相关论文: RefAlign: Representation Alignment for Reference-t…

Open-vocabulary grounding requires accurate vision-language alignment under weak supervision, yet existing methods either rely on global sentence embeddings that lack fine-grained expressiveness or introduce token-level alignment with…

In this paper, we focus on enhancing a diffusion-based text-to-video (T2V) model during the post-training phase by distilling a highly capable consistency model from a pretrained T2V model. Our proposed method, T2V-Turbo-v2, introduces a…

Text-to-video generation is an emerging field in generative AI, enabling the creation of realistic, semantically accurate videos from text prompts. While current models achieve impressive visual quality and alignment with input text, they…

The quality of finetuning data is crucial for aligning large language models (LLMs) with human values. Current methods to improve data quality are either labor-intensive or prone to factual errors caused by LLM hallucinations. This paper…

Text-to-video retrieval essentially aims to train models to align visual content with textual descriptions accurately. Due to the impressive general multimodal knowledge demonstrated by image-text pretrained models such as CLIP, existing…

Text-driven video editing enables users to modify video content only using text queries. While existing methods can modify video content if explicit descriptions of editing targets with precise spatial locations and temporal boundaries are…

The Text-to-Video (T2V) model aims to generate dynamic and expressive videos from textual prompts. The generation pipeline typically involves multiple modules, such as language encoder, Diffusion Transformer (DiT), and Variational…

With the recent progress in large-scale vision and language representation learning, Vision Language Pre-training (VLP) models have achieved promising improvements on various multi-modal downstream tasks. Albeit powerful, these models have…

Continual learning for vision-language models has achieved remarkable performance through synthetic replay, where samples are generated using Stable Diffusion to regularize during finetuning and retain knowledge. However, real-world…

Diffusion Transformers (DiT) have become the de-facto model for generating high-quality visual content like videos and images. A huge bottleneck is the attention mechanism where complexity scales quadratically with resolution and video…

Numerous text-to-video (T2V) editing methods have emerged recently, but the lack of a standardized benchmark for fair evaluation has led to inconsistent claims and an inability to assess model sensitivity to hyperparameters. Fine-grained…

Despite impressive visual fidelity, current text-to-image (T2I) diffusion models struggle to depict rare, complex, or culturally nuanced concepts due to training data limitations. We introduce RAVEL, a training-free framework that…

Text-to-video (T2V) generative models have advanced significantly, yet their ability to compose different objects, attributes, actions, and motions into a video remains unexplored. Previous text-to-video benchmarks also neglect this…

Reference-guided video editing takes a source video, a text instruction, and a reference image as inputs, requiring the model to faithfully apply the instructed edits while preserving original motion and unedited content. Existing methods…

Video-to-Audio (V2A) Generation achieves significant progress and plays a crucial role in film and video post-production. However, current methods overlook the cinematic language, a critical component of artistic expression in filmmaking.…

Reference-guided image generation has progressed rapidly, yet current diffusion models still struggle to preserve fine-grained visual details when refining a generated image using a reference. This limitation arises because VAE-based latent…

In this paper, we propose a novel reference based image super-resolution approach via Variational AutoEncoder (RefVAE). Existing state-of-the-art methods mainly focus on single image super-resolution which cannot perform well on large…

We propose an approach to referring expression generation (REG) in visually grounded dialogue that is meant to produce referring expressions (REs) that are both discriminative and discourse-appropriate. Our method constitutes a two-stage…

Latent diffusion models (LDMs) achieve state-of-the-art image synthesis, yet their reconstruction-style denoising objective provides only indirect semantic supervision: high-level semantics emerge slowly, requiring longer training and…

Modern video codecs and learning-based approaches struggle for semantic reconstruction at extremely low bit-rates due to reliance on low-level spatiotemporal redundancies. Generative models, especially diffusion models, offer a new paradigm…