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.
By Akshita Gupta, Aditya Arora, Federico Tombari, Marcus Rohrbach, Anna Rohrbach
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...
PRISM‑Bench is an audio‑centric diagnostic benchmark for text‑to‑audio‑video generation, built from 900 human‑verified samples. It evaluates audio along two axes—audio type (speech, music, sound) and sound‑source visibility (on‑screen vs. off‑screen)—across four perceptual dimensions (audio‑visual coherence, audio quality, audio expressiveness, and prompt following) using 35 fine‑grained criteria. The benchmark employs an enhanced MLLM‑as‑a‑Judge protocol that aligns strongly with human raters, revealing a performance gap between frontier and open‑source T2AV models and highlighting overfitting to perceptual fidelity while struggling with complex grounding and control tasks, especially for music and synchronized on‑screen audio.
By Yuchen Sun, Qian Yang, Jun Wang, Detai Xin, Guoqiao Yu, Guanglu Wan, Qi Jia
arXiv:2609.30631v1 Announce Type: cross
Abstract: Online audio-visual target-speaker extraction aims to remove competing voices while preserving speech quality and bounding lookahead. Existing extrac...
By Rayhan Rashed, Senja Filipi, Ross Cutler
TiTok is an audio‑visual large language model designed for multi‑segment temporal grounding in untrimmed videos. It introduces Time Token Interleaving (TTI) to align temporal perception with prediction, and uses decoupled reinforcement‑learning rewards (global, local, count, precision, format) optimized via GDPO. Evaluated on a new UnAV‑100 protocol with the CountF1 metric, TiTok achieves state‑of‑the‑art results (65.7 mIoU, 0.58 CountF1).
By Eunji Shin, Dahyun Choi, Seungyeon Jo, Yejin Hong, Jiyoung Lee
arXiv:2606. 02642v1 Announce Type: cross Abstract: Despite the success of audio-visual large-language models (LLMs), they can produce plausible but ungrounded outputs, termed hallucination.
By Chenshuang Zhang, Kyeong Seon Kim, Chengxin Liu, Tae-Hyun Oh
The paper investigates why joint audio–video generators often learn to predict sound from visual appearance rather than from the underlying event, a problem termed the visual shortcut. By constructing a controlled causal model where audio is independent of video appearance, the authors show that common remedies such as shared latent spaces fail to prevent this shortcut. They propose that intervening on the nuisance appearance is necessary and sufficient for counterfactual invariance, and validate this approach across synthetic and real datasets, highlighting the remaining challenge of unknown nuisances.
By Jian Xu, Delu Zeng, John Paisley
The paper investigates how joint audio–video generation models learn to associate sound with visual appearance rather than the underlying causal event, a problem termed the visual shortcut. By constructing a structural causal model where audio is independent of video appearance, the authors demonstrate that cross‑attention and shared latent approaches fail when appearance‑event correlations are broken, and that common‑cause routing does not solve the issue. They propose blocking the shortcut via interventions on nuisance variables, proving that counterfactual invariance is necessary and sufficient for identifying the causal predictor, and validate this approach on synthetic and real datasets, including a pretrained video‑to‑audio generator.
By Jian Xu, Delu Zeng, John Paisley, Qibin Zhao
AVTrace is a diagnostic suite designed to evaluate audio‑visual temporal reasoning in omni models. It covers tasks such as onset and span grounding, synchronization, next‑step prediction, cross‑modal localization, chain parsing, and event‑conditioned comprehension, providing 34,114 training examples and balanced development and test splits. Five open omni models were tested, all scoring below the majority‑label baseline on synchronization verification and showing low performance on chain parsing and event‑conditioned tasks, while parameter‑efficient temporal post‑training improved some metrics.
By Longyin Zhang, Parth Sakhare Mahendra, Chengwei Wei, Ning Zhang, Lim Ming Chong, Sirui He, Ai Ti Aw
arXiv:2608.05776v2 Announce Type: replace
Abstract: Autoregressive continuation provides a natural path toward minute-scale audio-visual generation by repeatedly extending a short-window generator co...
By Lisai Zhang, Yidi Wu, Qi Liu, Xin Ma, Yang Ding, Gang Yue, Siqian Yang, Jingyuan Chen, Lin Ma, Yaohui Wang
Vorch-Human is a unified framework for human‑centric audio‑visual generation that handles multiple tasks—animating a person from speech, jointly generating speech and video from a voice reference, and synthesizing a scene from paired appearance and voice references—using a single dual‑stream audio‑video diffusion transformer. The model incorporates clean condition‑audio and condition‑video tokens, per‑token task embeddings, temporal position types, condition masks, and a shared multimodal prompt encoder to express diverse inputs such as driving speech, timbre examples, first frames, and subject images. A two‑level data pipeline supplies the necessary supervision by extracting speech, appearance, and timbre annotations from clips and linking consistent identity and outfit references across videos, while a frozen‑prefix recurrence enables long‑form audio‑driven generation with reduced boundary discontinuity and identity drift.
By Yang Ding, Haoran Yu, Xin Ma, Yulei Lu, Menglin Han, Yaole Wang, Siqian Yang, Gang Yue, Kaihao Zhang, Yaohui Wang, Lin Ma
The paper evaluates audio‑visual predictive turn‑taking models trained on clean data when applied to a noisy cocktail‑party scenario derived from the AVCocktail dataset. Results show a consistent performance drop—up to 38% relative in weighted F1—across both audio and visual modalities, with fine‑tuning improving robustness but varying by modality and pre‑training data size. The study highlights differing generalisation and adaptation abilities of audio versus visual inputs and underscores the need for robust modelling strategies in noisy human interactions.
By Long-Vu Hoang, Naomi Harte