PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation

arXiv:2512.23994 · cs.SD, cs.AI · Submitted 2025-12-30 · Read on arXiv

cs.SD, cs.AI

Submitted: 2025-12-30

Updated: 2026-10-11

Code: https://github.com/imxtx/PhyAVBench

Terminology

• Benchmark — 3× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes

Sources

• SyncFlow: Toward Temporally Aligned Joint Audio-Video Generation from Text
• UniVerse-1: Unified Audio-Video Generation via Stitching of Experts
• Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation
• CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
• ModelScope Text-to-Video Technical Report
• AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation
• UniForm: A Unified Multi-Task Diffusion Transformer for Audio-Video Generation
• SAVGBench: Benchmarking Spatially Aligned Audio-Video Generation
• VABench: A Comprehensive Benchmark for Audio-Video Generation
• T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation
• Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model
• FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds
• HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation
• ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing
• PEAVS: Perceptual Evaluation of Audio-Visual Synchrony Grounded in Viewers' Opinion Scores
• Text-to-Audio Generation Synchronized with Videos
• FoleyBench: A Benchmark For Video-to-Audio Models
• Long-Video Audio Synthesis with Multi-Agent Collaboration
• LTX-2: Efficient Joint Audio-Visual Foundation Model
• MOVA: Towards Scalable and Synchronized Video-Audio Generation

Related papers

• 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
• AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
• SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
• WASIL: In-the-Wild Arabic Spoken Interactions with LLMs