Related papers: Logit-KL Flow Matching: Non-Autoregressive Text Ge…
Flow Matching (FM) (also referred to as stochastic interpolants or rectified flows) stands out as a class of generative models that aims to bridge in finite time the target distribution $\nu^\star$ with an auxiliary distribution $\mu$,…
Forecasting neural activity in response to naturalistic stimuli remains a key challenge for understanding brain dynamics and enabling downstream neurotechnological applications. Here, we introduce a generative forecasting framework for…
Recently, non-autoregressive (NAR) neural machine translation models have received increasing attention due to their efficient parallel decoding. However, the probabilistic framework of NAR models necessitates conditional independence…
Non-autoregressive neural machine translation (NAT) models are proposed to accelerate the inference process while maintaining relatively high performance. However, existing NAT models are difficult to achieve the desired efficiency-quality…
Non-autoregressive approaches aim to improve the inference speed of translation models, particularly those that generate output in a one-pass forward manner. However, these approaches often suffer from a significant drop in translation…
Flow Matching (FM) is a recent generative modelling technique: we aim to learn how to sample from distribution $\mathfrak{X}_1$ by flowing samples from some distribution $\mathfrak{X}_0$ that is easy to sample from. The key trick is that…
Scaling language models to longer contexts is essential for capturing rich dependencies across extended discourse. However, na\"ive context extension imposes significant computational and memory burdens, often resulting in inefficiencies…
Visually-guided acoustic highlighting seeks to rebalance audio in alignment with the accompanying video, creating a coherent audio-visual experience. While visual saliency and enhancement have been widely studied, acoustic highlighting…
Neural Architecture Search (NAS) automates network design, but conventional methods demand substantial computational resources. We propose a closed-loop pipeline leveraging large language models (LLMs) to iteratively generate, evaluate, and…
Standard flow matching scales well but typically relies on an unstructured source distribution, limiting its ability to learn interpretable latent structure. Latent-variable models, by contrast, capture structure but often sacrifice…
Modern non-autoregressive~(NAR) speech recognition systems aim to accelerate the inference speed; however, they suffer from performance degradation compared with autoregressive~(AR) models as well as the huge model size issue. We propose a…
Flow matching has recently emerged as a promising alternative to diffusion-based generative models, offering faster sampling and simpler training by learning continuous flows governed by ordinary differential equations. Despite growing…
Generative Retrieval introduces a new approach to Information Retrieval by reframing it as a constrained generation task, leveraging recent advancements in Autoregressive (AR) language models. However, AR-based Generative Retrieval methods…
Normalizing Flows (NFs) are a class of generative models distinguished by a mathematically invertible architecture, where the forward pass transforms data into a latent space for density estimation, and the reverse pass generates new…
Flow Matching has limited ability in achieving one-step generation due to its reliance on learned curved trajectories. Previous studies have attempted to address this limitation by either modifying the coupling distribution to prevent…
Retrieval Augmented Generation (RAG) systems often struggle with domain-specific knowledge due to performance deterioration of pre-trained embeddings and prohibitive computational costs of large language model (LLM)-based retrievers. While…
Planning is a critical component of end-to-end autonomous driving. However, prevailing imitation learning methods often suffer from mode collapse, failing to produce diverse trajectory hypotheses. Meanwhile, existing generative approaches…
Over the past year, the field of Natural Language Generation (NLG) has experienced an exponential surge, largely due to the introduction of Large Language Models (LLMs). These models have exhibited the most effective performance in a range…
The growing demand for text-to-image generation has led to rapid advances in generative modeling. Recently, text-to-image diffusion models trained with flow matching algorithms, such as FLUX, have achieved remarkable progress and emerged as…
Flow-based models have proven successful for time-series generation, particularly when defined in lower-dimensional latent spaces that enable efficient sampling. However, how to design latent representations with desirable equivariance…