GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed

arXiv:2609.39600 · cs.CV, cs.AI, cs.LG, cs.RO · Submitted 2026-09-30 · Read on arXiv

cs.CV, cs.AI, cs.LG, cs.RO

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/groundingpi/GroundAnything

Project page: https://groundingpi.github.io/groundanything

Terminology

• Grounding — 165× in this paper · explained in 3 episodes
• Accuracy — 31× in this paper · explained in 1 episode
• Verification — 30× in this paper · explained in 2 episodes
• Alignment — 24× in this paper · explained in 1 episode
• Ablation — 19× in this paper · explained in 1 episode
• Benchmark — 17× in this paper · explained in 2 episodes
• GRPO — 14× in this paper · explained in 6 episodes
• Verifier — 14× in this paper · explained in 2 episodes
• Speculative Decoding — 13× in this paper · explained in 2 episodes
• Visual Grounding — 12× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 7× in this paper
• Consistency — 7× in this paper · explained in 3 episodes
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• Reinforcement Learning — 7× in this paper · explained in 4 episodes
• Aggregation — 6× in this paper · explained in 1 episode
• Decode — 5× in this paper · explained in 2 episodes
• Foundation Model — 5× in this paper · explained in 3 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• Embeddings — 4× in this paper · explained in 2 episodes
• Generative AI — 4× in this paper · explained in 2 episodes
• Reinforcement Learning (RL) — 4× in this paper · explained in 25 episodes
• Affordance — 3× in this paper · explained in 1 episode
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Diffusion Models — 3× in this paper · explained in 6 episodes
• International Conference on Document Analysis and Recognition — 3× in this paper
• Ablation Studies — 2× in this paper · explained in 1 episode
• Quantization — 2× in this paper · explained in 12 episodes
• Activation Checkpointing — 1× in this paper · explained in 1 episode
• Block Diffusion — 1× in this paper · explained in 2 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Instance Segmentation — 1× in this paper · explained in 3 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Multimodal Inputs — 1× in this paper · explained in 2 episodes
• Pseudo-labels — 1× in this paper · explained in 2 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Tokenization — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• Pix2seq: A Language Modeling Framework for Object Detection
• M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• PaddleOCR 3.0 Technical Report
• RynnBrain: Open Embodied Foundation Models
• Emerging Properties in Unified Multimodal Pretraining
• Seed1.5-VL Technical Report
• Vision as Unified Multimodal Generation
• Towards GUI Agents: Vision-Language Diffusion Models for GUI Grounding
• RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model
• Kosmos-2: Grounding Multimodal Large Language Models to the World
• LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Kimi K3: Open Frontier Intelligence
• Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM
• DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
• Qwen3 Technical Report

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models