Representation Learning

MoEdit: On Learning Quantity Perception for Multi-object Image Editing CVPR 2025 MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition ICML 2025 Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts ICML 2025 MolHFCNet: Enhancing Molecular Graph Representations with Hierarchical Feature Combining and Hybrid Pretraining IJCAI 2025 MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights AAAI 2025 MolParser: End-to-end Visual Recognition of Molecule Structures in the Wild ICCV 2025 Monet: Mixture of Monosemantic Experts for Transformers ICLR 2025 Monitoring Primitive Interactions During the Training of DNNs AAAI 2025 MonSTeR: a Unified Model for Motion, Scene, Text Retrieval ICCV 2025 MORE: Molecule Pretraining with Multi-Level Pretext Task AAAI 2025 More Than Meets the Eye: Enhancing Multi-Object Tracking Even with Prolonged Occlusions ICML 2025 Morpheme Induction for Emergent Language EMNLP 2025 MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphing NAACL 2025 Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning CVPR 2025 Motif-aware Graph Neural Networks for Networked Time Series Imputation AAAI 2025 MotifGPL: Motif-Enhanced Graph Prototype Learning for Deciphering Urban Social Segregation AAAI 2025 Motif-Oriented Representation Learning with Topology Refinement for Drug-Drug Interaction Prediction AAAI 2025 Motion-adaptive Transformer for Event-based Image Deblurring AAAI 2025 MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion ICLR 2025 Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generation AAAI 2025 MotionMap: Representing Multimodality in Human Pose Forecasting CVPR 2025 Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture CVPR 2025 MPCG: Multi-Round Persona-Conditioned Generation for Modeling the Evolution of Misinformation with LLMs EMNLP 2025 MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations ICLR 2025 MR-FIQA: Face Image Quality Assessment with Multi-Reference Representations from Synthetic Data Generation ICCV 2025