mlsanityData to 14 Oct 2026

Toward Ambulatory Vision: Learning Visually-Grounded Active View Selection

arXiv 2512.13250 ↗First posted 15 Dec 2025cs.CVcited by 6

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

Abstract (arXiv)

Vision Language Models (VLMs) excel at visual question answering (VQA) but remain limited to snapshot vision, reasoning from static images. In contrast, embodied agents require ambulatory vision, actively moving to obtain more informative views. We introduce Visually Grounded Active View Selection (VG-AVS), a task that selects the most informative next viewpoint using only the visual information in the current image, without relying on scene memory or external knowledge. To support this task, we construct a synthetic dataset with automatically generated paired query-target views and question-answer prompts. We also propose a framework that fine-tunes pretrained VLMs through supervised fine-tuning (SFT) followed by RL-based policy optimization. Our approach achieves strong question answering performance based on viewpoint selection and generalizes robustly to unseen synthetic and real scenes. Furthermore, incorporating our learned VG-AVS framework into existing scene-exploration-based EQA systems improves downstream question-answering accuracy.

Key facts. Cited by 6 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 40 of its 53 references that are in the map. First posted on arXiv 15 Dec 2025.

Builds on

40 of 53 references.

References · 40

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2025Qwen2.5-VL Technical Reportcited by 5,587
  4. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  5. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  6. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  7. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  8. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  9. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  10. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  11. 2025Group Sequence Policy Optimizationcited by 835
  12. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 706
28 more
  1. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 592
  2. 2025VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Modelcited by 526
  3. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 380
  4. 2024Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Modelscited by 339
  5. 2017Embodied Question Answeringcited by 336
  6. 2025Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learningcited by 278
  7. 2024LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awarenesscited by 183
  8. 2024Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learningcited by 158
  9. 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planningcited by 156
  10. 2025Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawingcited by 136
  11. 2024SAT: Dynamic Spatial Aptitude Training for Multimodal Language Modelscited by 114
  12. 2025What Can RL Bring to VLA Generalization? An Empirical Studycited by 108
  13. 20243D-Mem: 3D Scene Memory for Embodied Exploration and Reasoningcited by 75
  14. 2024Explore until Confident: Efficient Exploration for Embodied Question Answeringcited by 74
  15. 20253D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformercited by 68
  16. 2025SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoningcited by 68
  17. 2023SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulationcited by 66
  18. 2025Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenescited by 63
  19. 2025MindJourney: Test-Time Scaling with World Models for Spatial Reasoningcited by 50
  20. 2023Posterior Distillation Samplingcited by 46
  21. 2025SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Modelscited by 38
  22. 2024GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answeringcited by 37
  23. 2025Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answeringcited by 30
  24. 2024SyncTweedies: A General Generative Framework Based on Synchronized Diffusionscited by 26
  25. 2025Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Roboticscited by 21
  26. 2025VideoHandles: Editing 3D Object Compositions in Videos Using Video Generative Priorscited by 14
  27. 2024Right this way: Can VLMs Guide Us to See More to Answer Questions?cited by 10
  28. 2024Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Posescited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026LIME: Learning Intent-aware Camera Motion from Egocentric Videocited by 2
  2. 2026Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?cited by 1
  3. 2026PInVerify: An Offline Embodied Benchmark for Active Instance Verificationcited by 0
  4. 2026INSPECT: Learning Robot View Selection from Assistant Usecited by 0
  5. 2026Rendering-Free Lookahead for Question-Guided Active Visioncited by 0
  6. 2026SpatialASM: Internalizing Active Mentalization for Spatial Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types
  2. 2023From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities
  3. 2026Self-Evolving Visual Questioner
  4. 2025AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition
  5. 2025VoQA: Visual-only Question Answering
  6. 2025Elevating Visual Question Answering through Implicitly Learned Reasoning Pathways in LVLMs
  7. 2022A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge
  8. 2025The Quest for Visual Understanding: A Journey Through the Evolution of Visual Question Answering