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

AutoPrune: LLM-Designed Visual Token Pruning Cuts 94.4% Tokens with 99% Performance

AI By Crimson AI Hugging Face Papers 15 August 2026 · 00:00 12 views
Share: X Telegram

Hugging Face researchers introduce AutoPrune, a training-free framework that uses large language models to automatically design visual-token pruning policies for multimodal LLMs, achieving 9.9x FLOPs reduction and 6.4x prefill latency speedup with minimal performance loss.

AutoPrune: LLM-Designed Visual Token Pruning Cuts 94.4% Tokens with 99% Performance

Key points

Visual-token pruning is a key technique for reducing the inference cost of multimodal large language models (MLLMs), but existing methods rely on fixed, handcrafted heuristics and costly expert trial and error. As models and objectives diversify, manually exploring the design space becomes increasingly difficult.

In a new paper, researchers from Hugging Face propose AutoPrune, a training-free framework that leverages large language models (LLMs) to automatically design effective visual-token pruning policies. The core innovation is a Token Pruning Domain-Specific Language (TPDSL) with 131 reusable atoms for budget control, token scoring, selection constraints, and token reassembly.

A key property of TPDSL is its residual formulation: each search state is represented as a modification of a strong base policy. This narrows the search space and focuses the LLM's attention on the most consequential policy components, making the search more efficient and effective.

Experiments on 14 multimodal benchmarks and three MLLM backbones demonstrate AutoPrune's effectiveness, efficiency, and transferability. Notably, even when removing 94.4% of visual tokens, AutoPrune preserves more than 99% of full-token performance while reducing FLOPs by 9.9x and prefill latency by 6.4x.

The paper is available on Hugging Face and was highlighted by the Librarian Bot, which also recommended related works such as TOPS, DIVE, and AnchorPrune.

MetricValue
Visual tokens removed94.4%
Performance preserved>99%
FLOPs reduction9.9x
Prefill latency speedup6.4x
Benchmarks tested14
MLLM backbones3
TPDSL atoms131
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 29 Aug 2026

Hugging Face Audit: 110 of 124 AI Evaluations Fail to Support Their Claims

A new commit-bound census of 124 Inspect Evals units reveals that 110 stop before deterministic inference due to missing historica...

4
Research paper
Hugging Face 29 Aug 2026

Aphanta: New Framework Diagnoses When Image Editing Boosts Multimodal Reasoning

Hugging Face researchers introduce Aphanta, a diagnostic framework that evaluates when image-editing intermediates improve multimo...

5
Research paper
Hugging Face 29 Aug 2026

EditaLive! Enables Real-Time Character Video Editing for Live Streaming

Hugging Face researchers introduce EditaLive, a framework for real-time human-centric video editing in live streams, achieving sta...

4