Loss Functions

Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue EMNLP 2024 Reward (Mis)design for Autonomous Driving (Abstract Reprint) AAAI 2024 Reward Modeling Requires Automatic Adjustment Based on Data Quality EMNLP 2024 ROUGE-K: Do Your Summaries Have Keywords? NAACL 2024 Scalable Geometric Fracture Assembly via Co-creation Space among Assemblers AAAI 2024 Scaling laws for learning with real and surrogate data NeurIPS 2024 Scoring with Confidence? – Exploring High-confidence Scoring for Saving Manual Grading Effort NAACL 2024 SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects CVPR 2024 Self-Calibrating Vicinal Risk Minimisation for Model Calibration CVPR 2024 Self-Distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approach AAAI 2024 Sequence Reducible Holdout Loss for Language Model Pretraining COLING 2024 Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement CVPR 2024 Soft metrics for evaluation with disagreements: an assessment COLING 2024 Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluation CVPR 2024 Speech dereverberation constrained on room impulse response characteristics Interspeech 2024 ST$_k$: A Scalable Module for Solving Top-k Problems NeurIPS 2024 Suppressing Uncertainty in Gaze Estimation AAAI 2024 Surrogate Bayesian Networks for Approximating Evolutionary Games AISTATS 2024 Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning AAAI 2024 SYSTRAN @ WMT24 Non-Repetitive Translation Task EMNLP 2024 The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective JMLR 2024 Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention AISTATS 2024 The Role of n-gram Smoothing in the Age of Neural Networks NAACL 2024 Threshold-Consistent Margin Loss for Open-World Deep Metric Learning ICLR 2024 TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback ACL 2024