Self-Supervised Learning

Masking meets Supervision: A Strong Learning Alliance CVPR 2025 MaskTwins: Dual-form Complementary Masking for Domain-Adaptive Image Segmentation ICML 2025 MatAnyone: Stable Video Matting with Consistent Memory Propagation CVPR 2025 MaTe: Images Are All You Need for Material Transfer via Diffusion Transformer ICCV 2025 MAVias: Mitigate any Visual Bias ICCV 2025 MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs ACL 2025 MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval ACL 2025 MENTOR: Human Perception-Guided Pretraining for Increased Generalization WACV 2025 MENTOR: Multi-level Self-supervised Learning for Multimodal Recommendation AAAI 2025 MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization CVPR 2025 MERIT: Multi-Agent Collaboration for Unsupervised Time Series Representation Learning ACL 2025 Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models ACL 2025 Meta-Reflection: A Feedback-Free Reflection Learning Framework ACL 2025 MetaSynth: Meta-Prompting-Driven Agentic Scaffolds for Diverse Synthetic Data Generation ACL 2025 MIETT: Multi-Instance Encrypted Traffic Transformer for Encrypted Traffic Classification AAAI 2025 Mimic Blocker: Self-Supervised Adversarial Training for Voice Conversion Defense with Pretrained Feature Extractors Interspeech 2025 MIMTrack: In-Context Tracking via Masked Image Modeling AAAI 2025 MindPainter: Efficient Brain-Conditioned Painting of Natural Images via Cross-Modal Self-Supervised Learning AAAI 2025 Mind the Gap: Preserving and Compensating for the Modality Gap in CLIP-Based Continual Learning ICCV 2025 Mining the Past with Dual Criteria: Integrating Three types of Historical Information for Context-aware Event Forecasting EMNLP 2025 MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations WACV 2025 MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models ACL 2025 Model as Loss: A Self-Consistent Training Paradigm Interspeech 2025 MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights AAAI 2025 Mondrian: A Framework for Logical Abstract (Re)Structuring EMNLP 2025