{"total":30,"rows":[{"id":"2110.04403","title":"Temperature as Uncertainty in Contrastive Learning","created":"2021-10-08","cited_by_count":25,"area":null},{"id":"2302.08692","title":"SAM operates far from home: eigenvalue regularization as a dynamical phenomenon","created":"2023-02-17","cited_by_count":24,"area":null},{"id":"2507.13338","title":"Training Transformers with Enforced Lipschitz Constants","created":"2025-07-17","cited_by_count":20,"area":null},{"id":"2410.04642","title":"The Optimization Landscape of SGD Across the Feature Learning Strength","created":"2024-10-06","cited_by_count":13,"area":null},{"id":"2401.10809","title":"Neglected Hessian component explains mysteries in Sharpness regularization","created":"2024-01-19","cited_by_count":12,"area":null},{"id":"2402.05271","title":"Feature learning as alignment: a structural property of gradient descent in non-linear neural networks","created":"2024-02-07","cited_by_count":10,"area":null},{"id":"2502.20604","title":"Exploring the Impact of Temperature Scaling in Softmax for Classification and Adversarial Robustness","created":"2025-02-28","cited_by_count":9,"area":null},{"id":"2102.03793","title":"Tilting the playing field: Dynamical loss functions for machine learning","created":"2021-02-07","cited_by_count":7,"area":null},{"id":"2404.09232","title":"MAP: Model Aggregation and Personalization in Federated Learning with Incomplete Classes","created":"2024-04-14","cited_by_count":7,"area":null},{"id":"2305.02385","title":"SimSC: A Simple Framework for Semantic Correspondence with Temperature Learning","created":"2023-05-03","cited_by_count":6,"area":null},{"id":"2511.12340","title":"LILogic Net: Compact Logic Gate Networks with Learnable Connectivity for Efficient Hardware Deployment","created":"2025-11-15","cited_by_count":6,"area":null},{"id":"2209.09658","title":"Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty","created":"2022-09-19","cited_by_count":5,"area":null},{"id":"2401.09986","title":"Improving Local Training in Federated Learning via Temperature Scaling","created":"2024-01-18","cited_by_count":5,"area":null},{"id":"2505.14840","title":"Subquadratic Algorithms and Hardness for Attention with Any Temperature","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2402.03579","title":"Deconstructing the Goldilocks Zone of Neural Network Initialization","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2402.17509","title":"Extreme Miscalibration and the Illusion of Adversarial Robustness","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2111.04352","title":"Grassmannian learning mutual subspace method for image set recognition","created":"2021-11-08","cited_by_count":3,"area":null},{"id":"2302.06130","title":"Learning to Scale Temperature in Masked Self-Attention for Image Inpainting","created":"2023-02-13","cited_by_count":3,"area":null},{"id":"2602.06702","title":"Explaining Grokking in Transformers through the Lens of Inductive Bias","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2604.07925","title":"Sinkhorn doubly stochastic attention rank decay analysis","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2410.05757","title":"Temperature Optimization for Bayesian Deep Learning","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2503.02481","title":"A Novel Streamline-based diffusion MRI Tractography Registration Method with Probabilistic Keypoint Detection","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2210.17145","title":"Probability-Dependent Gradient Decay in Large Margin Softmax","created":"2022-10-31","cited_by_count":0,"area":null},{"id":"2504.15594","title":"Analytical Softmax Temperature Setting from Feature Dimensions for Model- and Domain-Robust Classification","created":"2025-04-22","cited_by_count":0,"area":null},{"id":"2505.07430","title":"Comparative sentiment analysis of public perception: Monkeypox vs. COVID-19 behavioral insights","created":"2025-05-12","cited_by_count":0,"area":null},{"id":"2602.00827","title":"Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.06638","title":"Temperature Scaling Attack Disrupting Model Confidence in Federated Learning","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2603.13552","title":"Ghosts of Softmax: Complex Singularities That Limit Safe Step Sizes in Cross-Entropy","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2605.19360","title":"Scalable, Energy-Efficient Optical-Neural Architecture for Multiplexed Deepfake Video Detection","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.28697","title":"Mitigating Batch Effects in Histopathology via Language-Mediated Robust Embedding Generation","created":"2026-06-27","cited_by_count":0,"area":null}],"next_cursor":null}