6 papers
PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models
Xinyu Guo, Bin Xie, Wei Chai +4
Large-scale pretraining has made Vision-Language-Action (VLA) models promising foundations for generalist robot manipulation, yet adapting them to downstream tasks remains necessar…
ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling
Jianxuan Yang, Xinyue Guo, Zhi Cheng +10
Recent advances in video-to-audio (V2A) generation enable high-quality audio synthesis from visual content, yet achieving robust and fine-grained controllability remains challengin…
GenVideoLens: Where LVLMs Fall Short in AI-Generated Video Detection?
Yueying Zou, Pei Pei Li, Zekun Li +4
In recent years, AI-generated videos have become increasingly realistic and sophisticated. Meanwhile, Large Vision-Language Models (LVLMs) have shown strong potential for detecting…
AV-Edit: Multimodal Generative Sound Effect Editing via Audio-Visual Semantic Joint Control
Xinyue Guo, Xiaoran Yang, Lipan Zhang +3
Sound effect editing-modifying audio by adding, removing, or replacing elements-remains constrained by existing approaches that rely solely on low-level signal processing or coarse…
MultiSoundGen: Video-to-Audio Generation for Multi-Event Scenarios via SlowFast Contrastive Audio-Visual Pretraining and Direct Preference Optimization
Jianxuan Yang, Xiaoran Yang, Lipan Zhang +3
Current video-to-audio (V2A) methods struggle in complex multi-event scenarios (video scenarios involving multiple sound sources, sound events, or transitions) due to two critical…
MeanFlow-Accelerated Multimodal Video-to-Audio Synthesis via One-Step Generation
Xiaoran Yang, Jianxuan Yang, Xinyue Guo +3
A key challenge in synthesizing audios from silent videos is the inherent trade-off between synthesis quality and inference efficiency in existing methods. For instance, flow match…