricate spatiotemporal prompts and often generate restricted or incorrect motion. To address these…

Recently, diffusion models have emerged as a new paradigm for generative models. Despite the success in domains using continuous signals such as vision and audio, adapting diffusion models to natural language is under-explored due to the…

Text-to-image generation has witnessed significant advancements with the integration of Large Vision-Language Models (LVLMs), yet challenges remain in aligning complex textual descriptions with high-quality, visually coherent images. This…

Diffusion model, a new generative modelling paradigm, has achieved great success in image, audio, and video generation. However, considering the discrete categorical nature of text, it is not trivial to extend continuous diffusion models to…