Deferred Audio Pruning with Local Audio-Visual Dynamics for Omni-LLMs

arXiv:2608.08794 · cs.AI, cs.MM, cs.SD · Submitted 2026-08-09 · Read on arXiv

Kyeongyoon Lee, Hongyeob Kim, Youngeun Kim, Sungeun Hong

cs.AI, cs.MM, cs.SD

Submitted: 2026-08-09

Updated: 2026-08-11

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

Terminology

• Pruning — 52× in this paper · explained in 4 episodes
• Alignment — 35× in this paper · explained in 1 episode
• Accuracy — 34× in this paper · explained in 1 episode
• Benchmark — 31× in this paper · explained in 2 episodes
• Redundancy — 13× in this paper · explained in 2 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Hallucination — 7× in this paper · explained in 4 episodes
• Embeddings — 5× in this paper · explained in 2 episodes
• Anchor Tokens — 4× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition — 4× in this paper
• Optimal Transport — 4× in this paper · explained in 5 episodes
• Ablation study — 3× in this paper · explained in 1 episode
• Centered Kernel Alignment — 3× in this paper
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• European Conference on Computer Vision — 3× in this paper
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Hyperparameters — 3× in this paper · explained in 2 episodes
• LLM judge — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Distillation — 2× in this paper · explained in 2 episodes
• International Conference on Machine Learning — 2× in this paper
• KV cache — 2× in this paper · explained in 3 episodes
• Two-Stage Framework — 2× in this paper · explained in 2 episodes
• Centered Kernel Alignment (CKA) — 1× in this paper · explained in 2 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Daily Life — 1× in this paper
• F1 Score — 1× in this paper · explained in 3 episodes
• International Conference on Learning Representations — 1× in this paper
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
• Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs
• VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling
• Baichuan-Omni-1.5 Technical Report
• Ola: Pushing the Frontiers of Omni-Modal Language Model
• Qwen2.5-Omni Technical Report
• OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models
• AdaptInfer: Adaptive Token Pruning for Vision-Language Model Inference via Dynamical Text Guidance
• Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection