Representation Learning

Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning ICML 2024 Position: The Platonic Representation Hypothesis ICML 2024 Position: Topological Deep Learning is the New Frontier for Relational Learning ICML 2024 PostureHMR: Posture Transformation for 3D Human Mesh Recovery CVPR 2024 Posture-Informed Muscular Force Learning for Robust Hand Pressure Estimation NeurIPS 2024 PPLNs: Parametric Piecewise Linear Networks for Event-Based Temporal Modeling and Beyond NeurIPS 2024 Predefined Prototypes for Intra-Class Separation and Disentanglement Interspeech 2024 Predicate Sense Disambiguation for UMR Annotation of Latin: Challenges and Insights ACL 2024 Predict but Also Integrate: an Analysis of Sentence Processing Models for English and Hindi ACL 2024 Predicting Atrial Fibrillation Treatment Outcome with Siamese Multi-modal Fusion and Cardiac Digital Twins MIDL 2024 Predicting Future Actions of Reinforcement Learning Agents NeurIPS 2024 Predicting Housing Transaction with Common Covariance GNNs IJCAI 2024 Predicting Label Distribution from Ternary Labels NeurIPS 2024 Predicting Text Preference Via Structured Comparative Reasoning ACL 2024 Prediction from compression for models with infinite memory, with applications to hidden Markov and renewal processes COLT 2024 PredToken: Predicting Unknown Tokens and Beyond with Coarse-to-Fine Iterative Decoding CVPR 2024 Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models ICML 2024 Preprocessing for acoustic-to-articulatory inversion using real-time MRI movies of Japanese speech Interspeech 2024 Preserving Fairness Generalization in Deepfake Detection CVPR 2024 Preserving Image Properties Through Initializations in Diffusion Models WACV 2024 Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality EMNLP 2024 PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks ICLR 2024 Pre-trained Large Language Models Use Fourier Features to Compute Addition NeurIPS 2024 Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control NeurIPS 2024 Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context NeurIPS 2024