parameter space

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin AAAI 2026 Practical Guidelines for Model Merging in LLMs Pre-Training ACL 2026 Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion ICML 2025 Controllable Style Arithmetic with Language Models ACL 2025 CoRA: Collaborative Information Perception by Large Language Model’s Weights for Recommendation AAAI 2025 CoT-Valve: Length-Compressible Chain-of-Thought Tuning ACL 2025 Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning CVPR 2025 Diffusion Models are Evolutionary Algorithms ICLR 2025 Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy ICCV 2025 Flat Reward in Policy Parameter Space Implies Robust Reinforcement Learning ICLR 2025 FuseChat: Knowledge Fusion of Chat Models EMNLP 2025 Lock on Target! Precision Unlearning via Directional Control EMNLP 2025 LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Won’t Fail) ICML 2025 Model Unlearning via Sparse Autoencoder Subspace Guided Projections EMNLP 2025 Wasserstein Gradient Flow over Variational Parameter Space for Variational Inference AISTATS 2025 Graph Metanetworks for Processing Diverse Neural Architectures ICLR 2024 Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis ICML 2024 Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models NeurIPS 2024 On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm ICML 2024 Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning ICLR 2024 Parameterized Physics-informed Neural Networks for Parameterized PDEs ICML 2024 Unleashing the Potential of Large Language Models through Spectral Modulation EMNLP 2024 Better Loss Landscape Visualization for Deep Neural Networks with Trajectory Information ACML 2023 Functional Equivalence and Path Connectivity of Reducible Hyperbolic Tangent Networks NeurIPS 2023 LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification ICLR 2023