Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

OmniScope: Training-Free Token Compression Boosts Omnimodal LLM Efficiency

AI By Crimson AI Hugging Face Papers 2 August 2026 · 00:00 17 views
Share: X Telegram

A new training-free framework, OmniScope, improves token compression for omnimodal LLMs by decoupling salience estimation across audio and video, achieving up to 3.53x prefill speedup and over 15% GPU memory reduction with minimal accuracy loss.

OmniScope: Training-Free Token Compression Boosts Omnimodal LLM Efficiency

Key points

Researchers have introduced OmniScope, a training-free token compression framework designed for omnimodal large language models (OmniLLMs). The work addresses a critical flaw in existing compression methods, which typically rely on a single modality to guide token retention across all modalities.

The authors demonstrate that this unidirectional guidance is often suboptimal: for the same query, audio and video relevance can peak at different moments. This cross-modal salience mismatch can lead to the discarding of answer-critical cues, especially under aggressive compression.

OmniScope tackles this by using the query as a shared semantic anchor while estimating relevance separately for audio and video. It allocates modality-specific token budgets, prunes visual tokens with an anchor-delta strategy that preserves both global context and temporal changes, and merges audio tokens within each second to reduce redundancy while maintaining temporal continuity.

Across four audio-video benchmarks and two Qwen2.5-Omni model scales, OmniScope achieved the best average accuracy across all compression settings. At 25% overall token retention, it delivered up to 3.53x prefill speedup and more than 15% GPU memory reduction, with only a 0.35-point drop in average accuracy.

The results suggest a simple design principle for OmniLLM inference: share the query across modalities, but not the salience estimates. The code is available on GitHub.

MetricValue
Token retention25%
Prefill speedupUp to 3.53x
GPU memory reduction>15%
Average accuracy drop0.35 points
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1