Machine Learning

COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets ICCV 2025 CoMemo: LVLMs Need Image Context with Image Memory ICML 2025 Comet: Dialog Context Fusion Mechanism for End-to-End Task-Oriented Dialog with Multi-task Learning COLING 2025 COME: Test-time Adaption by Conservatively Minimizing Entropy ICLR 2025 ComFace: Facial Representation Learning with Synthetic Data for Comparing Faces WACV 2025 ComLoRA: A Competitive Learning Approach for Enhancing LoRA ICLR 2025 Command-A-Translate: Raising the Bar of Machine Translation with Difficulty Filtering EMNLP 2025 Command R7B Arabic: a small, enterprise-focused, multilingual, and culturally aware Arabic LLM ACL 2025 COMM: Concentrated Margin Maximization for Robust Document-Level Relation Extraction AAAI 2025 COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems Against Semantic Attacks AAAI 2025 CoMMIT: Coordinated Multimodal Instruction Tuning EMNLP 2025 Commitment to Sparse Strategies in Two-Player Games AAAI 2025 Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space CVPR 2025 Common Ground, Diverse Roots: The Difficulty of Classifying Common Examples in Spanish Varieties COLING 2025 Common Learning Constraints Alter Interpretations of Direct Preference Optimization AISTATS 2025 Common Sense Bias Modeling for Classification Tasks AAAI 2025 Communicating Activations Between Language Model Agents ICML 2025 Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models ACL 2025 Community-Aware Variational Autoencoder for Continuous Dynamic Networks AAAI 2025 Community-Centric Graph Unlearning AAAI 2025 Community detection with the Bethe-Hessian COLT 2025 Community Forensics: Using Thousands of Generators to Train Fake Image Detectors CVPR 2025 Commute Graph Neural Networks ICML 2025 CommVQ: Commutative Vector Quantization for KV Cache Compression ICML 2025 CoMoE: Contrastive Representation for Mixture-of-Experts in Parameter-Efficient Fine-tuning EMNLP 2025