Zero-Shot Classification papers, 2023–2026

Key findings

• Zero-Shot Classification went from 203 papers in 2023 to 257 in 2026, roughly 1.3x in three years.
• CVPR publishes the most Zero-Shot Classification work: 318 papers from 2023 to 2026, 32% of the four-venue total.
• The fastest-growing overlap is with Reinforcement Learning: papers tagged with both rose from 7 in 2023 to 22 in 2026.
• Among the 5 topics under Open-Vocabulary Vision, it ranks #1 by 2026 paper count; the fastest grower in the group, Visual Grounding, is up 4.3x versus 1.3x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems
• ICML 2026Beyond Rational Illusion: Behaviorally Realistic Strategic Classification
• ICLR 2026Boomerang Distillation Enables Zero-Shot Model Size Interpolation
• CVPR 2026AG-VAS Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models
• NeurIPS 2025\(\varepsilon\)-Optimally Solving Two-Player Zero-Sum POSGs
• ICML 2025A Classification View on Meta Learning Bandits
• ICLR 2025Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification
• CVPR 2025AA-CLIP: Enhancing Zero-Shot Anomaly Detection via Anomaly-Aware CLIP
• NeurIPS 2024BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity
• ICML 2024Agent Instructs Large Language Models to be General Zero-Shot Reasoners
• ICLR 2024AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval
• CVPR 2024Depth-aware Test-Time Training for Zero-shot Video Object Segmentation
• NeurIPS 2023Black-box Backdoor Defense via Zero-shot Image Purification
• ICML 2023A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models
• ICLR 2023Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models
• CVPR 2023(ML)$^2$P-Encoder: On Exploration of Channel-Class Correlation for Multi-Label Zero-Shot Learning
• NeurIPS 2026Align3D-AD: Cross-Modal Feature Alignment and Dual-Prompt Learning for Zero-shot 3D Anomaly Detection
• ICML 2026Calibrating Uncertainty for Zero-Shot Adversarial CLIP
• ICLR 2026Decoupling Primitive with Experts: Dynamic Feature Alignment for Compositional Zero-Shot Learning
• CVPR 2026DLVP-CLIP Enhancing Fine-Grained Zero-Shot Anomaly Detection via Dynamic Local Visual

All Zero-Shot Classification papers

992 papers, page 6 of 20

251. NeurIPS 2026Voxel as Token: A New Perspective for Zero-shot Cross-subject Vision Decoding
252. NeurIPS 2026When a Zero-Shooter Cheats: Improving Age Estimation via Activation Steering
253. NeurIPS 2026When Does Subspace Direction Matter for LoRA? Regime Analysis of the Magnitude Principle in Few-Shot Adaptation
254. NeurIPS 2026When Graph Structure Provably Helps Classification: Non-Asymptotic Recovery Guarantees
255. NeurIPS 2026ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestration
256. NeurIPS 2026Zero-Shot Coordination among LLM Agents
257. NeurIPS 2026Zero-Shot Instruction Following in RL via Structured LTL Representations
258. CVPR 2025AA-CLIP: Enhancing Zero-Shot Anomaly Detection via Anomaly-Aware CLIP
259. CVPR 2025Active Data Curation Effectively Distills Large-Scale Multimodal Models
260. CVPR 2025Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection
261. CVPR 2025Beyond Image Classification: A Video Benchmark and Dual-Branch Hybrid Discrimination Framework for Compositional Zero-Shot Learning
262. CVPR 2025Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors
263. CVPR 2025CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP
264. CVPR 2025Conformal Prediction for Zero-Shot Models
265. CVPR 2025ConMo: Controllable Motion Disentanglement and Recomposition for Zero-Shot Motion Transfer
266. CVPR 2025Cross-View Completion Models are Zero-shot Correspondence Estimators
267. CVPR 2025Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera
268. CVPR 2025Diffusion Bridge: Leveraging Diffusion Model to Reduce the Modality Gap Between Text and Vision for Zero-Shot Image Captioning
269. CVPR 2025Diffusion Self-Distillation for Zero-Shot Customized Image Generation
270. CVPR 2025EIDT-V: Exploiting Intersections in Diffusion Trajectories for Model-Agnostic, Zero-Shot, Training-Free Text-to-Video Generation
271. CVPR 2025Enhancing Few-Shot Class-Incremental Learning via Training-Free Bi-Level Modality Calibration
272. CVPR 2025EZSR: Event-based Zero-Shot Recognition
273. CVPR 2025FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models
274. CVPR 2025FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classification
275. CVPR 2025Forensic Self-Descriptions Are All You Need for Zero-Shot Detection, Open-Set Source Attribution, and Clustering of AI-generated Images
276. CVPR 2025FoundationStereo: Zero-Shot Stereo Matching
277. CVPR 2025From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspective
278. CVPR 2025Generalized Zero-Shot Classification via Semantics-Free Inter-Class Feature Generation
279. CVPR 2025Generative Zero-Shot Composed Image Retrieval
280. CVPR 2025GenPC: Zero-shot Point Cloud Completion via 3D Generative Priors
281. CVPR 2025HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion
282. CVPR 2025Hybrid Global-Local Representation with Augmented Spatial Guidance for Zero-Shot Referring Image Segmentation
283. CVPR 2025Hyperspectral Pansharpening via Diffusion Models with Iteratively Zero-Shot Guidance
284. CVPR 2025IM-Zero: Instance-level Motion Controllable Video Generation in a Zero-shot Manner
285. CVPR 2025InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing
286. CVPR 2025Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce Classification
287. CVPR 2025L-SWAG: Layer-Sample Wise Activation with Gradients Information for Zero-Shot NAS on Vision Transformers
288. CVPR 2025Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator
289. CVPR 2025Learning on Model Weights using Tree Experts
290. CVPR 2025LesionLocator: Zero-Shot Universal Tumor Segmentation and Tracking in 3D Whole-Body Imaging
291. CVPR 2025LOGICZSL: Exploring Logic-induced Representation for Compositional Zero-shot Learning
292. CVPR 2025Logits DeConfusion with CLIP for Few-Shot Learning
293. CVPR 2025Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval
294. CVPR 2025Mitigating Ambiguities in 3D Classification with Gaussian Splatting
295. CVPR 2025MonSter: Marry Monodepth to Stereo Unleashes Power
296. CVPR 2025MVSAnywhere: Zero-Shot Multi-View Stereo
297. CVPR 2025Navigating the Unseen: Zero-shot Scene Graph Generation via Capsule-Based Equivariant Features
298. CVPR 2025Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models
299. CVPR 2025Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition
300. CVPR 2025On the Zero-shot Adversarial Robustness of Vision-Language Models: A Truly Zero-shot and Training-free Approach

FAQ

How many Zero-Shot Classification papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

992 in total: 203 in 2023, 262 in 2024, 270 in 2025, 257 in 2026.

How many Zero-Shot Classification papers are at NeurIPS 2026?

NeurIPS 2026 has 68 Zero-Shot Classification papers, versus 86 the year before.

How many Zero-Shot Classification papers are at ICLR 2026?

ICLR 2026 has 44 Zero-Shot Classification papers, versus 56 the year before.

How many Zero-Shot Classification papers are at ICML 2026?

ICML 2026 has 64 Zero-Shot Classification papers, versus 49 the year before.

How many Zero-Shot Classification papers are at CVPR 2026?

CVPR 2026 has 81 Zero-Shot Classification papers, versus 79 the year before.

Which conference publishes the most Zero-Shot Classification papers?

CVPR, with 318 papers from 2023 to 2026.