mlsanityData to 14 Oct 2026

CropVLM: Learning to Zoom for Fine-Grained Vision-Language Perception

arXiv 2511.19820 ↗First posted 25 Nov 2025cs.CV cs.AI cs.CLcited by 8

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

Vision-Language Models (VLMs) often struggle with tasks that require fine-grained image understanding, such as scene-text recognition or document analysis, due to perception limitations and visual fragmentation. To address these challenges, we introduce CropVLM as an external low-cost method for boosting performance, enabling VLMs to dynamically ''zoom in'' on relevant image regions, enhancing their ability to capture fine details. CropVLM is trained using reinforcement learning, without using human-labeled bounding boxes as a supervision signal, and without expensive synthetic evaluations. The model is trained once and can be paired with both open-source and proprietary VLMs to improve their performance. Our approach delivers significant improvements on tasks that require high-resolution image understanding, notably for benchmarks that are out-of-domain for the target VLM, without modifying or fine-tuning the VLM, thus avoiding catastrophic forgetting.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 29 of its 34 references that are in the map. First posted on arXiv 25 Nov 2025.

Builds on

29 of 34 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search9 Sep
  2. 2025Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization25 Apr
  3. 2025Semantic-Clipping: Efficient Vision-Language Modeling with Semantic-Guidedd Visual Selection14 Mar
  4. 2024Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning25 Mar
  5. 2022Flamingo: a Visual Language Model for Few-Shot Learning29 Apr

Other references · 24

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  5. 2023Visual Instruction Tuningcited by 7,869
  6. 2025Qwen2.5-VL Technical Reportcited by 5,587
  7. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
  8. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  9. 2019Towards VQA Models That Can Readcited by 1,718
  10. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  11. 2024Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMscited by 735
  12. 2025Visual-RFT: Visual Reinforcement Fine-Tuningcited by 513
12 more
  1. 2023V*: Guided Visual Search as a Core Mechanism in Multimodal LLMscited by 482
  2. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 476
  3. 2021InfographicVQAcited by 437
  4. 2019Scene Text Visual Question Answeringcited by 331
  5. 2025SmolVLM: Redefining small and efficient multimodal modelscited by 237
  6. 2025MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMscited by 176
  7. 2024Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Modelscited by 161
  8. 2024Matryoshka Multimodal Modelscited by 84
  9. 2024When Do We Not Need Larger Vision Models?cited by 67
  10. 2025VisRL: Intention-Driven Visual Perception via Reinforced Reasoningcited by 39
  11. 2024List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMscited by 32
  12. 2025Scaling Vision Pre-Training to 4K Resolutioncited by 28

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026Naive Visual Memory is Not Enough: A Failure-Mode Study of GUI Agentscited by 4
  2. 2026Foveated Reasoning: Stateful, Action-based Visual Focusing for Vision-Language Modelscited by 3
  3. 2026Look Again Before You Abstain:Budgeted Conformal Evidence Acquisition for Reliable Vision-Language Modelcited by 3
  4. 2026Look Where It Matters: Adaptive Visual Refinement for Vision-Language-Action Modelscited by 2
  5. 2026Beyond Zooming: Learning Multi-Tool Visual Reasoning for Ultra-High-Resolution Remote Sensingcited by 1
  6. 2026Learning to Look Again: Loss-Gap Supervision for Free-form Crop Routing in Vision-Language Modelscited by 1
  7. 2026AVA-VLM: Adaptive Visual Attention-Vision Language Model for In-the-Wild Construction Site Monitoringcited by 0
  8. 2026Q-CueGraph: Query-Conditioned Visual Evidence Graphs for Multimodal Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Cropper: Vision-Language Model for Image Cropping through In-Context Learning
  2. 2026Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
  3. 2026Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs
  4. 2025Zoomer: Adaptive Image Focus Optimization for Black-box MLLM
  5. 2025Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning
  6. 2023Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding
  7. 2024Improving Fine-grained Visual Understanding in VLMs through Text-Only Training
  8. 2025Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation