Machine Learning

Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional ICML 2025 Action Sequence Augmentation for Action Anticipation ICLR 2025 ActionStudio: A Lightweight Framework for Data and Training of Large Action Models EMNLP 2025 Activating Sparse Part Concepts for 3D Class Incremental Learning CVPR 2025 Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss ICML 2025 Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks ICLR 2025 Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Model ACML 2025 Activation Subspaces for Out-of-Distribution Detection ICCV 2025 Active Bipartite Ranking with Smooth Posterior Distributions AISTATS 2025 Active Curriculum Language Modeling over a Hybrid Pre-training Method EMNLP 2025 Active Data Curation Effectively Distills Large-Scale Multimodal Models CVPR 2025 Active Domain Knowledge Acquisition with 100-Dollar Budget: Enhancing LLMs via Cost-Efficient, Expert-Involved Interaction in Sensitive Domains EMNLP 2025 Active Evaluation Acquisition for Efficient LLM Benchmarking ICML 2025 Active Feature Acquisition for Personalised Treatment Assignment AISTATS 2025 Active feature acquisition via explainability-driven ranking ICML 2025 Active Few-Shot Learning for Text Classification NAACL 2025 Active Fine-Tuning of Multi-Task Policies ICML 2025 Active Fourier Auditor for Estimating Distributional Properties of ML Models AAAI 2025 ActiveGAMER: Active GAussian Mapping through Efficient Rendering CVPR 2025 Active Geospatial Search for Efficient Tenant Eviction Outreach AAAI 2025 ActiveHAI: Active Collection Based Human-AI Diagnosis with Limited Expert Predictions IJCAI 2025 Active Hyperspectral Imaging Using an Event Camera CVPR 2025 Active Large Language Model-Based Knowledge Distillation for Session-Based Recommendation AAAI 2025 Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation EMNLP 2025 Active Learning for Continual Learning: Keeping the Past Alive in the Present ICLR 2025