arXiv:2609.36503v1 Announce Type: new Abstract: Adding or removing a sounding object requires coordinated changes to visual content and sound while preserving the surrounding scene. Yet paired superv...
Recent advances in generative video modeling have enabled diverse generation, reference-based synthesis, extension, and editing, but existing approaches often rely on fragmented task-specific models. A general model must distinguish heterogeneous target, source, and reference signals to determine what to generate, preserve, or use as guidance, while reducing interference among tasks.
arXiv:2607. 10299v1 Announce Type: new Abstract: Recent advances in large-scale multimodal models have drivenremarkable progress in vision-language tasks; however, comprehensiveomni-modal understanding remains under-explored, largely due to thescarcity of datasets with rich, explicitly aligned auditory cues.
arXiv:2608. 09288v1 Announce Type: cross Abstract: Audio-visual speech enhancement under real-world conditions remains challenging due to unreliable visual inputs and the lack of large-scale training data with realistic acoustic conditions.
arXiv:2604.15086v3 Announce Type: replace-cross Abstract: Recent advances in video-to-audio (V2A) generation enable high-quality audio synthesis from visual content, yet achieving robust and fine-gra...
Video-HolmesV2 is a new benchmark that tests multimodal large language models on their ability to reason with spatio‑temporal audio‑visual evidence in long videos. It requires models to justify answers with precise evidence, uses a multi‑model cross‑verification pipeline and a spatio‑temporal evidence‑aware metric, and introduces an audio‑text guided token compression framework to reduce long‑context noise. In evaluations, even strong proprietary models score below 60% while the proposed approach outperforms comparable open‑source omni‑models.
Multimodal Large Language Models have demonstrated impressive video understanding, yet their ability to reason over long-form narratives is often masked by visual-centric evaluations and inefficient c...
Audio Description (AD) provides spoken narration of visual events during dialogue gaps, making movies accessible to visually impaired audiences. The problem requires determining both what (which visua...
arXiv:2506. 20995v4 Announce Type: replace-cross Abstract: We propose a step-by-step video-to-audio (V2A) generation method that provides finer control over the generation process and more realistic audio synthesis.
AVENUE is a new benchmark and evaluation framework for audio‑video editing that includes 1,291 source clips and 7,957 editing instructions covering audio‑targeted, video‑targeted, and coupled edits. It introduces a sample‑specific, modality‑aware evaluation that specifies the intended change and the content that must remain unchanged. The study applies this framework to joint, sequential, and separate editing models, revealing that existing models often alter unintended modalities, highlighting a key challenge in controllable AV editing.
arXiv:2602. 03762v4 Announce Type: replace-cross Abstract: Visually-guided acoustic highlighting seeks to rebalance audio in alignment with the accompanying video, creating a coherent audio-visual experience.
The paper introduces Cue2Narrate, a two‑stage pipeline that jointly predicts what visual events to narrate and when to insert the narration in long, untrimmed movie clips. It uses a dual‑head audio‑visual localizer to identify visual cue and narration windows, followed by a LoRA‑adapted vision‑language model that generates concise audio descriptions, trained with a Description Ranking Loss. The authors also present the LongLSMDC benchmark, comprising up to 8‑minute clips, and show that Cue2Narrate outperforms video‑only and audio‑only baselines by 5–12 points in average mAP and improves AD generation over fine‑tuned base VLMs.