CrossEdit: Cross-Modal Training Enables Rich Audio-Visual Editing
cs.SD, eess.AS, eess.IV
Submitted: 2026-10-07
Updated: 2026-10-27
Comments: 27 pages (10 main + 1 limitations); 8 figures
Project page: https://wanchichen.github.io/crossedit
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen3-VL Technical Report
- HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning
- AudioChat: Unified Audio Storytelling, Editing, and Understanding with Transfusion Forcing
- Qwen2-Audio Technical Report
- Emerging Properties in Unified Multimodal Pretraining
- Recomposer: Event-roll-guided generative audio editing
- TokenFlow: Consistent Diffusion Features for Consistent Video Editing
- Contrastive Audio-Visual Masked Autoencoder
- AudioStory: Generating Long-Form Narrative Audio with Large Language Models
- LTX-2: Efficient Joint Audio-Visual Foundation Model
- OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing
- TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization
- GPT-4o System Card
- Coherent Audio-Visual Editing via Conditional Audio Generation Following Video Edits
- OpenAI o1 System Card
- Auto-Encoding Variational Bayes
- TAC: Timestamped Audio Captioning
- Guiding Audio Editing with Audio Language Model
- SpongeBob: Sync-Aware Harmonious Audio-Visual Generative Editing
- Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation
Related papers
- Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
- MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control
- Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems