Loss Functions

Diverse Preference Learning for Capabilities and Alignment ICLR 2025 DLU: Dictionary Look-Up Data and Prediction CoNLL 2025 DocFusion: A Unified Framework for Document Parsing Tasks ACL 2025 Dynamic Pseudo Labeling via Gradient Cutting for High-Low Entropy Exploration CVPR 2025 Efficiently Selecting Response Generation Strategies for Synthetic Data Construction by Self-Aligned Perplexity EMNLP 2025 Elliptic Loss Regularization ICLR 2025 Empirical Evaluation of Loss Masking to Selectively Prevent Memorization ACL 2025 Enhanced Sample Selection with Confidence Tracking: Identifying Correctly Labeled Yet Hard-to-Learn Samples in Noisy Data AAAI 2025 Enhancing Noise-Robust Losses for Large-Scale Noisy Data Learning AAAI 2025 Enhancing Numerical Prediction of MLLMs with Soft Labeling ICCV 2025 Enhancing Robust Fairness via Confusional Spectral Regularization ICLR 2025 Extending Temperature Scaling with Homogenizing Maps JMLR 2025 Feature Clipping for Uncertainty Calibration AAAI 2025 FEVER-OOD: Free Energy Vulnerability Elimination for Robust Out-of-Distribution Detection ICCV 2025 Fossils at SemEval-2025 Task 9: Tasting Loss Functions for Food Hazard Detection in Text Reports SemEval 2025 GaRAGe: A Benchmark with Grounding Annotations for RAG Evaluation ACL 2025 GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost ICLR 2025 GLEN: Generalized Focal Loss Ensemble of Low-Rank Networks for Calibrated Visual Question Answering AAAI 2025 Group-Aware Reinforcement Learning for Output Diversity in Large Language Models EMNLP 2025 GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models EMNLP 2025 GT-Mean Loss: A Simple Yet Effective Solution for Brightness Mismatch in Low-Light Image Enhancement ICCV 2025 Guardian of the Ensembles: Introducing Pairwise Adversarially Robust Loss for Resisting Adversarial Attacks in DNN Ensembles WACV 2025 Heatmap Regression without Soft-Argmax for Facial Landmark Detection ICCV 2025 Improving Accuracy and Calibration via Differentiated Deep Mutual Learning CVPR 2025 Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles ACL 2025