Visual Grounding papers, 2023–2026

Key findings

• Visual Grounding went from 23 papers in 2023 to 100 in 2026, roughly 4.3x in three years.
• CVPR publishes the most Visual Grounding work: 108 papers from 2023 to 2026, 52% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 2 in 2023 to 56 in 2026.
• Among the 5 topics under Open-Vocabulary Vision, it ranks #3 by 2026 paper count; the fastest grower in the group, Open-Vocabulary Detection, is up 1.5x versus 4.3x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026From Squeezing to Grounding: Visual Guided DPO for Multimodal Hallucination Mitigation
• ICML 2026PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs
• ICLR 2026How Do Medical MLLMs Fail? A Study on Visual Grounding in Medical Images
• CVPR 2026EG-3DVG Expression and Geometry Aware Grounding Decoder for 3D Visual
• NeurIPS 2025From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes
• ICML 2025Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities
• ICLR 2025DenseGrounding: Improving Dense Language-Vision Semantics for Ego-centric 3D Visual Grounding
• CVPR 2025Discovering Hidden Visual Concepts Beyond Linguistic Input in Infant Learning
• NeurIPS 2024IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos
• ICLR 2024CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding
• CVPR 2024EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning
• NeurIPS 2023Grounding Neural Inference with Satisfiability Modulo Theories
• ICML 2023Rethinking Visual Reconstruction: Experience-Based Content Completion Guided by Visual Cues
• ICLR 2023Learning to reason over visual objects
• CVPR 2023Advancing Visual Grounding With Scene Knowledge: Benchmark and Method
• NeurIPS 2026Not All Instances Should Contribute Equally: Sparse Support Grounding via Unbalanced Transport for Heterogeneous MIL
• ICML 2026Grounding Functional Similarity by Invariance-Aware Model Stitching
• ICLR 2026CloDS: Visual-Only Unsupervised Cloth Dynamics Learning in Unknown Conditions
• CVPR 2026Enhancing Part-Level Point Grounding for Any Open-Source MLLMs
• NeurIPS 2025On the rankability of visual embeddings

All Visual Grounding papers

209 papers, page 2 of 5

51. ICLR 2026PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs
52. ICLR 2026RAR: Reversing Visual Attention Re-Sinking for Unlocking Potential in Multimodal Large Language Models
53. ICLR 2026Reasoning in Space via Grounding in the World
54. ICML 2026AmbiRefer3D: 3D Visual Grounding with Referential Ambiguity
55. ICML 2026CACR: Reinforcing Temporal Answer Grounding in Instructional Video via Candidate-Aware Causal Reasoning
56. ICML 2026CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large Vision-Language Models
57. ICML 2026Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding
58. ICML 2026DSGCR: Decomposed Spectral Geometry-Aware Cross-Modal Semantic Representation for 3D Visual Grounding
59. ICML 2026Efficient Skill Grounding via Code Refactoring with Small Language Models
60. ICML 2026Grounding Functional Similarity by Invariance-Aware Model Stitching
61. ICML 2026GUI-Spotlight: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding
62. ICML 2026Learning Attribute–Affordance Hierarchies in Hyperbolic Space for Open-Vocabulary 3D Object Affordance Grounding
63. ICML 2026Learning Sparse Visual Representations via Spatial-Semantic Factorization
64. ICML 2026MedSIGHT: Towards Grounded Visual Comprehension in Medical Large Vision-Language Models
65. ICML 2026PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs
66. ICML 2026Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance
67. ICML 2026Unveiling the Visual Counting Bottleneck in Vision-Language Models
68. NeurIPS 2026Attention Heads are Complementary Visual Units: Mitigating Hallucinations in LVLMs via Adaptive Visual Cues Focusing
69. NeurIPS 2026BoxTuning: Object-Aware Visual Prompting for Multimodal Model Fine-Tuning
70. NeurIPS 2026Causal-Geo: Neuro-Symbolic Spatial Grounding for Situated Agent Planning
71. NeurIPS 2026DRAGON : A Benchmark for Evidence-Grounded Visual Reasoning over Diagrams
72. NeurIPS 2026Echo-SAM: Zero-Shot Learning of Unseen Structures via Medical Knowledge Graph Grounding
73. NeurIPS 2026Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models
74. NeurIPS 2026From Squeezing to Grounding: Visual Guided DPO for Multimodal Hallucination Mitigation
75. NeurIPS 2026GEAR-Align: Grounding-Evidence-Aware Gradient Routing for Multimodal Alignment
76. NeurIPS 2026Grounding Multimodal Reasoning with Evidence-Ablated Negatives
77. NeurIPS 2026Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding Fails
78. NeurIPS 2026IntentLens: Grounding Underspecified Multimodal Queries for Recommendation via Tool-Augmented Reasoning
79. NeurIPS 2026MammoGPS: A Benchmark for Visual Grounding, Perception, and Spatial Reasoning in Mammography
80. NeurIPS 2026MedVIGOR: Visual Evidence Internalization for Observation-Driven Reasoning in Medical VLMs
81. NeurIPS 2026MoT3DVG: A Benchmark for Outdoor 3D Visual Grounding with Motion-Aware Descriptions and Temporal Cues
82. NeurIPS 2026Not All Instances Should Contribute Equally: Sparse Support Grounding via Unbalanced Transport for Heterogeneous MIL
83. NeurIPS 2026PixFoundation 2.0: Do Video Multi-Modal LLMs Use Motion in Visual Grounding?
84. NeurIPS 2026RECIPE: Procedural Planning via Grounding in Instructional Video
85. NeurIPS 2026See to Believe: Segmentation by Reasoning with Visual Evidence
86. NeurIPS 2026Self-Rewarded Multimodal Coherent Reasoning Across Diverse Visual Domains
87. NeurIPS 2026SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring
88. NeurIPS 2026SLVR: Structured Latent Visual Reasoning via Human-like Reasoning Flows
89. NeurIPS 2026SpaG-DiT: Enhancing Spatial Grounding for Diffusion Transformers
90. NeurIPS 2026Thinking with Visual Primitives
91. NeurIPS 2026TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval
92. NeurIPS 2026UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Affordance Segmentation
93. NeurIPS 2026VC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning
94. NeurIPS 2026VIGOR: Benchmarking Visual Rationale Correctness in Multimodal Large Language Models
95. NeurIPS 2026Vision-Language Grounding as Bidirectional Concept Correspondence
96. NeurIPS 2026Visual Enhanced Depth Scaling for Multimodal Latent Reasoning
97. NeurIPS 2026Visual Grounding First, Multimodal In-context Learning Follows
98. NeurIPS 2026Visual Harness: Grounding Multimodal Reasoning in Physics Engines
99. NeurIPS 2026Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Models
100. NeurIPS 2026What Sketches Tell Us about LVLMs: Conventions, Grounding, and Localisation

FAQ

How many Visual Grounding papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

209 in total: 23 in 2023, 42 in 2024, 44 in 2025, 100 in 2026.

How many Visual Grounding papers are at NeurIPS 2026?

NeurIPS 2026 has 33 Visual Grounding papers, versus 13 the year before.

How many Visual Grounding papers are at ICLR 2026?

ICLR 2026 has 9 Visual Grounding papers, versus 9 the year before.

How many Visual Grounding papers are at ICML 2026?

ICML 2026 has 14 Visual Grounding papers, versus 3 the year before.

How many Visual Grounding papers are at CVPR 2026?

CVPR 2026 has 44 Visual Grounding papers, versus 19 the year before.

Which conference publishes the most Visual Grounding papers?

CVPR, with 108 papers from 2023 to 2026.