AAAI 2026 accepted papers on Label-efficient and robust learning
395 of the 4,417 papers accepted at AAAI 2026 (8.9%) are on Label-efficient and robust learning, compared with 11.3% at AAAI 2025. They fall into 9 topics.
See AAAI 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Recognition and long-tail · 167 papers
- From Points to Coalitions: Hierarchical Contrastive Shapley Values for Prioritizing Data Samples (5 citations)
- DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning (4 citations)
- Wavelet Enhanced Adaptive Frequency Filter for Sequential Recommendation (4 citations)
- X-ReID: Multi-granularity Information Interaction for Video-Based Visible-Infrared Person Re-Identification (4 citations)
- OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestion (3 citations)
- RealRep: Generalized SDR-to-HDR Conversion via Attribute-Disentangled Representation Learning (3 citations)
- Trusted Multi-view Learning for Long-tailed Classification (3 citations)
- EMOD: A Unified EEG Emotion Representation Framework Leveraging V-A Guided Contrastive Learning (2 citations)
- Exploiting Inter-Session Information with Frequency-enhanced Dual-Path Networks for Sequential Recommendation (2 citations)
- Fidelity-Aware Recommendation Explanations via Stochastic Path Integration (2 citations)
- Hypergraph-Based Multi-View Multi-Label Classification via Adaptive High-Order Semantic Fusion (2 citations)
- Inductive Generative Recommendation via Retrieval-based Speculation (2 citations)
and 155 more in the interactive map.
Domain adaptation and generalization · 55 papers
- From Blind Transfer to Wise Selection: Prototype-Driven Neighbor-Domain Adaptation for Fake News Detection (5 citations)
- Anchor-Guided Discriminative Subspace Alignment and Clustering for Cross-Scene Hyperspectral Imagery (3 citations)
- Domain Adaptation Guided Infrared and Visible Image Fusion (3 citations)
- Dynamic-Static Collaboration for Unsupervised Domain Adaptive Video-Based Visible-Infrared Person Re-Identification (3 citations)
- Earth-Adapter: Bridge the Geospatial Domain Gaps with a Frequency-Guided Mixture of Adapters (3 citations)
- Bipartite Mode Matching for Vision Training Set Search from a Hierarchical Data Server (2 citations)
- Causal Decoupling Domain Generalization for Remote Sensing Change Detection (2 citations)
- Causal-Tune: Mining Causal Factors from Vision Foundation Models for Domain Generalized Semantic Segmentation (2 citations)
- From IDs to Semantics: A Generative Framework for Cross-Domain Recommendation with Adaptive Semantic Tokenization (2 citations)
- Wi-CBR: Salient-aware Adaptive WiFi Sensing for Cross-domain Behavior Recognition (2 citations)
- Balancing Multimodal Domain Generalization via Gradient Modulation and Projection (1 citation)
- Bridging Day and Night: Target-Class Hallucination Suppression in Unpaired Image Translation (1 citation)
and 43 more in the interactive map.
Self-supervised and contrastive · 34 papers
- A Network of Biologically Inspired Rectified Spectral Units (ReSUs) Learns Hierarchical Features Without Error Backpropagation (1 citation)
- On Model and Data Scaling for Skeleton-based Self-Supervised Gait Recognition (1 citation)
- Parameter-Free Clustering via Self-Supervised Consensus Maximization (1 citation)
- RiverScope: High-Resolution River Masking Dataset (1 citation)
- Self-Supervised Learning Based on Transformed Image Reconstruction for Equivariance-Coherent Feature Representation (1 citation)
- SigFusion: Unified Signal-Level Self-Supervised Learning Paradigm for Image Fusion (1 citation)
- State Mamba: Spatiotemporal EEG State-Space Model with Dynamic Brain Alignment for Cross-Subject Representation (1 citation)
- Time2Agri: Temporal Pretext Tasks for Agricultural Monitoring (1 citation)
- Towards Better Code Understanding in Decoder-Only Models with Contrastive Learning (1 citation)
- Appearance Discrepancy-guided Sequence Hybrid Masking for Robust Scene Text Recognition
- BraSTORM: A Dual-Branch Self-Supervised Framework for EEG Representation Learning via Input-Level Spatio-Temporal Decomposition
- Cyto-SSL: A Self-Supervised Pretraining Framework for Cytology Foundation Model
and 22 more in the interactive map.
