mlsanityData to 7 Oct 2026

LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

arXiv 2605.27365 ↗First posted 26 May 2026cs.CV cs.AI cs.LGcited by 20

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

Abstract (arXiv)

Vision-language models (VLMs) commonly formulate visual grounding and detection as a coordinate-token generation problem, serializing each 2D box into multiple 1D tokens that are learned and decoded largely independently. This token-by-token decoding mismatches the coupled structure of box geometry and creates a practical inference bottleneck due to strictly sequential generation. We introduce LocateAnything, a unified generative grounding and detection framework based on Parallel Box Decoding (PBD). By decoding geometric elements such as bounding boxes and points as atomic units in a single step, LocateAnything preserves intra-box geometric coherence and unlocks substantial parallelism. We show that PBD improves both decoding throughput and localization accuracy. We further develop a scalable data engine and curate LocateAnything-Data, a large-scale dataset with more than 138 million training samples, substantially increasing data diversity for high-precision localization. Extensive evaluations show that LocateAnything advances the speed-accuracy frontier, achieving significantly higher decoding throughput while improving high-IoU localization quality across diverse benchmarks. The results highlight the complementary benefits of Parallel Box Decoding and large-scale training data in enabling efficient and precise unified visual grounding and detection.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 185 of its 239 references that are in the map. First posted on arXiv 26 May 2026.

Builds on

185 of 239 references.

Closest ancestors · 17

Same direction, newest first

  1. 2025CoT4Det: A Chain-of-Thought Framework for Perception-Oriented Vision-Language Tasks7 Dec
  2. 2025Seed1.5-VL Technical Report11 May
  3. 2025Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models20 Jan
  4. 2024Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models25 Sep
  5. 2024Building and better understanding vision-language models: insights and future directions22 Aug
  6. 2024SPARK: Multi-Vision Sensor Perception and Reasoning Benchmark for Large-scale Vision-Language Models22 Aug
  7. 2024WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences16 Jun
  8. 2024What matters when building vision-language models?3 May
  9. 2024Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models19 Apr
  10. 2024Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models1 Mar
  11. 2024ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models18 Feb
  12. 2023LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models5 Dec
5 more
  1. 2023PixelLM: Pixel Reasoning with Large Multimodal Model4 Dec
  2. 2023Griffon: Spelling out All Object Locations at Any Granularity with Large Language Models24 Nov
  3. 2023Ferret: Refer and Ground Anything Anywhere at Any Granularity11 Oct
  4. 2023LISA: Reasoning Segmentation via Large Language Model1 Aug
  5. 2023Kosmos-2: Grounding Multimodal Large Language Models to the World26 Jun

Other references · 168

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2023Visual Instruction Tuningcited by 7,792
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2025Qwen2.5-VL Technical Reportcited by 5,418
  6. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  7. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  8. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  9. 2025Qwen3-VL Technical Reportcited by 2,534
  10. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  11. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  12. 2019Towards VQA Models That Can Readcited by 1,696
38 more
  1. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  2. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,449
  3. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  4. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,352
  5. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  6. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  7. 2016Modeling Context in Referring Expressionscited by 1,054
  8. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  9. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 891
  10. 2025Large Language Diffusion Modelscited by 872
  11. 2018VizWiz Grand Challenge: Answering Visual Questions from Blind Peoplecited by 852
  12. 2024Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Headscited by 821
  13. 2016A Diagram Is Worth A Dozen Imagescited by 793
  14. 2023MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Modelscited by 724
  15. 2022A-OKVQA: A Benchmark for Visual Question Answering using World Knowledgecited by 702
  16. 2024DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understandingcited by 559
  17. 2023DriveLM: Driving with Graph Visual Question Answeringcited by 527
  18. 2025Dream 7B: Diffusion Large Language Modelscited by 515
  19. 2020The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memescited by 485
  20. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 483
  21. 2020PathVQA: 30000+ Questions for Medical Visual Question Answeringcited by 467
  22. 2021InfographicVQAcited by 430
  23. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 404
  24. 2021OCR-free Document Understanding Transformercited by 400
  25. 2025Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Modelscited by 385
  26. 2021Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoningcited by 376
  27. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 351
  28. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 347
  29. 2019FUNSD: A Dataset for Form Understanding in Noisy Scanned Documentscited by 345
  30. 2021Pix2seq: A Language Modeling Framework for Object Detectioncited by 345
  31. 2024Better & Faster Large Language Models via Multi-token Predictioncited by 344
  32. 2018DVQA: Understanding Data Visualizations via Question Answeringcited by 338
  33. 2023PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answeringcited by 333
  34. 2019Scene Text Visual Question Answeringcited by 327
  35. 2019PlotQA: Reasoning over Scientific Plotscited by 317
  36. 2017FigureQA: An Annotated Figure Dataset for Visual Reasoningcited by 314
  37. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 313
  38. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 305

50 most cited of 168 All 168 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 20.

20 papers.

Sort:

By area:

  1. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 137
  2. 2026Vision as Unified Multimodal Generationcited by 5
  3. 2026SpatialCLI: Learning to Reason With Spatial Tools, Then Without Themcited by 1
  4. 2026HARMONY: Hierarchical Agentic Reasoning for MONocular Image-to-Scene Synthesiscited by 1
  5. 2026UniRef-UAV: A Multimodal Benchmark for Universal Referring in UAV Imagerycited by 0
  6. 2026Mixture-of-Thought-Tokens: Unifying Perception and Reasoning for Free-form Multimodal Groundingcited by 0
  7. 2026OVEarth-Bench: Evaluating Category Breadth and Query Diversity for Open-Vocabulary Earth Observationcited by 0
  8. 2026LocAnyMed: Vision-Language Grounding for Multimodal Medical Imagescited by 0
  9. 2026Falcon Perception-HD: High Density Perception via Reinforcement Learningcited by 0
  10. 2026PointRL: Learning Point-Level Vision-Language Grounding from Verifiable Annotation Evidencecited by 0
  11. 2026Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Groundingcited by 0
  12. 2026TempoGround: State-Aware Streaming Visual Grounding with Vision-Language Modelscited by 0
8 more
  1. 2026What Looks Like a Capability Limit in Vision-Language Models Is a Readout Limitcited by 0
  2. 2026A Unified Framework and Dataset for Oriented Object Visual Grounding in Remote Sensingcited by 0
  3. 2026HEIR: Learning Human-Entity Interactions with Functional Rolescited by 0
  4. 2026S4VY: Segment Anything in Feed-Forward 4D Visual Geometrycited by 0
  5. 2026PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligencecited by 0
  6. 2026EviRover: Reinforcing Agentic Perception Beyond a Glancecited by 0
  7. 2026AutoGUIWorld: Image Generators as Visual World Models for GUI Agentcited by 0
  8. 2026NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtimecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed
  2. 2025Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding
  3. 2024PD-APE: A Parallel Decoding Framework with Adaptive Position Encoding for 3D Visual Grounding
  4. 2026Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding
  5. 2026UniGround: Universal 3D Visual Grounding via Training-Free Scene Parsing
  6. 2026DeCo: Efficient Decouple-to-Couple Learning for Multi-Task Visual Grounding
  7. 2026IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning
  8. 2026Groundbench: Multi-Resolution Polygon Grounding Exposes the Geometry Gap in Vision-Language Models