相关论文: Variance Reduction for Expectations with Diffusion…

Diffusion large language models (dLLMs) offer parallel decoding and bidirectional context, but state-of-the-art dLLMs require billions of parameters for competitive performance. While existing distillation methods for dLLMs reduce inference…

The core of knowledge distillation lies in transferring the teacher's rich 'dark knowledge'-subtle probabilistic patterns that reveal how classes are related and the distribution of uncertainties. While this idea is well established,…

Self-supervised learning has achieved remarkable success in learning visual representations from clean data, yet remains challenging when clean observations are sparse or not available at all. In this paper, we demonstrate that pretrained…

Recent recommender systems have shown remarkable performance by using an ensemble of heterogeneous models. However, it is exceedingly costly because it requires resources and inference latency proportional to the number of models, which…

Wepresent Alice v1, a 14-billion parameter open-source video generation model that achieves state-of-the-art quality through consistency distillation with score regularization (rCM). Contrary to conventional distillation-which trades…

Large generative diffusion models have revolutionized text-to-image generation and offer immense potential for conditional generation tasks such as image enhancement, restoration, editing, and compositing. However, their widespread adoption…

Ensembles of deep neural networks have demonstrated superior performance, but their heavy computational cost hinders applying them for resource-limited environments. It motivates distilling knowledge from the ensemble teacher into a smaller…

Recent progress in deep latent variable models has largely been driven by the development of flexible and scalable variational inference methods. Variational training of this type involves maximizing a lower bound on the log-likelihood,…

Significant advancements in image generation have been made with diffusion models. Nevertheless, when contrasted with previous generative models, diffusion models face substantial computational overhead, leading to failure in real-time…

Diffusion models have achieved remarkable generation quality, but they suffer from significant inference cost due to their reliance on multiple sequential denoising steps, motivating recent efforts to distill this inference process into a…

In this contribution, we propose a new computationally efficient method to combine Variational Inference (VI) with Markov Chain Monte Carlo (MCMC). This approach can be used with generic MCMC kernels, but is especially well suited to…

We present a new antithetic multilevel Monte Carlo (MLMC) method for the estimation of expectations with respect to laws of diffusion processes that can be elliptic or hypo-elliptic. In particular, we consider the case where one has to…

Although the vision-and-language pretraining (VLP) equipped cross-modal image-text retrieval (ITR) has achieved remarkable progress in the past two years, it suffers from a major drawback: the ever-increasing size of VLP models restricts…

We introduce overdispersed black-box variational inference, a method to reduce the variance of the Monte Carlo estimator of the gradient in black-box variational inference. Instead of taking samples from the variational distribution, we use…

In this paper, we propose that small models may not need to absorb the cost of pre-training to reap its benefits. Instead, they can capitalize on the astonishing results achieved by modern, enormous models to a surprising degree. We observe…

Control variates are variance reduction tools for Monte Carlo estimators. They can provide significant variance reduction, but usually require a large number of samples, which can be prohibitive when sampling or evaluating the integrand is…

Diffusion models produce high-quality text-to-image results, but their iterative denoising is computationally expensive.Distribution Matching Distillation (DMD) emerges as a promising path to few-step distillation, but suffers from…

Diffusion models have emerged as powerful generative tools across various domains, yet tailoring pre-trained models to exhibit specific desirable properties remains challenging. While reinforcement learning (RL) offers a promising…

Contrastive Learning and Masked Image Modelling have demonstrated exceptional performance on self-supervised representation learning, where Momentum Contrast (i.e., MoCo) and Masked AutoEncoder (i.e., MAE) are the state-of-the-art,…

Score Distillation Sampling (SDS) has emerged as an effective technique for leveraging 2D diffusion priors for tasks such as text-to-3D generation. While powerful, SDS struggles with achieving fine-grained alignment to user intent. To…