loss landscape

A Better Start: Sensitivity-Aware Warm-Up for Robust and Efficient Fine-Tuning AAAI 2026 Beyond Sharpness: A Flatness Decomposition Framework for Efficient Continual Learning AAAI 2026 Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias AAAI 2026 FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction CVPR 2026 GDFA: Geometry-Driven Federated Unlearning with Directional Task Vector Alignment CVPR 2026 Globscope: Toward a Global View of the Loss Landscape CVPR 2026 Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via Data-Free Flatness-Aware Prompt Pretraining CVPR 2026 Perturbing to Preserve: Defending Fragile Knowledge in Online Continual Learning AAAI 2026 Prompting Adversarial Transferability via Path Flatness Attack AAAI 2026 Random Amalgamation of Adapters for Flatter Loss Landscapes: Towards Class-Incremental Learning with Better Stability AAAI 2026 Reframing Long-Tailed Learning via Loss Landscape Geometry CVPR 2026 Super Level Sets and Exponential Decay: A Synergistic Approach to Stable Neural Network Training (Abstract Reprint) AAAI 2026 Adam Exploits ℓ_∞-geometry of Loss Landscape via Coordinate-wise Adaptivity ICLR 2025 Attention with Markov: A Curious Case of Single-layer Transformers ICLR 2025 A Unified Theory of Quantum Neural Network Loss Landscapes ICLR 2025 Boosting Adversarial Transferability via Negative Hessian Trace Regularization ICCV 2025 Boosting Adversarial Transferability via Residual Perturbation Attack ICCV 2025 Enhancing Adversarial Transferability by Balancing Exploration and Exploitation with Gradient-Guided Sampling ICCV 2025 Enhancing Language Model Hypernetworks with Restart: A Study on Optimization NAACL 2025 Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality ICLR 2025 Gradient-Guided Annealing for Domain Generalization CVPR 2025 How Far Are We from True Unlearnability? ICLR 2025 Improving Generalization of Deep Neural Networks by Optimum Shifting AAAI 2025 Input Space Mode Connectivity in Deep Neural Networks ICLR 2025 Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding ICLR 2025