Neural Network Optimization

Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble ICML 2025 Propulsion: Steering LLM with Tiny Fine-Tuning COLING 2025 Provable In-Context Vector Arithmetic via Retrieving Task Concepts ICML 2025 Pruning Large Language Models with Semi-Structural Adaptive Sparse Training AAAI 2025 QiMLP: Quantum-inspired Multilayer Perceptron with Strong Correlation Mining and Parameter Compression AAAI 2025 Quantum-Infused Whisper: A Framework for Replacing Classical Components AACL 2025 Random Pruning Over-parameterized Neural Networks Can Improve Generalization: A Training Dynamics Analysis JMLR 2025 Reasoning with Latent Thoughts: On the Power of Looped Transformers ICLR 2025 ReAttention: Training-Free Infinite Context with Finite Attention Scope ICLR 2025 Reducing Divergence in Batch Normalization for Domain Adaptation AAAI 2025 RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs ACL 2025 Refined generalization analysis of the Deep Ritz Method and Physics-Informed Neural Networks ICML 2025 Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models ACL 2025 ReGLA: Refining Gated Linear Attention NAACL 2025 ReMamba: Equip Mamba with Effective Long-Sequence Modeling EMNLP 2025 Remove Symmetries to Control Model Expressivity and Improve Optimization ICLR 2025 Rethinking the Role of Text Complexity in Language Model Pretraining EMNLP 2025 Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-up ACL 2025 Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment ICCV 2025 Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration JMLR 2025 Revisit Micro-batch Clipping: Adaptive Data Pruning via Gradient Manipulation ICLR 2025 Robust and Adaptive AI Models for Medication Usage Forecasting Using ICD-9/10 Code (Student Abstract) AAAI 2025 Robust Weight Initialization for Tanh Neural Networks with Fixed Point Analysis ICLR 2025 RTdetector: Deep Transformer Networks for Time Series Anomaly Detection Based on Reconstruction Trend IJCAI 2025 s1: Simple test-time scaling EMNLP 2025