相关论文: Learning Multimodal Latent Space with EBM Prior an…

As deep neural networks become more adept at traditional tasks, many of the most exciting new challenges concern multimodality---observations that combine diverse types, such as image and text. In this paper, we introduce a family of…

We propose a latent space energy-based prior model for text generation and classification. The model stands on a generator network that generates the text sequence based on a continuous latent vector. The energy term of the prior model…

We investigate the use of normalizing flow (NF) models as flexible priors in Bayesian inference via Markov Chain Monte Carlo (MCMC) sampling for iterative Bayesian calibration. Trained on posteriors from previous analyses, these models can…

Energy-based models (EBMs) offer a flexible framework for parameterizing probability distributions using neural networks. However, learning EBMs by exact maximum likelihood estimation (MLE) is generally intractable, due to the need to…

Multimodal Knowledge Graphs (MKGs) extend traditional knowledge graphs by incorporating visual and textual modalities, enabling richer and more expressive entity representations. However, existing MKGs often suffer from incompleteness,…

Neural language models can be successfully trained on source code, leading to applications such as code completion. However, their versatile autoregressive self-supervision objective overlooks important global sequence-level features that…

A unified diffusion framework for multi-modal generation and understanding has the transformative potential to achieve seamless and controllable image diffusion and other cross-modal tasks. In this paper, we introduce MMGen, a unified…

Empowering Large Multimodal Models (LMMs) with image generation often leads to catastrophic forgetting in understanding tasks due to severe gradient conflicts. While existing paradigms like Mixture-of-Transformers (MoT) mitigate this…

One of the primary areas of interest in High Performance Computing is the improvement of performance of parallel workloads. Nowadays, compilable source code-based optimization tasks that employ deep learning often exploit LLVM Intermediate…

When using deep, multi-layered architectures to build generative models of data, it is difficult to train all layers at once. We propose a layer-wise training procedure admitting a performance guarantee compared to the global optimum. It is…

Arriving at the complete probabilistic knowledge of a domain, i.e., learning how all variables interact, is indeed a demanding task. In reality, settings often arise for which an individual merely possesses partial knowledge of the domain,…

In recent years, large-scale pre-trained multimodal models (LMMs) generally emerge to integrate the vision and language modalities, achieving considerable success in multimodal tasks, such as text-image classification. The growing size of…

Concept bottleneck models (CBM) aim to produce inherently interpretable models that rely on human-understandable concepts for their predictions. However, existing approaches to design interpretable generative models based on CBMs are not…

This paper proposes a latent space energy-based prior model for semi-supervised learning. The model stands on a generator network that maps a latent vector to the observed example. The energy term of the prior model couples the latent…

Semantic word embeddings represent the meaning of a word via a vector, and are created by diverse methods. Many use nonlinear operations on co-occurrence statistics, and have hand-tuned hyperparameters and reweighting methods. This paper…

We present a conditional generative model that maps low-dimensional embeddings of multiple modalities of data to a common latent space hence extracting semantic relationships between them. The embedding specific to a modality is first…

This paper introduces a Bayesian framework that combines Markov chain Monte Carlo (MCMC) sampling, dimensionality reduction, and neural density estimation to efficiently handle inverse problems that (i) must be solved multiple times, and…

Knowledge retrieval with multi-modal queries plays a crucial role in supporting knowledge-intensive multi-modal applications. However, existing methods face challenges in terms of their effectiveness and training efficiency, especially when…

Generative models (e.g., GANs, diffusion models) learn the underlying data distribution in an unsupervised manner. However, many applications of interest require sampling from a particular region of the output space or sampling evenly over…

Model-based offline reinforcement learning is brittle under distribution shift: policy improvement drives rollouts into state--action regions weakly supported by the dataset, where compounding model error yields severe value overestimation.…