AVTrace: Diagnosing Audio-Visual Temporal Reasoning in Omni Models

arXiv:2609.19991 · cs.CV, cs.AI · Submitted 2026-09-17 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-17

Updated: 2026-09-17

Code: https://github.com/YapengTian/AVVP-ECCV20

Project page: https://unav100.github.io

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 41× in this paper · explained in 2 episodes
• Grounding — 31× in this paper · explained in 3 episodes
• Accuracy — 30× in this paper · explained in 1 episode
• Verification — 9× in this paper · explained in 2 episodes
• Temporal Reasoning — 8× in this paper · explained in 2 episodes
• Alignment — 6× in this paper · explained in 1 episode
• Abstention — 4× in this paper · explained in 1 episode
• Perplexity — 4× in this paper · explained in 3 episodes
• Provenance — 3× in this paper · explained in 3 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• Visual Grounding — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Audio-Visual Temporal Reasoning Assessment and Capability Evaluation — 1× in this paper
• AudioVisual Temporal Reasoning Assessment and Capability Evaluation — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Multimodal Fusion — 1× in this paper · explained in 3 episodes
• Structural Constraints — 1× in this paper · explained in 2 episodes

Sources

• Gemma 4 Technical Report
• LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos
• WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
• AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models
• Learning to Answer Questions in Dynamic Audio-Visual Scenarios
• VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models
• Audio-Visual Event Localization in Unconstrained Videos
• InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue
• CoVoST 2 and Massively Multilingual Speech-to-Text Translation
• MAVERIX: Multimodal Audio-Visual Evaluation and Recognition IndeX
• Qwen2.5-Omni Technical Report
• Qwen3-Omni Technical Report
• Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models
• Unlocking Cognitive Capabilities and Analyzing the Perception-Logic Trade-off
• Audio-Visual Segmentation
• Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models