Representation Learning

THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings AAAI 2025 The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer ICCV 2025 The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities ICLR 2025 The Strawberry Problem: Emergence of Character-level Understanding in Tokenized Language Models EMNLP 2025 The Surprising Effectiveness of Infinite-Width NTKs for Characterizing and Improving Model Training AAAI 2025 The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data ICML 2025 The Transfer Neurons Hypothesis: An Underlying Mechanism for Language Latent Space Transitions in Multilingual LLMs EMNLP 2025 The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training ICML 2025 THGNets: Constrained Temporal Hypergraphs and Graph Neural Networks in Hyperbolic Space for Information Diffusion Prediction AAAI 2025 Think Both Ways: Teacher-Student Bidirectional Reasoning Enhances MCQ Generation and Distractor Quality ACL 2025 ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models EMNLP 2025 Thin-Plate Spline-based Interpolation for Animation Line Inbetweening AAAI 2025 Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with Neural Deformation Fields CVPR 2025 t-HNE: A Text-guided Hierarchical Noise Eliminator for Multimodal Sentiment Analysis COLING 2025 THOR-MoE: Hierarchical Task-Guided and Context-Responsive Routing for Neural Machine Translation ACL 2025 Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classifications AAAI 2025 TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining ACL 2025 TicTac: Time-aware Supervised Fine-tuning for Automatic Text Dating ACL 2025 TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction CVPR 2025 Tight Clusters Make Specialized Experts ICLR 2025 TimeBooth: Disentangled Facial Invariant Representation for Diverse and Personalized Face Aging ICCV 2025 TimeCHEAT: A Channel Harmony Strategy for Irregularly Sampled Multivariate Time Series Analysis AAAI 2025 TIME-FS: Joint Learning of Tensorial Incomplete Multi-View Unsupervised Feature Selection and Missing-View Imputation AAAI 2025 TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis ICLR 2025 Time Series Representations with Hard-Coded Invariances ICML 2025