cross-entropy loss

MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces IJCAI 2025 Maintaining Fairness in Logit-based Knowledge Distillation for Class-Incremental Learning AAAI 2025 Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification ICLR 2025 On the Sample Complexity of Next-Token Prediction AISTATS 2025 Optimizing Pre-Training Data Mixtures with Mixtures of Data Expert Models ACL 2025 Preserving Diversity in Supervised Fine-Tuning of Large Language Models ICLR 2025 Provable In-Context Vector Arithmetic via Retrieving Task Concepts ICML 2025 Regress, Don’t Guess: A Regression-like Loss on Number Tokens for Language Models ICML 2025 Relating Misfit to Gain in Weak-to-Strong Generalization Beyond the Squared Loss ICML 2025 Stop Jostling: Adaptive Negative Sampling Reduces the Marginalization of Low-Resource Language Tokens by Cross-Entropy Loss COLING 2025 Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales ICML 2025 Task-Specific Gradient Adaptation for Few-Shot One-Class Classification CVPR 2025 The Impact Label Noise and Choice of Threshold has on Cross-Entropy and Soft-Dice in Image Segmentation CVPR 2025 Training Deep Neural Networks with Virtual Smoothing Classes AAAI 2025 Uncovering Latent Memories in Large Language Models ICLR 2025 Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models ICML 2025 What is Wrong with Perplexity for Long-context Language Modeling? ICLR 2025 Accuracy-Preserving Calibration via Statistical Modeling on Probability Simplex AISTATS 2024 Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching CVPR 2024 An Analysis of Tokenization: Transformers under Markov Data NeurIPS 2024 Anisotropy Is Inherent to Self-Attention in Transformers EACL 2024 Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning EMNLP 2024 BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens NeurIPS 2024 Classification with Deep Neural Networks and Logistic Loss JMLR 2024 Consistent and Asymptotically Unbiased Estimation of Proper Calibration Errors AISTATS 2024