NeurIPS 2026 accepted papers on Label-efficient and robust learning
349 of the 6,080 papers accepted at NeurIPS 2026 (5.7%) are on Label-efficient and robust learning, compared with 5.9% at NeurIPS 2025. They fall into 9 topics.
See NeurIPS 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 · 154 papers
- Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects (1 citation)
- Generative Cross-Entropy: A Strictly Proper Loss for Data-Efficient Classification (1 citation)
- TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks (1 citation)
- Action-On-Item Preference Flow: A Shared Event Schema for Predictive and Generative Personalization
- Active Learning From Positive and Unlabeled Examples
- Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery
- AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving
- Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias
- Calibration without Ground Truth
- Capturing LLM Capabilities via Evidence-Calibrated Query Clustering
- Coherent Hierarchical Multi-Label Learning to Defer for Medical Imaging
- Concept frustration: Aligning human concepts and machine representations
and 142 more in the interactive map.
Self-supervised and contrastive · 37 papers
- mRNABench: A curated benchmark for mature mRNA property and function prediction (3 citations)
- Brain2voice 2.0: High-performance voice synthesis brain-computer interface
- Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning
- DINOv3
- Efficient Dataset Distillation for Pre-Trained Self-Supervised Models via Statistical Flow Matching
- Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation
- Learning What to Predict: Downstream-Guided Task Design for Continued Pretraining
- Leveraging unlabelled data for generalizable neural population decoding
- Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensation
- OpenWhistle: A Large-Scale Longitudinal Dataset and Benchmark of Bottlenose Dolphin Vocalizations
- PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment
- Reconstructing the Vocal Tract with Differentiable Acoustic Simulation
and 25 more in the interactive map.
Knowledge distillation · 36 papers
- AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
- Closed-Form Linear-Probe Dataset Distillation for Pre-trained Vision Models
- DD-Ranking: Rethinking the Evaluation of Dataset Distillation
- DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation
- Distilling What Matters: Confidence-Aware Selective Distillation for Large Language Models
- Identified-Set Geometry of Distributional Model Extraction under Top-K Censored API Access
- LARK: Learnability-Grounded Trajectory Selection for Efficient Reasoning Distillation
- Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory
- Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR
- Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets?
- SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision
- SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation
and 24 more in the interactive map.
OOD and anomaly detection · 32 papers
- A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts
- ASAT: Adaptive Scoring and Thresholding with Human Feedback for Robust Out-of-Distribution Detection
- Auditing Attention Head Masking for Out-of-Distribution Detection: Cross-Architecture Wins, Failures, and Polarity Inversions
- Beyond Normal References: Discriminative Few-Shot Anomaly Detection
- Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization
- Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning
- FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks
- Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
- Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry
- Local Sparsity Enables Unsupervised LLM Safety Detection
- MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
- Perturb and Correct: Post-Hoc Ensembles using Affine Redundancy
and 20 more in the interactive map.
Domain adaptation and generalization · 29 papers
- Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study
- Knowledge Transfer Scaling Laws for 3D Medical Imaging
- Language-Induced Priors for Domain Adaptation
- Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMs
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions
- The Shape of Events: Edge-Based Inductive Biases via Cross-Domain Distillation
- Transfer Learning Through Conditional Quantile Matching
- Why Invariance is Not Enough for Biomedical Domain Generalization and How to Fix It
- ADIS-Law: Unified Scaling Laws for Annealing-Phase Domain Injection in Large Language Models
- Beyond Average Flatness: Domain-wise Flatness for Domain Generalization
- Bridging Sequence and Structure with Unified Domain Adaptation for Drug-Target Interaction Prediction
- Bridging Simulation and Reality: Geometry and Decision Alignment for Autonomous Driving
and 17 more in the interactive map.
Zero-/few-shot and meta-learning · 20 papers
- A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems
- Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization
- RABBiT: Rapidly adaptive BOLD foundation model via brain-tuning for accurate zero-shot and few-shot prediction of speech-elicited responses in the brain
- Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Training
- WildBox: A Dataset and Benchmark for Aerial Monocular 3D Detection of African Savanna Wildlife
- A Simple Unigram Cross-Entropy Lens on the Lexical Imprint of Pre-training Data
- Beyond the Node Barrier: Zero-Shot Strategy Planning for LLM Training on Super-Nodes
- DDGE: Disentangled Dirichlet Geodesic Evaluation for Robust Few-Shot Learning
- Emergent Biological Capabilities in a Foundation Model for Molecular Interactions
- EpistasisBench: Revealing Structural Limitations of Zero-Shot Protein Language Models
- Hyperspherical Local Margin Retraction for Zero-Shot Instance-Wise Machine Unlearning
- Intervention-Guided Image-Free Classifier Expansion for Fine-Grained Recognition
and 8 more in the interactive map.
Test-time adaptation · 19 papers
- "What is Different Between These Datasets?" A Framework for Explaining Data Distribution Shifts
- Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution Shifts
- Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts
- Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging
- EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample
- ASSET: Acquisition-Sensitive Subspace Estimation for Test-Time Adaptation of Medical VLMs
- Complementary Cache Guidance with Gradient Disentanglement for Continuous Test-Time Adaptation
- DEDCA: Test-Time Adaptation for Generalized AI-Generated Image Detection
- Deployment-Memory LLM Test-Time Training Should Require Behavioral Evidence Beyond Perplexity
- Dynamic Context Modeling for Longitudinal Mental Health Monitoring under Distribution Shift
- Efficient Test-Time Adaptation For Robot Policies
- GeoCurv-TTT: Geometry-Aware Deformation Restoration for 3D Test-Time Training
and 7 more in the interactive map.
Noisy labels · 14 papers
- An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration
- Estimation of the Label-Noise Transition Matrix with Performance Guarantees via Selective Classification
- Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noise
- Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise
- Radial-Angular Geometry for Reliable Update Diagnosis in Noisy-Label Learning
- Stress-Testing Neural Network Verifiers with Provably Robust Instances
- Unveiling Memorization–Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise
- Counting without Scale: Scale-Consistent Error Correction for Crowd Counting
- Dual-Granularity Learning for Regression with Continuous Noisy Labels
- Fisher information and the geometry of memorization in neural networks
- GradTrack: Detecting Noisy Labels via Temporal Trajectories of Class-wise Gradient Misalignment
- Not All Instances Should Contribute Equally: Sparse Support Grounding via Unbalanced Transport for Heterogeneous MIL
and 2 more in the interactive map.
Semi-supervised learning · 8 papers
- ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control
- Label-Efficient Dataset Pruning via Semi-Supervised Pseudo-Labeling
- AdapMatch: Adaptive Bias Decoupling for Semi-Supervised Partial Label Learning under Unknown Class Distributions
- CLEAR: Complementary Tripartite Play with Bayesian Calibration for Semi-Supervised Edge Classification
- Mitigating Confidence Miscalibration in Open-World Semi-Supervised Learning
- Parametric Meets Non-parametric: Bridging Dual Prediction Spaces for Semi-supervised Medical Image Segmentation
- Progressive Pseudo-label Self-balancing Towards Unsupervised Vision-Language Models Adaptation
- Resilient Semi-Supervised Inference with Heterogeneous Unlabeled Data