Representation Learning

Out-of-Distribution Detection with Prototypical Outlier Proxy AAAI 2025 Out-of-Distribution Generalization on Graphs via Progressive Inference AAAI 2025 OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature EMNLP 2025 Parameter-Aware Contrastive Knowledge Editing: Tracing and Rectifying based on Critical Transmission Paths ACL 2025 Patch-wise Structural Loss for Time Series Forecasting ICML 2025 PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models CVPR 2025 Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios NAACL 2025 Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics CVPR 2025 Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment ACL 2025 Personality Vector: Modulating Personality of Large Language Models by Model Merging EMNLP 2025 Physics-Informed DeepONets for drift-diffusion on metric graphs: simulation and parameter identification ICML 2025 Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts EMNLP 2025 PlaNet: Learning to Mitigate Atmospheric Turbulence in Planetary Images AAAI 2025 Planning-Aware Code Infilling via Horizon-Length Prediction EMNLP 2025 Point-Level Topological Representation Learning on Point Clouds ICML 2025 Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications ICML 2025 PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment ACL 2025 Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research ICML 2025 Position: Deep Learning is Not So Mysterious or Different ICML 2025 Potential Field Based Deep Metric Learning CVPR 2025 PQR: Improving Dense Retrieval via Potential Query Modeling ACL 2025 Pre-trained Language Models Learn Remarkably Accurate Representations of Numbers EMNLP 2025 PRISM: A Framework for Producing Interpretable Political Bias Embeddings with Political-Aware Cross-Encoder ACL 2025 Privacy-Preserving Speaker Verification via End-to-End Secure Representation Learning Interspeech 2025 Probing for Arithmetic Errors in Language Models EMNLP 2025