Related papers: Beyond Modality Collapse: Representations Blending…

Dataset distillation aims at synthesizing a dataset by a small number of artificially generated data items, which, when used as training data, reproduce or approximate a machine learning (ML) model as if it were trained on the entire…

Dataset Condensation aims to condense a large dataset into a smaller one while maintaining its ability to train a well-performing model, thus reducing the storage cost and training effort in deep learning applications. However, conventional…

Combining the respective advantages of cross-modality images can compensate for the lack of information in the single modality, which has attracted increasing attention of researchers into multi-modal image matching tasks. Meanwhile, due to…

The training of large multimodal models fundamentally relies on massive image-text datasets, which inevitably incur prohibitive computational overhead. Dataset selection offers a promising paradigm by identifying a highly informative…

Multimodal learning has shown great potentials in numerous scenes and attracts increasing interest recently. However, it often encounters the problem of missing modality data and thus suffers severe performance degradation in practice. To…

Dataset distillation or condensation aims to generate a smaller but representative subset from a large dataset, which allows a model to be trained more efficiently, meanwhile evaluating on the original testing data distribution to achieve…

Dataset distillation (DD) has emerged as a powerful paradigm for dataset compression, enabling the synthesis of compact surrogate datasets that approximate the training utility of large-scale ones. While significant progress has been…

Recent progress in image-to-video (I2V) diffusion models has significantly advanced the field of generative inbetweening, which aims to generate semantically plausible frames between two keyframes. In particular, inference-time sampling…

Heterogeneous gap among different modalities emerges as one of the critical issues in modern AI problems. Unlike traditional uni-modal cases, where raw features are extracted and directly measured, the heterogeneous nature of cross modal…

Training machine learning models on massive datasets is expensive and time-consuming. Dataset distillation addresses this by creating a small synthetic dataset that achieves the same performance as the full dataset. Recent methods use…

Dataset distillation plays a crucial role in creating compact datasets with similar training performance compared with original large-scale ones. This is essential for addressing the challenges of data storage and training costs. Prevalent…

Dataset distillation (DD) aims to generate a compact yet informative dataset that achieves performance comparable to the original dataset, thereby reducing demands on storage and computational resources. Although diffusion models have made…

Food recommendation systems serve as pivotal components in the realm of digital lifestyle services, designed to assist users in discovering recipes and food items that resonate with their unique dietary predilections. Typically, multi-modal…

Multimodal deep learning (MDL) has emerged as a transformative approach in computational pathology. By integrating complementary information from multiple data sources, MDL models have demonstrated superior predictive performance across…

Multimodal representation learning, exemplified by multimodal contrastive learning (MMCL) using image-text pairs, aims to learn powerful representations by aligning cues across modalities. This approach relies on the core assumption that…

Large video diffusion and flow models have achieved remarkable success in high-quality video generation, but their use in real-time interactive applications remains limited due to their inefficient multi-step sampling process. In this work,…

Dataset distillation (DD) compresses a large training set into a small synthetic set for efficient training, but most DD methods optimize only clean accuracy and leave robustness uncontrolled. Recent robust DD methods improve robustness,…

Different modalities hold considerable gaps in optimization trajectories, including speeds and paths, which lead to modality laziness and modality clash when jointly training multimodal models, resulting in insufficient and imbalanced…

This work introduces Variational Diffusion Distillation (VDD), a novel method that distills denoising diffusion policies into Mixtures of Experts (MoE) through variational inference. Diffusion Models are the current state-of-the-art in…

Compositional diffusion planning generates long-horizon trajectories by stitching together overlapping short-horizon segments through score composition. However, when local plan distributions are multimodal, existing compositional methods…