MusTBench: Benchmarking and Advancing Temporal Grounding in Music LLMs

arXiv:2605.29300 · cs.CL, cs.AI, cs.SD · Submitted 2026-05-28 · Read on arXiv

cs.CL, cs.AI, cs.SD

Submitted: 2026-05-28

Updated: 2026-09-01

Terminology

• Grounding — 53× in this paper · explained in 3 episodes
• Benchmark — 21× in this paper · explained in 2 episodes
• Fine-Tuning — 19× in this paper · explained in 5 episodes
• GRPO — 18× in this paper · explained in 6 episodes
• Adaptation — 9× in this paper · explained in 1 episode
• Ablation — 8× in this paper · explained in 1 episode
• Mood Trajectory Reasoning — 8× in this paper
• Alignment — 7× in this paper · explained in 1 episode
• Temporal Source Grounding — 6× in this paper
• Transition-aware Description — 6× in this paper
• Adam — 5× in this paper · explained in 2 episodes
• Global Temporal Ordering — 5× in this paper
• Core — 4× in this paper · explained in 2 episodes
• Local Transition Recognition — 4× in this paper
• Accuracy — 3× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 4 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Feature Extraction — 2× in this paper · explained in 2 episodes
• Hallucination — 2× in this paper · explained in 4 episodes
• Temporal Reasoning — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• International Society for Music Information Retrieval — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Qwen2-Audio Technical Report
• Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• gpt-oss-120b & gpt-oss-20b Model Card
• MusicLM: Generating Music From Text
• Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music
• Music Flamingo: Scaling Music Understanding in Audio Language Models
• SongFormer: Scaling Music Structure Analysis with Heterogeneous Supervision
• GPT-4o System Card
• TAC: Timestamped Audio Captioning
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• SALMONN: Towards Generic Hearing Abilities for Large Language Models
• LLaMA: Open and Efficient Foundation Language Models
• MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models
• MuMu-LLaMA: Multi-modal Music Understanding and Generation via Large Language Models
• Qwen2.5-Omni Technical Report
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Decoupled Weight Decay Regularization
• Qwen3 Technical Report
• Not in Sync: Unveiling Temporal Bias in Audio Chat Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering