Related papers: An Empirical Study On Contrastive Search And Contr…

Recent studies have demonstrated that gradient matching-based dataset synthesis, or dataset condensation (DC), methods can achieve state-of-the-art performance when applied to data-efficient learning tasks. However, in this study, we prove…

Cross-modal attention mechanisms have been widely applied to the image-text matching task and have achieved remarkable improvements thanks to its capability of learning fine-grained relevance across different modalities. However, the…

Energy-Based Models (EBMs) have been widely used for generative modeling. Contrastive Divergence (CD), a prevailing training objective for EBMs, requires sampling from the EBM with Markov Chain Monte Carlo methods (MCMCs), which leads to an…

Most approaches to cross-modal retrieval (CMR) focus either on object-centric datasets, meaning that each document depicts or describes a single object, or on scene-centric datasets, meaning that each image depicts or describes a complex…

This paper addresses the performance bottlenecks of existing text-driven image generation methods in terms of semantic alignment accuracy and structural consistency. A high-fidelity image generation method is proposed by integrating…

Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel…

Diffusion probabilistic models (DPMs) have become a popular approach to conditional generation, due to their promising results and support for cross-modal synthesis. A key desideratum in conditional synthesis is to achieve high…

Generating diverse and relevant questions over text is a task with widespread applications. We argue that commonly-used evaluation metrics such as BLEU and METEOR are not suitable for this task due to the inherent diversity of reference…

Video-grounded dialogue systems aim to integrate video understanding and dialogue understanding to generate responses that are relevant to both the dialogue and video context. Most existing approaches employ deep learning models and have…

This paper studies constrained text generation, which is to generate sentences under certain pre-conditions. We focus on CommonGen, the task of generating text based on a set of concepts, as a representative task of constrained text…

Following SimCSE, contrastive learning based methods have achieved the state-of-the-art (SOTA) performance in learning sentence embeddings. However, the unsupervised contrastive learning methods still lag far behind the supervised…

Change detection (CD) identifies scene changes from multi-temporal observations and is widely used in urban development and environmental monitoring. Most existing CD methods rely on supervised learning, making performance strongly…

Recently, a method [7] was proposed to generate contrastive explanations for differentiable models such as deep neural networks, where one has complete access to the model. In this work, we propose a method, Model Agnostic Contrastive…

Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By…

The CLIP model has been recently proven to be very effective for a variety of cross-modal tasks, including the evaluation of captions generated from vision-and-language architectures. In this paper, we propose a new recipe for a…

Multi-document question generation focuses on generating a question that covers the common aspect of multiple documents. Such a model is useful in generating clarifying options. However, a naive model trained only using the targeted…

In the popular video coding trend, the encoder has the task to exploit both spatial and temporal redundancies present in the video sequence, which is a complex procedure. As a result almost all video encoders have five to ten times more…

Collecting human judgements is currently the most reliable evaluation method for natural language generation systems. Automatic metrics have reported flaws when applied to measure quality aspects of generated text and have been shown to…

Large language Model (LLM)-assisted algorithm discovery is an iterative, black-box optimization process over programs to approximatively solve a target task, where an LLM proposes candidate programs and an external evaluator provides task…

We present a new supervised learning technique for the Variational AutoEncoder (VAE) that allows it to learn a causally disentangled representation and generate causally disentangled outcomes simultaneously. We call this approach Causally…