# Local Information Matters: Inference Acceleration For Grounded Conversation Generation Models Through Adaptive Local-Aware Token Pruning

arXiv: https://arxiv.org/abs/2503.23959 · HTML: https://mlsanity.com/paper/2503.23959/

## Key facts

- Cited by 2 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 21 of its 25 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## 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, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models](https://mlsanity.com/paper/2403.06764/) (2024)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models](https://mlsanity.com/paper/2403.15388/) (2024)
- [SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference](https://mlsanity.com/paper/2410.04417/) (2024)
- [GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest](https://mlsanity.com/paper/2307.03601/) (2023)
- [PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction](https://mlsanity.com/paper/2410.17247/) (2024)
- [BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs](https://mlsanity.com/paper/2307.08581/) (2023)
- [Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention](https://mlsanity.com/paper/2304.04237/) (2023)
- [FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression](https://mlsanity.com/paper/2411.14228/) (2024)

## Built on by (most cited first, 2 of 2)

- [Dynamic Resolution Routing for Efficient Egocentric Grounding](https://mlsanity.com/paper/2608.01638/) (2026)
- [Efficient GUI Agents: A Systems Survey of Observation, Memory, Action, and Runtime Optimization](https://mlsanity.com/paper/2609.02309/) (2026)

## Abstract (arXiv)

Grounded Conversation Generation (GCG) is an emerging vision-language task that requires models to generate natural language responses seamlessly intertwined with corresponding object segmentation masks. Recent models, such as GLaMM and OMG-LLaVA, achieve pixel-level grounding but incur significant computational costs due to processing a large number of visual tokens. Existing token pruning methods, like FastV and PyramidDrop, fail to preserve the local visual features critical for accurate grounding, leading to substantial performance drops in GCG tasks. To address this, we propose Adaptive Local-Aware Token Pruning (ALTP), a simple yet effective framework that accelerates GCG models by prioritizing local object information. ALTP introduces two key components: (1) Detail Density Capture (DDC), which uses superpixel segmentation to retain tokens in object-centric regions, preserving fine-grained details, and (2) Dynamic Density Formation (DDF), which dynamically allocates tokens based on information density, ensuring higher retention in semantically rich areas. Extensive experiments on the GranDf dataset demonstrate that ALTP significantly outperforms existing token pruning methods, such as FastV and PyramidDrop, on both GLaMM and OMG-LLaVA models. Notably, when applied to GLaMM, ALTP achieves a 90% reduction in visual tokens with a 4.9% improvement in AP50 and a 5.0% improvement in Recall compared to PyramidDrop. Similarly, on OMG-LLaVA, ALTP improves AP by 2.1% and mIOU by 3.0% at a 90% token reduction compared with PDrop.