Self-Supervised Learning

Beyond Confidence: Exploiting Homogeneous Pattern for Semi-Supervised Semantic Segmentation ICML 2025 Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance EMNLP 2025 Beyond Homophily: Graph Contrastive Learning with Macro-Micro Message Passing AAAI 2025 Beyond Inherent Cognition Biases in LLM-Based Event Forecasting: A Multi-Cognition Agentic Framework EMNLP 2025 Beyond instruction-conditioning, MoTE: Mixture of Task Experts for Multi-task Embedding Models ACL 2025 Beyond Random Augmentations: Pretraining with Hard Views ICLR 2025 Beyond Single Images: Retrieval Self-Augmented Unsupervised Camouflaged Object Detection ICCV 2025 Beyond the Answer: Advancing Multi-Hop QA with Fine-Grained Graph Reasoning and Evaluation ACL 2025 Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset NAACL 2025 Beyond Words: Augmenting Discriminative Richness via Diffusions in Unsupervised Prompt Learning CVPR 2025 Bi-DiffCD: Bidirectional Diffusion Guided Collaborative Change Detection for Arbitrary-Modal Remote Sensing Images IJCAI 2025 Bidirectional Reasoning Supervision for Multilingual Financial Decision Making EMNLP 2025 Bi-level Contrastive Learning for Knowledge-Enhanced Molecule Representations AAAI 2025 Bi-Level Optimization for Self-Supervised AI-Generated Face Detection ICCV 2025 BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics ICLR 2025 Birth and Death of a Rose CVPR 2025 Blind2Sound: Self-Supervised Image Denoising without Residual Noise ICCV 2025 BMIP: Bi-directional Modality Interaction Prompt Learning for VLM IJCAI 2025 BOE-ViT: Boosting Orientation Estimation with Equivariance in Self-Supervised 3D Subtomogram Alignment CVPR 2025 BoN Appetit Team at LeWiDi-2025: Best-of-N Test-time Scaling Can Not Stomach Annotation Disagreements (Yet) EMNLP 2025 Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features ICCV 2025 Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners ICML 2025 Boost Self-Supervised Dataset Distillation via Parameterization, Predefined Augmentation, and Approximation ICLR 2025 Boost Your Human Image Generation Model via Direct Preference Optimization CVPR 2025 Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approach AAAI 2025