相关论文: Diffusion Models as Masked Audio-Video Learners

Diffusion models have gained traction as powerful algorithms for synthesizing high-quality images. Central to these algorithms is the diffusion process, a set of equations which maps data to noise in a way that can significantly affect…

Contrastive audio-language pretraining yields powerful joint representations, yet a persistent audio-text modality gap limits the benefits of coupling multimodal encoders with large language models (LLMs). We present Diffusion-Link, a…

Learning robust representations for physiological time-series signals continues to pose a substantial challenge in developing efficient few-shot learning applications. This difficulty is largely due to the complex pathological variations in…

Speech enhancement significantly improves the clarity and intelligibility of speech in noisy environments, improving communication and listening experiences. In this paper, we introduce a novel pretraining feature-guided diffusion model…

We propose the first joint audio-video generation framework that brings engaging watching and listening experiences simultaneously, towards high-quality realistic videos. To generate joint audio-video pairs, we propose a novel Multi-Modal…

Video Frame Interpolation (VFI) remains a cornerstone in video enhancement, enabling temporal upscaling for tasks like slow-motion rendering, frame rate conversion, and video restoration. While classical methods rely on optical flow and…

With the rapid growth in deepfake video content, we require improved and generalizable methods to detect them. Most existing detection methods either use uni-modal cues or rely on supervised training to capture the dissonance between the…

We introduce a multi-modal diffusion model tailored for the bi-directional conditional generation of video and audio. We propose a joint contrastive training loss to improve the synchronization between visual and auditory occurrences. We…

Recent studies have demonstrated that vision models can effectively learn multimodal audio-image representations when paired. However, the challenge of enabling deep models to learn representations from unpaired modalities remains…

Recent Speech Large Language Models~(LLMs) have achieved impressive capabilities in end-to-end speech interaction. However, the prevailing autoregressive paradigm imposes strict serial constraints, limiting generation efficiency and…

Contrastive Language-Image Pre-training (CLIP), which excels at abstracting open-world representations across domains and modalities, has become a foundation for a variety of vision and multimodal tasks. However, recent studies reveal that…

We present a multimodal framework to learn general audio representations from videos. Existing contrastive audio representation learning methods mainly focus on using the audio modality alone during training. In this work, we show that…

End-to-end autonomous driving systems based on vision-language-action (VLA) models integrate multimodal sensor inputs and language instructions to generate planning and control signals. While autoregressive large language models and…

In this paper, we address the challenge of procedure planning in instructional videos, aiming to generate coherent and task-aligned action sequences from start and end visual observations. Previous work has mainly relied on text-level…

With recent advances in Multimodal Large Language Models (MLLMs) showing strong visual understanding and reasoning, interest is growing in using them to improve the editing performance of diffusion models. Despite rapid progress, most…

Recent advances in multimodal large language models (MLLMs) have enabled image-based question-answering capabilities. However, a key limitation is the use of CLIP as the visual encoder; while it can capture coarse global information, it…

Self-supervised learning has proved effective for skeleton-based human action understanding. However, previous works either rely on contrastive learning that suffers false negative problems or are based on reconstruction that learns too…

Audio and video are two most common modalities in the mainstream media platforms, e.g., YouTube. To learn from multimodal videos effectively, in this work, we propose a novel audio-video recognition approach termed audio video Transformer,…

Training diffusion models for audiovisual sequences allows for a range of generation tasks by learning conditional distributions of various input-output combinations of the two modalities. Nevertheless, this strategy often requires training…

This paper combines autoregressive and masked-diffusion training objectives without any architectural modifications, resulting in flexible language models that outperform single-objective models. Autoregressive modeling has been a popular…