Loss Functions

Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks ICLR 2025 Bias-variance decompositions: the exclusive privilege of Bregman divergences JMLR 2025 Binary Losses for Density Ratio Estimation ICLR 2025 Calibrating Language Models for Neural Ranking under Noisy Supervision with Relaxed Labels EMNLP 2025 Calibrating LLMs with Information-Theoretic Evidential Deep Learning ICLR 2025 Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations EMNLP 2025 CaliMatch: Adaptive Calibration for Improving Safe Semi-supervised Learning ICCV 2025 Calm Composite Losses: Being Improper Yet Proper Composite AISTATS 2025 CAMIEval: Enhancing NLG Evaluation through Multidimensional Comparative Instruction-Following Analysis NAACL 2025 CARMA: Enhanced Compositionality in LLMs via Advanced Regularisation and Mutual Information Alignment EMNLP 2025 ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance ICLR 2025 Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model NAACL 2025 CLOC: Contrastive Learning for Ordinal Classification with Multi-Margin N-pair Loss CVPR 2025 Code-switching Mediated Sentence-level Semantic Learning AAAI 2025 COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement IJCAI 2025 COME: Test-time Adaption by Conservatively Minimizing Entropy ICLR 2025 CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward EMNLP 2025 Confidence Calibration in Large Language Model-Based Entity Matching EMNLP 2025 Controlling Language Confusion in Multilingual LLMs ACL 2025 Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling ICLR 2025 Data Unlearning in Diffusion Models ICLR 2025 DCRM: A Heuristic to Measure Response Pair Quality in Preference Optimization EMNLP 2025 Debiased All-in-one Image Restoration with Task Uncertainty Regularization AAAI 2025 Decoupled Imbalanced Label Distribution Learning IJCAI 2025 Difficulty-aware Balancing Margin Loss for Long-tailed Recognition AAAI 2025