conftrace_

training stability

36 papers

Explore in graph

Co-occurring keywords

generative adversarial network (1944) neural network optimization (1293) neural network (6616) control theory (31) image generation (2073) stochastic gradient descent (1091) gan training (21) mode collapse (102) training instability (11) large language model (13587)

Papers

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
Cross-Space Synergy: A Unified Framework for Multimodal Emotion Recognition in Conversation AAAI 2026
Interactive Training: Feedback-Driven Neural Network Optimization EMNLP 2025
A Proactive Reliability Metric for Detecting Failures in Language Model Training EMNLP 2025
MCGAN: Enhancing GAN Training with Regression-Based Generator Loss AAAI 2025
Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural Gradient NIPS 2024
Stable Language Model Pre-training by Reducing Embedding Variability EMNLP 2024
P2D: Plug and Play Discriminator for Accelerating GAN Frameworks WACV 2024
Why Do We Need Weight Decay in Modern Deep Learning? NIPS 2024
C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory NIPS 2024
Implicit Stochastic Gradient Descent for Training Physics-Informed Neural Networks AAAI 2023
Stabilizing GANs’ Training with Brownian Motion Controller ICML 2023
ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection NIPS 2023
Stabilizing Transformer Training by Preventing Attention Entropy Collapse ICML 2023
Internally Rewarded Reinforcement Learning ICML 2023
Cut your Losses with Squentropy ICML 2023
The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models NIPS 2022
Deep equilibrium networks are sensitive to initialization statistics ICML 2022
Uncertainty-aware Binary Neural Networks IJCAI 2021
Adaptive Weighted Discriminator for Training Generative Adversarial Networks CVPR 2021
GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training NIPS 2021
An Empirical Study of Training Self-Supervised Vision Transformers ICCV 2021
Improved Contrastive Divergence Training of Energy-Based Models ICML 2021
Orthogonal Convolutional Neural Networks CVPR 2020