cross-entropy loss

Every Error has Its Magnitude: Asymmetric Mistake Severity Training for Multiclass Multiple Instance Learning CVPR 2026 Gradient-Guided Multi-Judge Prompt Optimization ACL 2026 MEMO: Human-like Crisp Edge Detection Using Masked Edge Prediction CVPR 2026 RankOOD - Class Ranking-based Out-of-Distribution Detection CVPR 2026 SAT-RRG: LLM-Guided Self-Adaptive Training for Radiology Report Generation with Token-Level Push-Pull Optimization CVPR 2026 Temporal Imbalance of Positive and Negative Supervision in Class-Incremental Learning CVPR 2026 Universality of high-dimensional scaling limits of stochastic gradient descent (extended abstract) COLT 2026 A Two-Head Loss Function for Deep Average-K Classification WACV 2025 BCE vs. CE in Deep Feature Learning ICML 2025 BD at BEA 2025 Shared Task: MPNet Ensembles for Pedagogical Mistake Identification and Localization in AI Tutor Responses ACL 2025 Calibrated Language Models and How to Find Them with Label Smoothing ICML 2025 Challenging Assumptions in Learning Generic Text Style Embeddings NAACL 2025 CMU’s IWSLT 2025 Simultaneous Speech Translation System ACL 2025 Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity ACL 2025 Cut Your Losses in Large-Vocabulary Language Models ICLR 2025 Divergence of Neural Tangent Kernel in Classification Problems ICLR 2025 Enhancing Numerical Prediction of MLLMs with Soft Labeling ICCV 2025 Free Process Rewards without Process Labels ICML 2025 Hierarchical Classification Auxiliary Network for Time Series Forecasting AAAI 2025 Improving Accuracy and Calibration via Differentiated Deep Mutual Learning CVPR 2025 Learning In-context n-grams with Transformers: Sub-n-grams Are Near-Stationary Points ICML 2025 Learning Is Not A Race: Improving Retrieval in Language Models via Equal Learning EMNLP 2025 Loss Functions and Operators Generated by f-Divergences ICML 2025 Low-Rank Adapting Models for Sparse Autoencoders ICML 2025 LSPnet: an ultra-low bitrate hybrid neural codec Interspeech 2025