OmniRoute: Mapping Temporal Semantic Evidence to Audio-Visual Token Budgets for Efficient Omnimodal Large Language Models

arXiv:2609.37052 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Accuracy — 21× in this paper · explained in 1 episode
• Benchmark — 6× in this paper · explained in 2 episodes
• Budget-Constrained Semantic Compression — 5× in this paper
• Ablation — 3× in this paper · explained in 1 episode
• Embeddings — 3× in this paper · explained in 2 episodes
• Pruning — 3× in this paper · explained in 4 episodes
• Temporal Evidence-Guided Budgeting — 3× in this paper
• Alignment — 2× in this paper · explained in 1 episode
• Calibration — 2× in this paper · explained in 7 episodes
• Core — 2× in this paper · explained in 2 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Training-Free Framework — 1× in this paper · explained in 2 episodes

Sources

• OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
• InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue
• Qwen3-Omni Technical Report
• Qwen3.5-Omni Technical Report
• OmniMem: Perturbation-aware Memory Compression for Streaming Audio-Visual LLMs
• OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
• EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs
• OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models
• FastAV: Efficient Token Pruning for Audio-Visual Large Language Model Inference
• OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models
• OmniDrop: Layer-wise Token Pruning for Omni-modal LLMs via Query-Guidance
• AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression
• WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
• 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