Loss Functions

REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation AAAI 2026 Rethinking the Dark Knowledge and Kullback-Leibler Divergence Loss in Knowledge Distillation Under Capacity Mismatching AAAI 2026 Reward Model Evaluation via Automatically-Ranked Policy Alignment AAAI 2026 RI-Loss: A Learnable Residual-Informed Loss for Time Series Forecasting AAAI 2026 Second-Order Bounds for $[0,1]$-Valued Regression via Betting Loss COLT 2026 Thesis proposal: Are We Losing Textual Diversity to Natural Language Processing? EACL 2026 Tractable Sharpness-Aware Learning of Probabilistic Circuits AAAI 2026 Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models WACV 2026 Variation-Bounded Loss for Noise-Tolerant Learning AAAI 2026 AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge NAACL 2025 Adam-mini: Use Fewer Learning Rates To Gain More ICLR 2025 Advancing Community Detection with Graph Convolutional Neural Networks: Bridging Topological and Attributive Cohesion IJCAI 2025 Advancing Loss Functions in Recommender Systems: A Comparative Study with a Rényi Divergence-Based Solution AAAI 2025 Advancing Sequential Numerical Prediction in Autoregressive Models ACL 2025 AQUAFace: Age-Invariant Quality Adaptive Face Recognition for Unconstrained Selfie vs ID Verification AAAI 2025 Are Ensembles Getting Better All the Time? JMLR 2025 A Symmetric Relative-Error Loss Function for Intermittent Multiscale Signal Modelling IJCAI 2025 Attack-inspired Calibration Loss for Calibrating Crack Recognition AAAI 2025 Attention-based Conditional Random Field for Financial Fraud Detection IJCAI 2025 A Two-Head Loss Function for Deep Average-K Classification WACV 2025 A Unified Loss for Handling Inter-Class and Intra-Class Imbalance in Medical Image Segmentation AAAI 2025 Balanced Sharpness-Aware Minimization for Imbalanced Regression ICCV 2025 Balancing Forget Quality and Model Utility: A Reverse KL-Divergence Knowledge Distillation Approach for Better Unlearning in LLMs NAACL 2025 Balancing Two Classifiers via A Simplex ETF Structure for Model Calibration CVPR 2025 Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning CVPR 2025