Related papers: Cross-Frame Representation Alignment for Fine-Tuni…

Video generation based on diffusion models presents a challenging multimodal task, with video editing emerging as a pivotal direction in this field. Recent video editing approaches primarily fall into two categories: training-required and…

Enabling VLA models to predict environmental dynamics, known as world modeling, has been recognized as essential for improving robotic reasoning and generalization. However, current approaches face two main issues: 1. The training objective…

Medical contrastive vision-language pre-training (VLP) has demonstrated significant potential in improving performance on downstream tasks. Traditional approaches typically employ contrastive learning, treating paired image-report samples…

In cross-domain few-shot classification (CFC), recent works mainly focus on adapting a simple transformation head on top of a frozen pre-trained backbone with few labeled data to project embeddings into a task-specific metric space where…

With the rapid growth of video data, text-video retrieval technology has become increasingly important in numerous application scenarios such as recommendation and search. Early text-video retrieval methods suffer from two critical…

In recent years, pre-trained visual-linguistic models have demonstrated tremendous potential, becoming a crucial foundational framework for numerous downstream tasks. However, the information density between text and images is not uniformly…

In the rapidly evolving field of artificial intelligence, multimodal models, e.g., integrating vision and language into visual-language models (VLMs), have become pivotal for many applications, ranging from image captioning to multimodal…

Video generation has achieved remarkable progress with the introduction of diffusion models, which have significantly improved the quality of generated videos. However, recent research has primarily focused on scaling up model training,…

Remote sensing change detection is often challenged by spatial misalignment between bi-temporal images, especially when acquisitions are separated by long seasonal or multi-year gaps. While modern convolutional and transformer-based models…

Vision-Language Models (VLMs) demonstrate remarkable general-purpose capabilities but often fall short in specialized domains such as medical imaging or geometric problem-solving. Supervised Fine-Tuning (SFT) can enhance performance within…

Physics-informed diffusion models typically enforce PDE constraints only on final outputs, leaving intermediate representations unconstrained and prone to shortcut learning under shifted boundary conditions. We introduce **REPA-P**, a…

Vision-Language Models (VLMs) such as CLIP learn a shared embedding space for images and text, yet their representations remain geometrically separated, a phenomenon known as the modality gap. This gap limits tasks requiring cross-modal…

The goal of this paper is to optimize the training process of diffusion-based text-to-speech models. While recent studies have achieved remarkable advancements, their training demands substantial time and computational costs, largely due to…

Cross-resolution person re-identification (CR-ReID) remains challenging in practical surveillance, where camera quality and capture distance lead to substantial resolution gaps between low-resolution (LR) queries and high-resolution (HR)…

State-of-the-art video generation models produce remarkable photorealism, but they lack the precise control required to align generated content with specific scene requirements. Furthermore, without an underlying explicit geometry, these…

Recent advancements in human preference optimization, initially developed for Language Models (LMs), have shown promise for text-to-image Diffusion Models, enhancing prompt alignment, visual appeal, and user preference. Unlike LMs,…

Rotary Position Embedding (RoPE) has shown strong performance in text-based Large Language Models (LLMs), but extending it to video remains a challenge due to the intricate spatiotemporal structure of video frames. Existing adaptations,…

The challenge in fine-grained visual categorization lies in how to explore the subtle differences between different subclasses and achieve accurate discrimination. Previous research has relied on large-scale annotated data and pre-trained…

Video super-resolution remains a major challenge in low-level vision tasks. To date, CNN- and Transformer-based methods have delivered impressive results. However, CNNs are limited by local receptive fields, while Transformers struggle with…

Despite the huge effort in developing novel regularizers for Domain Generalization (DG), adding simple data augmentation to the vanilla ERM which is a practical implementation of the Vicinal Risk Minimization principle (VRM)…