Representation Learning

On the Generalization Ability of Next-Token-Prediction Pretraining ICML 2025 On the Guidance of Flow Matching ICML 2025 On the Impact of Noise in Differentially Private Text Rewriting NAACL 2025 On the Importance of Gaussianizing Representations ICML 2025 On the Learning with Augmented Class via Forests IJCAI 2025 On the Provable Importance of Gradients for Autonomous Language-Assisted Image Clustering ICCV 2025 On the Relation Between Fine-Tuning, Topological Properties, and Task Performance in Sense-Enhanced Embeddings ACL 2025 On the Relationship Between Monotone and Squared Probabilistic Circuits AAAI 2025 On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions EMNLP 2025 On the Role of Label Noise in the Feature Learning Process ICML 2025 On the Versatility of Sparse Autoencoders for In-Context Learning EMNLP 2025 Open-Det: An Efficient Learning Framework for Open-Ended Detection ICML 2025 Open Political Corpora: Structuring, Searching, and Analyzing Political Text Collections with PoliCorp EMNLP 2025 Open-world Radio Frequency Fingerprint Identification via Augmented Semi-supervised Learning AAAI 2025 Operator Learning for Hyperbolic PDEs JMLR 2025 OPTICAL: Leveraging Optimal Transport for Contribution Allocation in Dataset Distillation CVPR 2025 Optimal Transport for Brain-Image Alignment: Unveiling Redundancy and Synergy in Neural Information Processing ICCV 2025 Optimized Gradient Clipping for Noisy Label Learning AAAI 2025 Order Doesn’t Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation EMNLP 2025 Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models ICML 2025 Origin Identification for Text-Guided Image-to-Image Diffusion Models ICML 2025 Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection ICML 2025 OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference ICML 2025 Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads ICML 2025 OTCXR: Rethinking Self-Supervised Alignment using Optimal Transport for Chest X-ray Analysis WACV 2025