mlsanityData to 14 Oct 2026

The Role of Entropy in Visual Grounding: Analysis and Optimization

arXiv 2512.06726 ↗First posted 7 Dec 2025cs.CV cs.AI cs.CLcited by 1

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

Recent advances in fine-tuning multimodal large language models (MLLMs) using reinforcement learning have achieved remarkable progress, particularly with the introduction of various entropy control techniques. However, the role and characteristics of entropy in perception-oriented tasks like visual grounding, as well as effective strategies for controlling it, remain largely unexplored. To address this issue, we focus on the visual grounding task and analyze the role and characteristics of entropy in comparison to reasoning tasks. Building on these findings, we introduce ECVGPO (Entropy Control Visual Grounding Policy Optimization), an interpretable algorithm designed for effective entropy regulation. Through entropy control, the trade-off between exploration and exploitation is better balanced. Experiments show that ECVGPO achieves broad improvements across various benchmarks and models.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 32 of its 43 references that are in the map. First posted on arXiv 7 Dec 2025.

Builds on

32 of 43 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model10 Apr
  2. 2025LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL10 Mar

Other references · 30

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2023Visual Instruction Tuningcited by 7,869
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  5. 2025Qwen2.5-VL Technical Reportcited by 5,587
  6. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  7. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  8. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  9. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  10. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  11. 2015VQA: Visual Question Answeringcited by 2,506
  12. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
18 more
  1. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  2. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,050
  3. 2025Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoningcited by 559
  4. 2025Visual-RFT: Visual Reinforcement Fine-Tuningcited by 513
  5. 2025The Entropy Mechanism of Reinforcement Learning for Reasoning Language Modelscited by 485
  6. 2016Visual Dialogcited by 377
  7. 2024InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Modelcited by 326
  8. 2023InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Compositioncited by 297
  9. 2025Reasoning with Exploration: An Entropy Perspectivecited by 281
  10. 2025GRIT: Teaching MLLMs to Think with Imagescited by 125
  11. 2025UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learningcited by 84
  12. 2025Grounded Reinforcement Learning for Visual Reasoningcited by 83
  13. 2024Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Modelscited by 53
  14. 2025EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversitycited by 41
  15. 2025NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoningcited by 38
  16. 2024MouSi: Poly-Visual-Expert Vision-Language Modelscited by 24
  17. 2025CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learningcited by 23
  18. 2022Do You Need the Entropy Reward (in Practice)?cited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selectioncited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Entropy-Preserving Reinforcement Learning
  2. 2026On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models
  3. 2025KARL: Knowledge-Aware Reasoning and Reinforcement Learning for Knowledge-Intensive Visual Grounding
  4. 2024Visual Grounding for Object-Level Generalization in Reinforcement Learning
  5. 2025Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective
  6. 2025GuirlVG: Incentivize GUI Visual Grounding via Empirical Exploration on Reinforcement Learning
  7. 2025High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
  8. 2025More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models