视觉定位论文趋势 2023–2026

短语定位

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 209 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

视觉定位论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20234111723
202410402842
202513931944
20263391444100

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部视觉定位论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 100 篇，第 2 / 2 页

  1. ICLR 2026PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs
  2. ICLR 2026RAR: Reversing Visual Attention Re-Sinking for Unlocking Potential in Multimodal Large Language Models
  3. ICLR 2026Reasoning in Space via Grounding in the World
  4. ICML 2026AmbiRefer3D: 3D Visual Grounding with Referential Ambiguity
  5. ICML 2026CACR: Reinforcing Temporal Answer Grounding in Instructional Video via Candidate-Aware Causal Reasoning
  6. ICML 2026CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large Vision-Language Models
  7. ICML 2026Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding
  8. ICML 2026DSGCR: Decomposed Spectral Geometry-Aware Cross-Modal Semantic Representation for 3D Visual Grounding
  9. ICML 2026Efficient Skill Grounding via Code Refactoring with Small Language Models
  10. ICML 2026Grounding Functional Similarity by Invariance-Aware Model Stitching
  11. ICML 2026GUI-Spotlight: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding
  12. ICML 2026Learning Attribute–Affordance Hierarchies in Hyperbolic Space for Open-Vocabulary 3D Object Affordance Grounding
  13. ICML 2026Learning Sparse Visual Representations via Spatial-Semantic Factorization
  14. ICML 2026MedSIGHT: Towards Grounded Visual Comprehension in Medical Large Vision-Language Models
  15. ICML 2026PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs
  16. ICML 2026Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance
  17. ICML 2026Unveiling the Visual Counting Bottleneck in Vision-Language Models
  18. NeurIPS 2026Attention Heads are Complementary Visual Units: Mitigating Hallucinations in LVLMs via Adaptive Visual Cues Focusing
  19. NeurIPS 2026BoxTuning: Object-Aware Visual Prompting for Multimodal Model Fine-Tuning
  20. NeurIPS 2026Causal-Geo: Neuro-Symbolic Spatial Grounding for Situated Agent Planning
  21. NeurIPS 2026DRAGON : A Benchmark for Evidence-Grounded Visual Reasoning over Diagrams
  22. NeurIPS 2026Echo-SAM: Zero-Shot Learning of Unseen Structures via Medical Knowledge Graph Grounding
  23. NeurIPS 2026Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models
  24. NeurIPS 2026From Squeezing to Grounding: Visual Guided DPO for Multimodal Hallucination Mitigation
  25. NeurIPS 2026GEAR-Align: Grounding-Evidence-Aware Gradient Routing for Multimodal Alignment
  26. NeurIPS 2026Grounding Multimodal Reasoning with Evidence-Ablated Negatives
  27. NeurIPS 2026Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding Fails
  28. NeurIPS 2026IntentLens: Grounding Underspecified Multimodal Queries for Recommendation via Tool-Augmented Reasoning
  29. NeurIPS 2026MammoGPS: A Benchmark for Visual Grounding, Perception, and Spatial Reasoning in Mammography
  30. NeurIPS 2026MedVIGOR: Visual Evidence Internalization for Observation-Driven Reasoning in Medical VLMs
  31. NeurIPS 2026MoT3DVG: A Benchmark for Outdoor 3D Visual Grounding with Motion-Aware Descriptions and Temporal Cues
  32. NeurIPS 2026Not All Instances Should Contribute Equally: Sparse Support Grounding via Unbalanced Transport for Heterogeneous MIL
  33. NeurIPS 2026PixFoundation 2.0: Do Video Multi-Modal LLMs Use Motion in Visual Grounding?
  34. NeurIPS 2026RECIPE: Procedural Planning via Grounding in Instructional Video
  35. NeurIPS 2026See to Believe: Segmentation by Reasoning with Visual Evidence
  36. NeurIPS 2026Self-Rewarded Multimodal Coherent Reasoning Across Diverse Visual Domains
  37. NeurIPS 2026SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring
  38. NeurIPS 2026SLVR: Structured Latent Visual Reasoning via Human-like Reasoning Flows
  39. NeurIPS 2026SpaG-DiT: Enhancing Spatial Grounding for Diffusion Transformers
  40. NeurIPS 2026Thinking with Visual Primitives
  41. NeurIPS 2026TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval
  42. NeurIPS 2026UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Affordance Segmentation
  43. NeurIPS 2026VC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning
  44. NeurIPS 2026VIGOR: Benchmarking Visual Rationale Correctness in Multimodal Large Language Models
  45. NeurIPS 2026Vision-Language Grounding as Bidirectional Concept Correspondence
  46. NeurIPS 2026Visual Enhanced Depth Scaling for Multimodal Latent Reasoning
  47. NeurIPS 2026Visual Grounding First, Multimodal In-context Learning Follows
  48. NeurIPS 2026Visual Harness: Grounding Multimodal Reasoning in Physics Engines
  49. NeurIPS 2026Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Models
  50. NeurIPS 2026What Sketches Tell Us about LVLMs: Conventions, Grounding, and Localisation

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查视觉定位在 CVPR 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "grounding"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇视觉定位论文？
共 209 篇，按年份分别是 2023 年 23 篇、2024 年 42 篇、2025 年 44 篇、2026 年 100 篇。
NeurIPS 2026 有多少篇视觉定位论文？
NeurIPS 2026 有 33 篇视觉定位论文，上一届是 13 篇。
ICLR 2026 有多少篇视觉定位论文？
ICLR 2026 有 9 篇视觉定位论文，上一届是 9 篇。
ICML 2026 有多少篇视觉定位论文？
ICML 2026 有 14 篇视觉定位论文，上一届是 3 篇。
CVPR 2026 有多少篇视觉定位论文？
CVPR 2026 有 44 篇视觉定位论文，上一届是 19 篇。
哪个会议的视觉定位论文最多？
CVPR，2023–2026 年共 108 篇。

「开放词汇视觉」下的其他主题