Self-Supervised Learning

MESC-3D:Mining Effective Semantic Cues for 3D Reconstruction from a Single Image CVPR 2025 MeshMask: Physics-Based Simulations with Masked Graph Neural Networks ICLR 2025 Meta-Reflection: A Feedback-Free Reflection Learning Framework ACL 2025 MEXMA: Token-level objectives improve sentence representations ACL 2025 MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised Learning AAAI 2025 MICAS: Multi-grained In-Context Adaptive Sampling for 3D Point Cloud Processing CVPR 2025 MIND: Math Informed syNthetic Dialogues for Pretraining LLMs ICLR 2025 Mind_Matrix at CQs-Gen 2025: Adaptive Generation of Critical Questions for Argumentative Interventions ACL 2025 MindPainter: Efficient Brain-Conditioned Painting of Natural Images via Cross-Modal Self-Supervised Learning AAAI 2025 MindTuner: Cross-Subject Visual Decoding with Visual Fingerprint and Semantic Correction AAAI 2025 Mining the Past with Dual Criteria: Integrating Three types of Historical Information for Context-aware Event Forecasting EMNLP 2025 Minority-Focused Text-to-Image Generation via Prompt Optimization CVPR 2025 MirrorDuo: Reflection-Consistent Visuomotor Learning from Mirrored Demonstration Pairs CoRL 2025 Mitigating Shortcut Learning with InterpoLated Learning ACL 2025 MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations WACV 2025 Mixing Inference-time Experts for Enhancing LLM Reasoning EMNLP 2025 Mixture of Experts as Representation Learner for Deep Multi-View Clustering AAAI 2025 Mixture of Parrots: Experts improve memorization more than reasoning ICLR 2025 ML$^2$-GCL: Manifold Learning Inspired Lightweight Graph Contrastive Learning ICML 2025 MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents ICLR 2025 MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence Calibration ACL 2025 mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data ACL 2025 MM-Mixing: Multi-Modal Mixing Alignment for 3D Understanding AAAI 2025 Modality-Guided Dynamic Graph Fusion and Temporal Diffusion for Self-Supervised RGB-T Tracking IJCAI 2025 Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training ICML 2025