"training stability" Papers
14 papers found
Conference
2 OLMo 2 Furious (COLM’s Version)
Evan Pete Walsh, Luca Soldaini, Dirk Groeneveld et al.
COLM 2025paper
A Gradient Guidance Perspective on Stepwise Preference Optimization for Diffusion Models
Joshua Tian Jin Tee, Hee Suk Yoon, Abu Hanif Muhammad Syarubany et al.
NEURIPS 2025oral
EDiT: A Local-SGD-Based Efficient Distributed Training Method for Large Language Models
Jialiang Cheng, Ning Gao, Yun Yue et al.
ICLR 2025arXiv:2412.07210
1
citations
Improving Neural Optimal Transport via Displacement Interpolation
Jaemoo Choi, Yongxin Chen, Jaewoong Choi
ICLR 2025arXiv:2410.03783
3
citations
Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
Jingcheng Hu, Yinmin Zhang, Qi Han et al.
NEURIPS 2025arXiv:2503.24290
347
citations
PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs
Oskar van der Wal, Pietro Lesci, Max Müller-Eberstein et al.
ICLR 2025arXiv:2503.09543
16
citations
Quantum Doubly Stochastic Transformers
Jannis Born, Filip Skogh, Kahn Rhrissorrakrai et al.
NEURIPS 2025spotlightarXiv:2504.16275
2
citations
Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks
Giyeong Oh, Woohyun Cho, Siyeol Kim et al.
NEURIPS 2025arXiv:2505.11881
Sinusoidal Initialization, Time for a New Start
Alberto Fernandez-Hernandez, Jose Mestre, Manuel F. Dolz et al.
NEURIPS 2025arXiv:2505.12909
1
citations
Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation
Zhenxin Lei, Man Yao, Jiakui Hu et al.
AAAI 2025paperarXiv:2412.14587
14
citations
A high-quality robust diffusion framework for corrupted dataset
Quan Dao, Binh Ta, Tung Pham et al.
ECCV 2024arXiv:2311.17101
7
citations
Collage: Light-Weight Low-Precision Strategy for LLM Training
Tao Yu, Gaurav Gupta, KARTHICK GOPALSWAMY et al.
ICML 2024arXiv:2405.03637
8
citations
Learning from Memory: Non-Parametric Memory Augmented Self-Supervised Learning of Visual Features
Thalles Silva, Helio Pedrini, Adín Ramírez Rivera
ICML 2024arXiv:2407.17486
7
citations
Self-Correcting Self-Consuming Loops for Generative Model Training
Nate Gillman, Michael Freeman, Daksh Aggarwal et al.
ICML 2024arXiv:2402.07087
24
citations