# AVA-VLM: Adaptive Visual Attention-Vision Language Model for In-the-Wild Construction Site Monitoring

arXiv: https://arxiv.org/abs/2607.05859 · HTML: https://mlsanity.com/paper/2607.05859/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 30 of its 46 references that are in the map.
- First posted on arXiv 7 Jul 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Chart understanding and anomaly detection](https://mlsanity.com/mllm/chart-understanding-and-anomaly-detection/)

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (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)
- [MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning](https://mlsanity.com/paper/2310.09478/) (2023)
- [LLaVA-CoT: Let Vision Language Models Reason Step-by-Step](https://mlsanity.com/paper/2411.10440/) (2024)
- [VisionZip: Longer is Better but Not Necessary in Vision Language Models](https://mlsanity.com/paper/2412.04467/) (2024)
- [PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction](https://mlsanity.com/paper/2410.17247/) (2024)
- [MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning](https://mlsanity.com/paper/2309.07915/) (2023)
- [UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers](https://mlsanity.com/paper/2301.13741/) (2023)
- [VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning](https://mlsanity.com/paper/2507.13348/) (2025)
- [Chain of Thought Prompt Tuning in Vision Language Models](https://mlsanity.com/paper/2304.07919/) (2023)
- [Vision-Language Models for Edge Networks: A Comprehensive Survey](https://mlsanity.com/paper/2502.07855/) (2025)
- [AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition](https://mlsanity.com/paper/2512.03794/) (2025)
- [VRU-Accident: A Vision-Language Benchmark for Video Question Answering and Dense Captioning for Accident Scene Understanding](https://mlsanity.com/paper/2507.09815/) (2025)
- [Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers](https://mlsanity.com/paper/2410.14072/) (2024)
- [Privacy-Aware Visual Language Models](https://mlsanity.com/paper/2405.17423/) (2024)
- [Res-Bench: Benchmarking the Robustness of Multimodal Large Language Models to Dynamic Resolution Input](https://mlsanity.com/paper/2510.16926/) (2025)
- [CropVLM: Learning to Zoom for Fine-Grained Vision-Language Perception](https://mlsanity.com/paper/2511.19820/) (2025)
- [Edge Video Analytics: A Survey on Applications, Systems and Enabling Techniques](https://mlsanity.com/paper/2211.15751/) (2022)
- [SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions](https://mlsanity.com/paper/2501.19377/) (2025)
- [Are Large Pre-trained Vision Language Models Effective Construction Safety Inspectors?](https://mlsanity.com/paper/2508.11011/) (2025)
- [Safe-LLaVA: A Privacy-Preserving Vision-Language Dataset and Benchmark for Biometric Safety](https://mlsanity.com/paper/2509.00192/) (2025)
- [2COOOL: 2nd Workshop on the Challenge Of Out-Of-Label Hazards in Autonomous Driving](https://mlsanity.com/paper/2508.21080/) (2025)

## Abstract (arXiv)

Existing construction-site Vision-Language Model (VLM) studies have primarily adapted pretrained VLMs through direct QA-style fine-tuning from a single global image, but we argue that this paradigm remains limited in operational range, reliability under reduced-resolution inputs, and inference efficiency. To address these limitations, we propose AVA-VLM, an Adaptive Visual Attention-Vision Language Model that follows a human-inspired coarse-to-fine strategy: it first reasons over a low-resolution global image and requests a high-resolution local crop only when detailed inspection is needed. We further introduce a region-aware Chain-of-Thought dataset that teaches when to inspect, where to crop, and how to use local evidence. Experiments show that, for violation identification, AVA-VLM improves overall F1 from 62.0 to 75.1 while using only 30.6% of the baseline visual-token budget; for long-distance PPE-violation cases, F1 improves from 16.0 to 63.6. These results demonstrate AVA-VLM's improved robustness to distant and reduced-resolution visual evidence with substantially lower visual-token usage.