training stability

Cross-Space Synergy: A Unified Framework for Multimodal Emotion Recognition in Conversation AAAI 2026 How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients ACL 2026 MARPO: A Reflective Policy Optimization for Multi-Agent Reinforcement Learning AAAI 2026 Stable and Efficient Single-Rollout RL for Multimodal Reasoning CVPR 2026 A Proactive Reliability Metric for Detecting Failures in Language Model Training EMNLP 2025 Interactive Training: Feedback-Driven Neural Network Optimization EMNLP 2025 MCGAN: Enhancing GAN Training with Regression-Based Generator Loss AAAI 2025 PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs ICLR 2025 SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training ICLR 2025 Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural Gradient NeurIPS 2024 C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory NeurIPS 2024 P2D: Plug and Play Discriminator for Accelerating GAN Frameworks WACV 2024 Stable Language Model Pre-training by Reducing Embedding Variability EMNLP 2024 Tight and Efficient Upper Bound on Spectral Norm of Convolutional Layers ECCV 2024 Why Do We Need Weight Decay in Modern Deep Learning? NeurIPS 2024 Cut your Losses with Squentropy ICML 2023 Implicit Stochastic Gradient Descent for Training Physics-Informed Neural Networks AAAI 2023 Internally Rewarded Reinforcement Learning ICML 2023 LipsFormer: Introducing Lipschitz Continuity to Vision Transformers ICLR 2023 ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection NeurIPS 2023 Stabilizing GANs’ Training with Brownian Motion Controller ICML 2023 Stabilizing Transformer Training by Preventing Attention Entropy Collapse ICML 2023 Deep equilibrium networks are sensitive to initialization statistics ICML 2022 The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models NeurIPS 2022 Towards Understanding Generalization via Decomposing Excess Risk Dynamics ICLR 2022