Open-Vocabulary Detection papers, 2023–2026

Key findings

• Open-Vocabulary Detection went from 111 papers in 2023 to 168 in 2026, roughly 1.5x in three years.
• CVPR publishes the most Open-Vocabulary Detection work: 294 papers from 2023 to 2026, 51% of the four-venue total.
• The fastest-growing overlap is with Open-Domain QA: papers tagged with both rose from 8 in 2023 to 22 in 2026.
• Among the 5 topics under Open-Vocabulary Vision, it ranks #2 by 2026 paper count; the fastest grower in the group, Visual Grounding, is up 4.3x versus 1.5x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026At FullTilt: Real-Time Open-Set 3D Macromolecule Detection Directly from Tilted 2D Projections
• ICML 2026An In-Depth Study on Deep Learning Model Cloning
• ICLR 2026DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection
• CVPR 2026ANTS Adaptive Negative Textual Space Shaping for OOD Detection via
• NeurIPS 2025Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning
• ICML 2025Position: We Can’t Understand AI Using our Existing Vocabulary
• ICLR 20253D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds
• CVPR 2025Anomize: Better Open Vocabulary Video Anomaly Detection
• NeurIPS 2024DreamCatcher: A Wearer-aware Multi-modal Sleep Event Dataset Based on Earables in Non-restrictive Environments
• ICML 2024Binary Decomposition: A Problem Transformation Perspective for Open-Set Semi-Supervised Learning
• ICLR 2024FROSTER: Frozen CLIP is A Strong Teacher for Open-Vocabulary Action Recognition
• CVPR 2024DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection
• NeurIPS 2023AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation
• ICML 2023Internet Explorer: Targeted Representation Learning on the Open Web
• ICLR 2023Adaptive Robust Evidential Optimization For Open Set Detection from Imbalanced Data
• CVPR 2023Being Comes From Not-Being: Open-Vocabulary Text-to-Motion Generation With Wordless Training
• NeurIPS 2026CompleteRXN: Toward Completing Open Chemical Reaction Databases
• ICML 2026Learning Attribute–Affordance Hierarchies in Hyperbolic Space for Open-Vocabulary 3D Object Affordance Grounding
• ICLR 2026DETR-ViP: Detection Transformer with Robust Discriminative Visual Prompts
• CVPR 2026Bypassing the Transport Plan Dynamic Reweighting for Out-of-Distribution Detection with

All Open-Vocabulary Detection papers

168 papers, page 4 of 4

151. NeurIPS 2026RelGS: Relation-Aware Gaussian Splatting for Open-Vocabulary 3D Scene Understanding
152. NeurIPS 2026Rethinking Geometric Depth in Monocular 3D Object Detection: A Projection-Consistent Reformulation
153. NeurIPS 2026Rethinking Infrared Small Target Detection: A Foundation Driven Efficient Paradigm
154. NeurIPS 2026RETR: A Structure-Preserving RGB-Event Transformer for Robust 3D Lane Detection
155. NeurIPS 2026ROAD: Rule-Grounded Context-Aware Open-World Driver Anomaly Detection
156. NeurIPS 2026Scalable Token-Level Hallucination Detection in Large Language Models
157. NeurIPS 2026Stability-Weighted Direction Regularization Disentangles Generator Shortcuts from Detection Signal
158. NeurIPS 2026StomataBench: Measuring Taxonomic Generalization in Stomatal Detection
159. NeurIPS 2026Stranger Things: When Objects Appear Without Their Typical Neighbours
160. NeurIPS 2026Strengthen Out-of-Distribution Detection via Adaptive Mahalanobis Gap
161. NeurIPS 2026Surprisingly consistent failures of post-hoc OOD detectors reveal security concerns in open-set recognition with modern CNNs and ViTs, stemming from representation mismatch
162. NeurIPS 2026TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition
163. NeurIPS 2026TerraMesh-Masks: Open‑Vocabulary Segmentation for Earth Observation
164. NeurIPS 2026Towards Unified Dynamic Face Landmark Detection
165. NeurIPS 2026Training-Free Open World Object Detection
166. NeurIPS 2026When the Same Coefficients Reach Different Places: Asymmetric Realizability in Transplanting Tokenizers across Large Language Models
167. NeurIPS 2026WildBox: A Dataset and Benchmark for Aerial Monocular 3D Detection of African Savanna Wildlife
168. NeurIPS 2026Witness Overlap: Directional Provenance Inside Open-Weight Model Families

FAQ

How many Open-Vocabulary Detection papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

577 in total: 111 in 2023, 144 in 2024, 154 in 2025, 168 in 2026.

How many Open-Vocabulary Detection papers are at NeurIPS 2026?

NeurIPS 2026 has 42 Open-Vocabulary Detection papers, versus 41 the year before.

How many Open-Vocabulary Detection papers are at ICLR 2026?

ICLR 2026 has 22 Open-Vocabulary Detection papers, versus 24 the year before.

How many Open-Vocabulary Detection papers are at ICML 2026?

ICML 2026 has 22 Open-Vocabulary Detection papers, versus 14 the year before.

How many Open-Vocabulary Detection papers are at CVPR 2026?

CVPR 2026 has 82 Open-Vocabulary Detection papers, versus 75 the year before.

Which conference publishes the most Open-Vocabulary Detection papers?

CVPR, with 294 papers from 2023 to 2026.