← Optimization & Theory
Machine Learning › Optimization & Theory ›

Loss Functions

1162 directly classified papers

Papers per year

Papers

DCRM: A Heuristic to Measure Response Pair Quality in Preference Optimization EMNLP 2025
Extending Temperature Scaling with Homogenizing Maps JMLR 2025
CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward EMNLP 2025
PossLoss: A Reliable and Sensitive Facial Landmark Detection Loss Function ICCV 2025
GLEN: Generalized Focal Loss Ensemble of Low-Rank Networks for Calibrated Visual Question Answering AAAI 2025
GT-Mean Loss: A Simple Yet Effective Solution for Brightness Mismatch in Low-Light Image Enhancement ICCV 2025
Improving Accuracy and Calibration via Differentiated Deep Mutual Learning CVPR 2025
Empirical Evaluation of Loss Masking to Selectively Prevent Memorization ACL 2025
Calibrating Language Models for Neural Ranking under Noisy Supervision with Relaxed Labels EMNLP 2025
GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models EMNLP 2025
Confidence Calibration in Large Language Model-Based Entity Matching EMNLP 2025
Group-Aware Reinforcement Learning for Output Diversity in Large Language Models EMNLP 2025
Dynamic Pseudo Labeling via Gradient Cutting for High-Low Entropy Exploration CVPR 2025
Parametric ρ-Norm Scaling Calibration AAAI 2025
Fossils at SemEval-2025 Task 9: Tasting Loss Functions for Food Hazard Detection in Text Reports ACL 2025
SLACE: A Monotone and Balance-Sensitive Loss Function for Ordinal Regression AAAI 2025
Advancing Sequential Numerical Prediction in Autoregressive Models ACL 2025
CARMA: Enhanced Compositionality in LLMs via Advanced Regularisation and Mutual Information Alignment EMNLP 2025
Are Ensembles Getting Better All the Time? JMLR 2025
R-VLM: Region-Aware Vision Language Model for Precise GUI Grounding ACL 2025
DLU: Dictionary Look-Up Data and Prediction CONLL 2025
A Unified Loss for Handling Inter-Class and Intra-Class Imbalance in Medical Image Segmentation AAAI 2025
Proper losses regret at least 1/2-order JMLR 2025
ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning EMNLP 2025
A Two-Head Loss Function for Deep Average-K Classification WACV 2025