model parameter

Bi-Level Optimization for Semi-Supervised Learning with Pseudo-Labeling AAAI 2025 Co-Dream: Collaborative Dream Synthesis over Decentralized Models AAAI 2025 Demystifying the Token Dynamics of Deep Selective State Space Models ICLR 2025 Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps EMNLP 2025 Prompt-based Unifying Inference Attack on Graph Neural Networks AAAI 2025 TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters ICLR 2025 Value Residual Learning ACL 2025 4+3 Phases of Compute-Optimal Neural Scaling Laws NeurIPS 2024 Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts ICML 2024 Massive End-to-end Speech Recognition Models with Time Reduction NAACL 2024 Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective ICLR 2024 Symmetry Induces Structure and Constraint of Learning ICML 2024 Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithms ICML 2024 ULMR: Unlearning Large Language Models via Negative Response and Model Parameter Average EMNLP 2024 Bias Propagation in Federated Learning ICLR 2023 Broken Neural Scaling Laws ICLR 2023 Privacy-Preserving Knowledge Transfer through Partial Parameter Sharing ACL 2023 Provably Robust and Plausible Counterfactual Explanations for Neural Networks via Robust Optimisation ACML 2023 Counterfactual Plans under Distributional Ambiguity ICLR 2022 HODEC: Towards Efficient High-Order DEcomposed Convolutional Neural Networks CVPR 2022 Gradient Driven Rewards to Guarantee Fairness in Collaborative Machine Learning NeurIPS 2021 Learning Curves for Analysis of Deep Networks ICML 2021 Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits ICLR 2021 Double Quantization for Communication-Efficient Distributed Optimization NeurIPS 2019 Regularizing Neural Networks via Stochastic Branch Layers ACML 2019