Neural Network Optimization

The Role of Outgoing Connection Heterogeneity in Feedforward Layers of Large Language Models EMNLP 2025 The Strawberry Problem: Emergence of Character-level Understanding in Tokenized Language Models EMNLP 2025 The Warmup Dilemma: How Learning Rate Strategies Impact Speech-to-Text Model Convergence ACL 2025 Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints ICCV 2025 Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory CVPR 2025 Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning ACL 2025 Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights CVPR 2025 Transformers without Normalization CVPR 2025 Truncated Consistency Models ICLR 2025 Tuning the Frequencies: Robust Training for Sinusoidal Neural Networks CVPR 2025 Value Residual Learning ACL 2025 Variance Sensitivity Induces Attention Entropy Collapse and Instability in Transformers EMNLP 2025 VI^3NR: Variance Informed Initialization for Implicit Neural Representations CVPR 2025 WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models CVPR 2025 What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective ACL 2025 When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning EMNLP 2025 Where to show Demos in Your Prompt: A Positional Bias of In-Context Learning EMNLP 2025 Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions, Self-Knowingly EMNLP 2025 $\boldsymbol{\mu}\mathbf{P^2}$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling NeurIPS 2024 1-Lipschitz Layers Compared: Memory Speed and Certifiable Robustness CVPR 2024 Abrupt Learning in Transformers: A Case Study on Matrix Completion NeurIPS 2024 Achieving Domain-Independent Certified Robustness via Knowledge Continuity NeurIPS 2024 A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning AISTATS 2024 Adam with model exponential moving average is effective for nonconvex optimization NeurIPS 2024 Adaptive Deep Neural Network Inference Optimization With EENet WACV 2024