Knowledge distillation · 30 papers
- S^2-KD: Semantic-Spectral Knowledge Distillation Spatiotemporal Forecasting (4 citations)
- Distillation Dynamics: Towards Understanding Feature-Based Distillation in Vision Transformers (2 citations)
- KeenKT: Knowledge Mastery-State Disambiguation for Knowledge Tracing (2 citations)
- Debiased Cognitive Diagnosis: A Contrastive Counterfactual Modeling Method via Variational Autoencoder (1 citation)
- Flow-Based Knowledge Transfer for Efficient Large Model Distillation (1 citation)
- Heterogeneous Complementary Distillation (1 citation)
- Revisiting Cross-Architecture Distillation: Adaptive Dual-Teacher Transfer for Lightweight Video Models (1 citation)
- A Closer Look at Knowledge Distillation in Spiking Neural Network Training
- ASKD: Reinforcement Learning-Style Knowledge Distillation with Quality-Adaptive Skewness
- Balanced Knowledge Distillation for Large Language Models with Mix-of-Experts
- Bi-Spectrum Distillation: Addressing Spectral Mismatch in ANN-SNN Knowledge Transfer
- Bidirectional Counterfactual Distillation for Review-Based Recommendation
and 18 more in the interactive map.
OOD and anomaly detection · 29 papers
- Cross-modal Proxy Evolving for OOD Detection with Vision-Language Models (17 citations)
- IAD-R1: Reinforcing Consistent Reasoning in Industrial Anomaly Detection (9 citations)
- Commonality in Few: Few-Shot Multimodal Anomaly Detection via Hypergraph-Enhanced Memory (3 citations)
- Out-of-Distribution Detection with Positive and Negative Prompt Supervision Using Large Language Models (3 citations)
- AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection (2 citations)
- IDK-S: Incremental Distributional Kernel for Streaming Anomaly Detection (2 citations)
- AnoStyler: Text-Driven Localized Anomaly Generation via Lightweight Style Transfer (1 citation)
- CASL: Curvature-Augmented Self-supervised Learning for 3D Anomaly Detection (1 citation)
- DCAC: Dynamic Class-Aware Cache Creates Stronger Out-of-Distribution Detectors (1 citation)
- GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI Agents (1 citation)
- ICAD-LLM: One-for-All Anomaly Detection via In-Context Learning with Large Language Models (1 citation)
- Robust Detection of Synthetic Tabular Data Under Schema Variability (1 citation)
and 17 more in the interactive map.
Semi-supervised learning · 27 papers
- Perceive, Act and Correct: Confidence Is Not Enough for Hyperspectral Classification (2 citations)
- S5: Scalable Semi-Supervised Semantic Segmentation in Remote Sensing (2 citations)
- Bidirectional Channel-selective Semantic Interaction for Semi-Supervised Medical Segmentation (1 citation)
- DiCaP: Distribution-Calibrated Pseudo-labeling for Semi-Supervised Multi-Label Learning (1 citation)
- DualFete: Revisiting Teacher-Student Interactions from a Feedback Perspective for Semi-supervised Medical Image Segmentation (1 citation)
- Neural Collapse Priors Driven Trust Semi-Supervised Multi-View Classification (1 citation)
- Sampling Control for Imbalanced Calibration in Semi-Supervised Learning (1 citation)
- A Pseudo-Label Optimization Method Based on Polar Coordinate Modeling and Prior Constraints
- Beyond Binary Classification: A Semi-supervised Approach to Generalized AI-generated Image Detection
- BidMatch: Boosting Semi-Supervised Learning by Bi-Dimensional Sample Weight Guidance
- Collaborative Dual Representations for Semi-Supervised Partial Label Learning
- Every Little Bit Helps: Exploring Better Utilization of Unlabeled Data for Semi-supervised Singing Melody Extraction Using Multi-bands Diffusion Model
and 15 more in the interactive map.
