# AVID: A Benchmark for Omni-Modal Audio-Visual Inconsistency Understanding via Agent-Driven Construction

arXiv: https://arxiv.org/abs/2604.13593 · HTML: https://mlsanity.com/paper/2604.13593/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Apr 2026.

## Built on by (most cited first, 2 of 2)

- [TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos](https://mlsanity.com/paper/2605.07593/) (2026)
- [SyncRA: Learning Temporal Correspondence in Omni-Modal Models](https://mlsanity.com/paper/2609.34363/) (2026)

## Abstract (arXiv)

We present AVID, the first large-scale benchmark for audio-visual inconsistency understanding in videos. While omni-modal large language models excel at temporally aligned tasks such as captioning and question answering, they struggle to perceive cross-modal conflicts, a fundamental human capability that is critical for trustworthy AI. Existing benchmarks predominantly focus on aligned events or deepfake detection, leaving a significant gap in evaluating inconsistency perception in long-form video contexts. AVID addresses this with: (1) a scalable construction pipeline comprising temporal segmentation that classifies video content into Active Speaker, Voiceover, and Scenic categories; an agent-driven strategy planner that selects semantically appropriate inconsistency categories; and five specialized injectors for diverse audio-visual conflict injection; (2) 11.2K long videos (avg. 235.5s) with 39.4K annotated inconsistency events and 78.7K segment clips, supporting evaluation across detection, temporal grounding, classification, and reasoning with 8 fine-grained inconsistency categories. Comprehensive evaluations of state-of-the-art omni-models reveal significant limitations in temporal grounding and reasoning. Our fine-tuned baseline, AVID-Qwen, achieves substantial improvements over the base model (2.8× higher BLEU-4 in segment reasoning) and surpasses all compared models in temporal grounding (mIoU: 36.1% vs 26.2%) and holistic understanding (SODA-m: 7.47 vs 6.15), validating AVID as an effective testbed for advancing trustworthy omni-modal AI systems.