Neural Network Optimization

ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention AAAI 2025 Visual Self-Refinement for Autoregressive Models EMNLP 2025 Wave-driven Graph Neural Networks with Energy Dynamics for Over-smoothing Mitigation IJCAI 2025 Wavelet-based Positional Representation for Long Context ICLR 2025 Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference NAACL 2025 What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis ICLR 2025 What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective ACL 2025 What Makes Freezing Layers in Deep Neural Networks Effective? A Linear Separability Perspective AutoML 2025 When Long Helps Short: How Context Length in Supervised Fine-tuning Affects Behavior of Large Language Models EMNLP 2025 Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse ICLR 2025 X-KAN: Optimizing Local Kolmogorov-Arnold Networks via Evolutionary Rule-Based Machine Learning IJCAI 2025 YNU-HPCC at SemEval-2025 Task 6: Using BERT Model with R-drop for Promise Verification SemEval 2025 YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model ACL 2025 Zero-cost Proxy for Adversarial Robustness Evaluation ICLR 2025 ZETA: Leveraging Z-order Curves for Efficient Top-k Attention ICLR 2025 $\boldsymbol{\mu}\mathbf{P^2}$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling NeurIPS 2024 1DFormer: A Transformer Architecture Learning 1D Landmark Representations for Facial Landmark Tracking IJCAI 2024 Abrupt Learning in Transformers: A Case Study on Matrix Completion NeurIPS 2024 Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise ICLR 2024 Accurate and Steady Inertial Pose Estimation through Sequence Structure Learning and Modulation NeurIPS 2024 A Comparison of Continuous-Time Approximations to Stochastic Gradient Descent JMLR 2024 Activating Self-Attention for Multi-Scene Absolute Pose Regression NeurIPS 2024 A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning AISTATS 2024 AdaFormer: Efficient Transformer with Adaptive Token Sparsification for Image Super-resolution AAAI 2024 AdaLomo: Low-memory Optimization with Adaptive Learning Rate ACL 2024