← authors · overview

• MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration
  2026
• Improving Data and Reward Design for Scientific Reasoning in Large Language Models
  2026
• Table-BiEval: A Self-Supervised, Dual-Track Framework for Decoupling Structure and Content in LLM Evaluation
  2026
• ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models
  2025
• Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models
  2025
• Optimizing Large Language Model Training Using FP4 Quantization
  2025
• Skywork Open Reasoner 1 Technical Report
  2025
• Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training
  2025
• Recycling Pretrained Checkpoints: Orthogonal Growth of Mixture-of-Experts for Efficient Large Language Model Pre-Training
  2025
• Learning from the Best, Differently: A Diversity-Driven Rethinking on Data Selection
  2025
• FP8-LM: Training FP8 Large Language Models
  2023
• Skywork: A More Open Bilingual Foundation Model
  2023
• Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
  2024