Zero-/few-shot and meta-learning · 21 papers
- Dual-Channel Learning Framework for Zero-Shot CircRNA-miRNA Interaction Prediction via State Space Modeling (8 citations)
- Counterfactual-Driven Zero-Shot Classifier Expansion (3 citations)
- HQ-SVC: Towards High-Quality Zero-Shot Singing Voice Conversion in Low-Resource Scenarios (1 citation)
- MSME: A Multi-Stage Multi-Expert Framework for Zero-Shot Stance Detection (1 citation)
- Training and Inference Within 1 Second – Tackle Cross-Sensor Degradation of Real-World Pansharpening with Efficient Residual Feature Tailoring (1 citation)
- Composition-Incremental Learning for Compositional Generalization
- F2SST: Frequency-to-Spatial Semantic Transfer for Few-Shot Image Classification
- I2CD: An Invertible Causal Framework for Compositional Zero-Shot Learning via Disentangle-Compose-Disentangle
- Incorporating Token Importance in Multi-Vector Retrieval
- Induce, Align, Predict: Zero-Shot Stance Detection via Cognitive Inductive Reasoning
- Leveraging Failed Samples: A Few-Shot and Training-Free Framework for Generalized Deepfake Detection
- MPA: Multimodal Prototype Augmentation for Few-Shot Learning
and 9 more in the interactive map.
Test-time adaptation · 17 papers
- Shedding the Facades, Connecting the Domains: Detecting Shifting Multimodal Hate Video with Test-Time Adaptation (2 citations)
- Adapt-As-You-Walk Through the Clouds: Training-Free Online Test-Time Adaptation of 3D Vision-Language Foundation Models (1 citation)
- Improving Batch Normalization with Test-Time Adaptation for Robust Object Detection in Self-Driving (1 citation)
- Lost in Time? A Meta-Learning Framework for Time-Shift-Tolerant Physiological Signal Transformation (1 citation)
- Multi-Task Test-time Adaptation via Gradient Consensus and Plasticity Constraint (1 citation)
- RFF-TTA: Physical Information-Aware Prototype for Temporally Varying RF Fingerprinting Online Test-Time-Adaptation (1 citation)
- 4D Point Cloud Segmentation via Active Test-Time Adaptation
- Bridging Modalities via Progressive Re-alignment for Multimodal Test-Time Adaptation
- Cross-Sample Augmented Test-Time Adaptation for Personalized Intraoperative Hypotension Prediction
- Diffusion-calibrated Continual Test-time Adaptation
- DISCODE: Distribution-Aware Score Decoder for Robust Automatic Evaluation of Image Captioning
- Duplex Rewards Optimization for Test-Time Composed Image Retrieval
and 5 more in the interactive map.
Noisy labels · 15 papers
- Is the Information Bottleneck Robust Enough? Towards Label-Noise Resistant Information Bottleneck Learning (2 citations)
- Neighbor-aware Instance Refining with Noisy Labels for Cross-Modal Retrieval (1 citation)
- Prototype-Guided Supervision for Graph Learning with Noisy and Sparse Labels (1 citation)
- CogniTrust: Cognitive Memory-Driven Verifiable Supervision for Robust Hashing
- Content Diversity-guided Ambiguity Mitigation for Open-Set Noisy Label Learning
- Denoising Mixup for Regression
- HaNa: Hardness and Noise-Aware Robust Cross-modal Retrieval
- Human-Corrected Labels Learning: Enhancing Labels Quality via Human Correction of VLMs Discrepancies
- Jump-teaching: Combating Sample Selection Bias via Temporal Disagreement
- Leveraging Dissimilarity Invariance as a Robust Anchor for Learning with Noisy Labels
- PCSR: Pseudo-label Consistency-Guided Sample Refinement for Noisy Correspondence Learning
- QAPNet: A Quantum-Attentive Patchwise Network for Robust Medical Image Classification Under Noisy Inputs
and 3 more in the interactive map.