# Audio-Visual Exchange-Aware Token Pruning for Efficient Audio-Visual Captioning

arXiv: https://arxiv.org/abs/2606.10533 · HTML: https://mlsanity.com/paper/2606.10533/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Visual token pruning in multimodal models, one of 12 directions in Efficient LLM inference and serving.
- Builds on 46 of its 75 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Placed in

- Efficient LLM inference and serving / [Visual token pruning in multimodal models](https://mlsanity.com/inference/visual-token-pruning-in-multimodal-models/)

## Builds on (most cited first, 30 of 46)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration](https://mlsanity.com/paper/2311.04257/) (2023)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)
- [SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference](https://mlsanity.com/paper/2410.04417/) (2024)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [PandaGPT: One Model To Instruction-Follow Them All](https://mlsanity.com/paper/2305.16355/) (2023)
- [Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning](https://mlsanity.com/paper/2302.14115/) (2023)
- [Valley: Video Assistant with Large Language model Enhanced abilitY](https://mlsanity.com/paper/2306.07207/) (2023)
- [OneLLM: One Framework to Align All Modalities with Language](https://mlsanity.com/paper/2312.03700/) (2023)
- [Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration](https://mlsanity.com/paper/2306.09093/) (2023)
- [TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?](https://mlsanity.com/paper/2106.11297/) (2021)
- [UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer](https://mlsanity.com/paper/2211.09552/) (2022)
- [Audio-Visual LLM for Video Understanding](https://mlsanity.com/paper/2312.06720/) (2023)
- [PruneVid: Visual Token Pruning for Efficient Video Large Language Models](https://mlsanity.com/paper/2412.16117/) (2024)

## Built on by (most cited first, 3 of 3)

- [EmoStyle: Affective Conditioning of Style-Specialist Experts for Emotional Image Generation](https://mlsanity.com/paper/2607.10165/) (2026)
- [Geometry-aware Gaussian Prior and Axial Attention for Cervical Cytology Image Classification](https://mlsanity.com/paper/2607.10278/) (2026)
- [FoveaTree: Information-Density Trees for Query-Guided Visual Token Pruning in Video Large Language Models](https://mlsanity.com/paper/2610.16744/) (2026)

## Abstract (arXiv)

Audio-visual captioning generates natural language descriptions from video and audio content. Multimodal LLMs have advanced this task, but both modalities contribute many tokens to the LLM input, where prefill self-attention scales quadratically. Existing token-pruning methods usually retain tokens by attention, saliency, or cross-entropy loss, yet the hard threshold selection makes it difficult to retain tokens that are truly valuable, especially for high-confusing tokens near the decision boundary. To this end, we propose a AVEX-Prune, an RL-based audio-visual dynamic token pruning method in this work. In our AVEX-Prune, an audio-visual token exchange strategy is proposed to select truly valuable tokens by replacing low-confidence retained tokens with high-confidence candidate tokens from the same or the other modality, and measuring the differences in caption generation from token swaps. AVEX-Prune preserves full-token quality at a 40% retention ratio on both VILA 1.5-8B (54.5 vs. 54.6) and VideoLLaMA 2 (57.0 vs. 56.8).