gradient analysis

Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders EMNLP 2025 Gradient Short-Circuit: Efficient Out-of-Distribution Detection via Feature Intervention ICCV 2025 On the Provable Importance of Gradients for Autonomous Language-Assisted Image Clustering ICCV 2025 Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It ICLR 2025 Tuned Contrastive Learning WACV 2025 What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective ACL 2025 Backward Lens: Projecting Language Model Gradients into the Vocabulary Space EMNLP 2024 GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis ACL 2024 In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models EMNLP 2024 ReGCL: Rethinking Message Passing in Graph Contrastive Learning AAAI 2024 Towards Better Understanding of Contrastive Sentence Representation Learning: A Unified Paradigm for Gradient ACL 2024 Understanding the Expressivity and Trainability of Fourier Neural Operator: A Mean-Field Perspective NeurIPS 2024 Dissecting Deep Metric Learning Losses for Image-Text Retrieval WACV 2023 Expected Gradients of Maxout Networks and Consequences to Parameter Initialization ICML 2023 Initialization Noise in Image Gradients and Saliency Maps CVPR 2023 Multi-Metrics Adaptively Identifies Backdoors in Federated Learning ICCV 2023 Rethinking Interpretation: Input-Agnostic Saliency Mapping of Deep Visual Classifiers AAAI 2023 Towards Understanding Generalization of Graph Neural Networks ICML 2023 ZiCo: Zero-shot NAS via inverse Coefficient of Variation on Gradients ICLR 2023 CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task EMNLP 2022 How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning ICLR 2022 When Does Differentially Private Learning Not Suffer in High Dimensions? NeurIPS 2022 Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions AAAI 2021 Efficiently Identifying Task Groupings for Multi-Task Learning NeurIPS 2021 Why Spectral Normalization Stabilizes GANs: Analysis and Improvements NeurIPS 2021