contrastive learning
A technique that learns to differentiate between similar and dissimilar samples, often by maximizing similarity for positive pairs and minimizing it for negative pairs in the feature space.
- A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics
- AdaTS: Learning Adaptive Time Series Representations via Dynamic Soft Contrasts
- Aligning Text to Image in Diffusion Models is Easier Than You Think
- BMW: Bidirectionally Memory bank reWriting for Unsupervised Person Re-Identification
- Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining
- CALM: Culturally Self-Aware Language Models
- CoUn: Empowering Machine Unlearning via Contrastive Learning
- Complete Structure Guided Point Cloud Completion via Cluster- and Instance-Level Contrastive Learning
- Contrastive Learning with Data Misalignment: Feature Purity, Training Dynamics and Theoretical Generalization Guarantees
- CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder
- Diversity Is All You Need for Contrastive Learning: Spectral Bounds on Gradient Magnitudes
- Dual Prototype-Enhanced Contrastive Framework for Class-Imbalanced Graph Domain Adaptation
- Embodied Cognition Augmented End2End Autonomous Driving
- Enhancing Contrastive Learning with Variable Similarity
- Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
- From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos
- Fuse2Match: Training-Free Fusion of Flow, Diffusion, and Contrastive Models for Zero-Shot Semantic Matching
- Generalized Contrastive Learning for Universal Multimodal Retrieval
- Generalized and Invariant Single-Neuron In-Vivo Activity Representation Learning
- HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models
- Image Token Matters: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing
- Improve Temporal Reasoning in Multimodal Large Language Models via Video Contrastive Decoding
- Language‑Bias‑Resilient Visual Question Answering via Adaptive Multi‑Margin Collaborative Debiasing
- MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
- Mitigating Spurious Features in Contrastive Learning with Spectral Regularization
- Mixture-of-Experts Meets In-Context Reinforcement Learning
- Neural-Driven Image Editing
- Object Concepts Emerge from Motion
- PCA++: How Uniformity Induces Robustness to Background Noise in Contrastive Learning
- Path-Enhanced Contrastive Learning for Recommendation
- RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models
- REOBench: Benchmarking Robustness of Earth Observation Foundation Models
- Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2
- Reasoning Planning for Language Models
- Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval
- Reconciling Geospatial Prediction and Retrieval via Sparse Representations
- SRA-CL: Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation
- STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning
- Sampled Estimators For Softmax Must Be Biased
- Scaling Language-centric Omnimodal Representation Learning
- Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning
- Spatiotemporal Consensus with Scene Prior for Unsupervised Domain Adaptive Person Search
- Stochastic Forward-Forward Learning through Representational Dimensionality Compression
- TRACE: Contrastive learning for multi-trial time series data in neuroscience
- TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception
- Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation
- The Complexity of Finding Local Optima in Contrastive Learning
- Time-Evolving Dynamical System for Learning Latent Representations of Mouse Visual Neural Activity
- Towards Robust Uncertainty Calibration for Composed Image Retrieval
- Understanding Contrastive Learning via Gaussian Mixture Models
- VITRIX-CLIPIN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction-Editing Data and Long Captions
- Variational Supervised Contrastive Learning
- Versatile Transferable Unlearnable Example Generator